A proteomic survival predictor for COVID-19 patients in intensive care

Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors. Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Vadim Demichev [verfasserIn] Pinkus Tober-Lau [verfasserIn] Tatiana Nazarenko [verfasserIn] Oliver Lemke [verfasserIn] Simran Kaur Aulakh [verfasserIn] Harry J. Whitwell [verfasserIn] Annika Röhl [verfasserIn] Anja Freiwald [verfasserIn] Mirja Mittermaier [verfasserIn] Lukasz Szyrwiel [verfasserIn] Daniela Ludwig [verfasserIn] Clara Correia-Melo [verfasserIn] Lena J. Lippert [verfasserIn] Elisa T. Helbig [verfasserIn] Paula Stubbemann [verfasserIn] Nadine Olk [verfasserIn] Charlotte Thibeault [verfasserIn] Nana-Maria Grüning [verfasserIn] Oleg Blyuss [verfasserIn] Spyros Vernardis [verfasserIn] Matthew White [verfasserIn] Christoph B. Messner [verfasserIn] Michael Joannidis [verfasserIn] Thomas Sonnweber [verfasserIn] Sebastian J. Klein [verfasserIn] Alex Pizzini [verfasserIn] Yvonne Wohlfarter [verfasserIn] Sabina Sahanic [verfasserIn] Richard Hilbe [verfasserIn] Benedikt Schaefer [verfasserIn] Sonja Wagner [verfasserIn] Felix Machleidt [verfasserIn] Carmen Garcia [verfasserIn] Christoph Ruwwe-Glösenkamp [verfasserIn] Tilman Lingscheid [verfasserIn] Laure Bosquillon de Jarcy [verfasserIn] Miriam S. Stegemann [verfasserIn] Moritz Pfeiffer [verfasserIn] Linda Jürgens [verfasserIn] Sophy Denker [verfasserIn] Daniel Zickler [verfasserIn] Claudia Spies [verfasserIn] Andreas Edel [verfasserIn] Nils B. Müller [verfasserIn] Philipp Enghard [verfasserIn] Aleksej Zelezniak [verfasserIn] Rosa Bellmann-Weiler [verfasserIn] Günter Weiss [verfasserIn] Archie Campbell [verfasserIn] Caroline Hayward [verfasserIn] David J. Porteous [verfasserIn] Riccardo E. Marioni [verfasserIn] Alexander Uhrig [verfasserIn] Heinz Zoller [verfasserIn] Judith Löffler-Ragg [verfasserIn] Markus A. Keller [verfasserIn] Ivan Tancevski [verfasserIn] John F. Timms [verfasserIn] Alexey Zaikin [verfasserIn] Stefan Hippenstiel [verfasserIn] Michael Ramharter [verfasserIn] Holger Müller-Redetzky [verfasserIn] Martin Witzenrath [verfasserIn] Norbert Suttorp [verfasserIn] Kathryn Lilley [verfasserIn] Michael Mülleder [verfasserIn] Leif Erik Sander [verfasserIn] Florian Kurth [verfasserIn] Markus Ralser [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Übergeordnetes Werk:	In: PLOS Digital Health - Public Library of Science (PLoS), 2022, 1(2022), 1
Übergeordnetes Werk:	volume:1 ; year:2022 ; number:1

Links:	Link aufrufen Link aufrufen Journal toc

Katalog-ID:	DOAJ081861427

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ081861427
003	DE-627
005	20230502075257.0
007	cr uuu---uuuuu
008	230310s2022 xx \|\|\|\|\|o 00\| \|\|eng c
035			\|a (DE-627)DOAJ081861427
035			\|a (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a R858-859.7
100	0		\|a Vadim Demichev \|e verfasserin \|4 aut
245	1	2	\|a A proteomic survival predictor for COVID-19 patients in intensive care
264		1	\|c 2022
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors.
653		0	\|a Computer applications to medicine. Medical informatics
700	0		\|a Pinkus Tober-Lau \|e verfasserin \|4 aut
700	0		\|a Tatiana Nazarenko \|e verfasserin \|4 aut
700	0		\|a Oliver Lemke \|e verfasserin \|4 aut
700	0		\|a Simran Kaur Aulakh \|e verfasserin \|4 aut
700	0		\|a Harry J. Whitwell \|e verfasserin \|4 aut
700	0		\|a Annika Röhl \|e verfasserin \|4 aut
700	0		\|a Anja Freiwald \|e verfasserin \|4 aut
700	0		\|a Mirja Mittermaier \|e verfasserin \|4 aut
700	0		\|a Lukasz Szyrwiel \|e verfasserin \|4 aut
700	0		\|a Daniela Ludwig \|e verfasserin \|4 aut
700	0		\|a Clara Correia-Melo \|e verfasserin \|4 aut
700	0		\|a Lena J. Lippert \|e verfasserin \|4 aut
700	0		\|a Elisa T. Helbig \|e verfasserin \|4 aut
700	0		\|a Paula Stubbemann \|e verfasserin \|4 aut
700	0		\|a Nadine Olk \|e verfasserin \|4 aut
700	0		\|a Charlotte Thibeault \|e verfasserin \|4 aut
700	0		\|a Nana-Maria Grüning \|e verfasserin \|4 aut
700	0		\|a Oleg Blyuss \|e verfasserin \|4 aut
700	0		\|a Spyros Vernardis \|e verfasserin \|4 aut
700	0		\|a Matthew White \|e verfasserin \|4 aut
700	0		\|a Christoph B. Messner \|e verfasserin \|4 aut
700	0		\|a Michael Joannidis \|e verfasserin \|4 aut
700	0		\|a Thomas Sonnweber \|e verfasserin \|4 aut
700	0		\|a Sebastian J. Klein \|e verfasserin \|4 aut
700	0		\|a Alex Pizzini \|e verfasserin \|4 aut
700	0		\|a Yvonne Wohlfarter \|e verfasserin \|4 aut
700	0		\|a Sabina Sahanic \|e verfasserin \|4 aut
700	0		\|a Richard Hilbe \|e verfasserin \|4 aut
700	0		\|a Benedikt Schaefer \|e verfasserin \|4 aut
700	0		\|a Sonja Wagner \|e verfasserin \|4 aut
700	0		\|a Felix Machleidt \|e verfasserin \|4 aut
700	0		\|a Carmen Garcia \|e verfasserin \|4 aut
700	0		\|a Christoph Ruwwe-Glösenkamp \|e verfasserin \|4 aut
700	0		\|a Tilman Lingscheid \|e verfasserin \|4 aut
700	0		\|a Laure Bosquillon de Jarcy \|e verfasserin \|4 aut
700	0		\|a Miriam S. Stegemann \|e verfasserin \|4 aut
700	0		\|a Moritz Pfeiffer \|e verfasserin \|4 aut
700	0		\|a Linda Jürgens \|e verfasserin \|4 aut
700	0		\|a Sophy Denker \|e verfasserin \|4 aut
700	0		\|a Daniel Zickler \|e verfasserin \|4 aut
700	0		\|a Claudia Spies \|e verfasserin \|4 aut
700	0		\|a Andreas Edel \|e verfasserin \|4 aut
700	0		\|a Nils B. Müller \|e verfasserin \|4 aut
700	0		\|a Philipp Enghard \|e verfasserin \|4 aut
700	0		\|a Aleksej Zelezniak \|e verfasserin \|4 aut
700	0		\|a Rosa Bellmann-Weiler \|e verfasserin \|4 aut
700	0		\|a Günter Weiss \|e verfasserin \|4 aut
700	0		\|a Archie Campbell \|e verfasserin \|4 aut
700	0		\|a Caroline Hayward \|e verfasserin \|4 aut
700	0		\|a David J. Porteous \|e verfasserin \|4 aut
700	0		\|a Riccardo E. Marioni \|e verfasserin \|4 aut
700	0		\|a Alexander Uhrig \|e verfasserin \|4 aut
700	0		\|a Heinz Zoller \|e verfasserin \|4 aut
700	0		\|a Judith Löffler-Ragg \|e verfasserin \|4 aut
700	0		\|a Markus A. Keller \|e verfasserin \|4 aut
700	0		\|a Ivan Tancevski \|e verfasserin \|4 aut
700	0		\|a John F. Timms \|e verfasserin \|4 aut
700	0		\|a Alexey Zaikin \|e verfasserin \|4 aut
700	0		\|a Stefan Hippenstiel \|e verfasserin \|4 aut
700	0		\|a Michael Ramharter \|e verfasserin \|4 aut
700	0		\|a Holger Müller-Redetzky \|e verfasserin \|4 aut
700	0		\|a Martin Witzenrath \|e verfasserin \|4 aut
700	0		\|a Norbert Suttorp \|e verfasserin \|4 aut
700	0		\|a Kathryn Lilley \|e verfasserin \|4 aut
700	0		\|a Michael Mülleder \|e verfasserin \|4 aut
700	0		\|a Leif Erik Sander \|e verfasserin \|4 aut
700	0		\|a Florian Kurth \|e verfasserin \|4 aut
700	0		\|a Markus Ralser \|e verfasserin \|4 aut
773	0	8	\|i In \|t PLOS Digital Health \|d Public Library of Science (PLoS), 2022 \|g 1(2022), 1 \|w (DE-627)1786633930 \|w (DE-600)3106944-7 \|x 27673170 \|7 nnns
773	1	8	\|g volume:1 \|g year:2022 \|g number:1
856	4	0	\|u https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 \|z kostenfrei
856	4	0	\|u https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2767-3170 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a SSG-OLC-PHA
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_73
912			\|a GBV_ILN_74
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_206
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2001
912			\|a GBV_ILN_2003
912			\|a GBV_ILN_2005
912			\|a GBV_ILN_2009
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2522
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 1 \|j 2022 \|e 1

Indexfelder

author_variant	v d vd p t l ptl t n tn o l ol s k a ska h j w hjw a r ar a f af m m mm l s ls d l dl c c m ccm l j l ljl e t h eth p s ps n o no c t ct n m g nmg o b ob s v sv m w mw c b m cbm m j mj t s ts s j k sjk a p ap y w yw s s ss r h rh b s bs s w sw f m fm c g cg c r g crg t l tl l b d j lbdj m s s mss m p mp l j lj s d sd d z dz c s cs a e ae n b m nbm p e pe a z az r b w rbw g w gw a c ac c h ch d j p djp r e m rem a u au h z hz j l r jlr m a k mak i t it j f t jft a z az s h sh m r mr h m r hmr m w mw n s ns k l kl m m mm l e s les f k fk m r mr
matchkey_str	article:27673170:2022----::poemcuvvlrdcofroi1ptet
hierarchy_sort_str	2022
callnumber-subject-code	R
publishDate	2022
allfields	(DE-627)DOAJ081861427 (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7 DE-627 ger DE-627 rakwb eng R858-859.7 Vadim Demichev verfasserin aut A proteomic survival predictor for COVID-19 patients in intensive care 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors. Computer applications to medicine. Medical informatics Pinkus Tober-Lau verfasserin aut Tatiana Nazarenko verfasserin aut Oliver Lemke verfasserin aut Simran Kaur Aulakh verfasserin aut Harry J. Whitwell verfasserin aut Annika Röhl verfasserin aut Anja Freiwald verfasserin aut Mirja Mittermaier verfasserin aut Lukasz Szyrwiel verfasserin aut Daniela Ludwig verfasserin aut Clara Correia-Melo verfasserin aut Lena J. Lippert verfasserin aut Elisa T. Helbig verfasserin aut Paula Stubbemann verfasserin aut Nadine Olk verfasserin aut Charlotte Thibeault verfasserin aut Nana-Maria Grüning verfasserin aut Oleg Blyuss verfasserin aut Spyros Vernardis verfasserin aut Matthew White verfasserin aut Christoph B. Messner verfasserin aut Michael Joannidis verfasserin aut Thomas Sonnweber verfasserin aut Sebastian J. Klein verfasserin aut Alex Pizzini verfasserin aut Yvonne Wohlfarter verfasserin aut Sabina Sahanic verfasserin aut Richard Hilbe verfasserin aut Benedikt Schaefer verfasserin aut Sonja Wagner verfasserin aut Felix Machleidt verfasserin aut Carmen Garcia verfasserin aut Christoph Ruwwe-Glösenkamp verfasserin aut Tilman Lingscheid verfasserin aut Laure Bosquillon de Jarcy verfasserin aut Miriam S. Stegemann verfasserin aut Moritz Pfeiffer verfasserin aut Linda Jürgens verfasserin aut Sophy Denker verfasserin aut Daniel Zickler verfasserin aut Claudia Spies verfasserin aut Andreas Edel verfasserin aut Nils B. Müller verfasserin aut Philipp Enghard verfasserin aut Aleksej Zelezniak verfasserin aut Rosa Bellmann-Weiler verfasserin aut Günter Weiss verfasserin aut Archie Campbell verfasserin aut Caroline Hayward verfasserin aut David J. Porteous verfasserin aut Riccardo E. Marioni verfasserin aut Alexander Uhrig verfasserin aut Heinz Zoller verfasserin aut Judith Löffler-Ragg verfasserin aut Markus A. Keller verfasserin aut Ivan Tancevski verfasserin aut John F. Timms verfasserin aut Alexey Zaikin verfasserin aut Stefan Hippenstiel verfasserin aut Michael Ramharter verfasserin aut Holger Müller-Redetzky verfasserin aut Martin Witzenrath verfasserin aut Norbert Suttorp verfasserin aut Kathryn Lilley verfasserin aut Michael Mülleder verfasserin aut Leif Erik Sander verfasserin aut Florian Kurth verfasserin aut Markus Ralser verfasserin aut In PLOS Digital Health Public Library of Science (PLoS), 2022 1(2022), 1 (DE-627)1786633930 (DE-600)3106944-7 27673170 nnns volume:1 year:2022 number:1 https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 kostenfrei https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI kostenfrei https://doaj.org/toc/2767-3170 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2014 GBV_ILN_2522 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 1 2022 1
spelling	(DE-627)DOAJ081861427 (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7 DE-627 ger DE-627 rakwb eng R858-859.7 Vadim Demichev verfasserin aut A proteomic survival predictor for COVID-19 patients in intensive care 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors. Computer applications to medicine. Medical informatics Pinkus Tober-Lau verfasserin aut Tatiana Nazarenko verfasserin aut Oliver Lemke verfasserin aut Simran Kaur Aulakh verfasserin aut Harry J. Whitwell verfasserin aut Annika Röhl verfasserin aut Anja Freiwald verfasserin aut Mirja Mittermaier verfasserin aut Lukasz Szyrwiel verfasserin aut Daniela Ludwig verfasserin aut Clara Correia-Melo verfasserin aut Lena J. Lippert verfasserin aut Elisa T. Helbig verfasserin aut Paula Stubbemann verfasserin aut Nadine Olk verfasserin aut Charlotte Thibeault verfasserin aut Nana-Maria Grüning verfasserin aut Oleg Blyuss verfasserin aut Spyros Vernardis verfasserin aut Matthew White verfasserin aut Christoph B. Messner verfasserin aut Michael Joannidis verfasserin aut Thomas Sonnweber verfasserin aut Sebastian J. Klein verfasserin aut Alex Pizzini verfasserin aut Yvonne Wohlfarter verfasserin aut Sabina Sahanic verfasserin aut Richard Hilbe verfasserin aut Benedikt Schaefer verfasserin aut Sonja Wagner verfasserin aut Felix Machleidt verfasserin aut Carmen Garcia verfasserin aut Christoph Ruwwe-Glösenkamp verfasserin aut Tilman Lingscheid verfasserin aut Laure Bosquillon de Jarcy verfasserin aut Miriam S. Stegemann verfasserin aut Moritz Pfeiffer verfasserin aut Linda Jürgens verfasserin aut Sophy Denker verfasserin aut Daniel Zickler verfasserin aut Claudia Spies verfasserin aut Andreas Edel verfasserin aut Nils B. Müller verfasserin aut Philipp Enghard verfasserin aut Aleksej Zelezniak verfasserin aut Rosa Bellmann-Weiler verfasserin aut Günter Weiss verfasserin aut Archie Campbell verfasserin aut Caroline Hayward verfasserin aut David J. Porteous verfasserin aut Riccardo E. Marioni verfasserin aut Alexander Uhrig verfasserin aut Heinz Zoller verfasserin aut Judith Löffler-Ragg verfasserin aut Markus A. Keller verfasserin aut Ivan Tancevski verfasserin aut John F. Timms verfasserin aut Alexey Zaikin verfasserin aut Stefan Hippenstiel verfasserin aut Michael Ramharter verfasserin aut Holger Müller-Redetzky verfasserin aut Martin Witzenrath verfasserin aut Norbert Suttorp verfasserin aut Kathryn Lilley verfasserin aut Michael Mülleder verfasserin aut Leif Erik Sander verfasserin aut Florian Kurth verfasserin aut Markus Ralser verfasserin aut In PLOS Digital Health Public Library of Science (PLoS), 2022 1(2022), 1 (DE-627)1786633930 (DE-600)3106944-7 27673170 nnns volume:1 year:2022 number:1 https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 kostenfrei https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI kostenfrei https://doaj.org/toc/2767-3170 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2014 GBV_ILN_2522 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 1 2022 1
allfields_unstemmed	(DE-627)DOAJ081861427 (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7 DE-627 ger DE-627 rakwb eng R858-859.7 Vadim Demichev verfasserin aut A proteomic survival predictor for COVID-19 patients in intensive care 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors. Computer applications to medicine. Medical informatics Pinkus Tober-Lau verfasserin aut Tatiana Nazarenko verfasserin aut Oliver Lemke verfasserin aut Simran Kaur Aulakh verfasserin aut Harry J. Whitwell verfasserin aut Annika Röhl verfasserin aut Anja Freiwald verfasserin aut Mirja Mittermaier verfasserin aut Lukasz Szyrwiel verfasserin aut Daniela Ludwig verfasserin aut Clara Correia-Melo verfasserin aut Lena J. Lippert verfasserin aut Elisa T. Helbig verfasserin aut Paula Stubbemann verfasserin aut Nadine Olk verfasserin aut Charlotte Thibeault verfasserin aut Nana-Maria Grüning verfasserin aut Oleg Blyuss verfasserin aut Spyros Vernardis verfasserin aut Matthew White verfasserin aut Christoph B. Messner verfasserin aut Michael Joannidis verfasserin aut Thomas Sonnweber verfasserin aut Sebastian J. Klein verfasserin aut Alex Pizzini verfasserin aut Yvonne Wohlfarter verfasserin aut Sabina Sahanic verfasserin aut Richard Hilbe verfasserin aut Benedikt Schaefer verfasserin aut Sonja Wagner verfasserin aut Felix Machleidt verfasserin aut Carmen Garcia verfasserin aut Christoph Ruwwe-Glösenkamp verfasserin aut Tilman Lingscheid verfasserin aut Laure Bosquillon de Jarcy verfasserin aut Miriam S. Stegemann verfasserin aut Moritz Pfeiffer verfasserin aut Linda Jürgens verfasserin aut Sophy Denker verfasserin aut Daniel Zickler verfasserin aut Claudia Spies verfasserin aut Andreas Edel verfasserin aut Nils B. Müller verfasserin aut Philipp Enghard verfasserin aut Aleksej Zelezniak verfasserin aut Rosa Bellmann-Weiler verfasserin aut Günter Weiss verfasserin aut Archie Campbell verfasserin aut Caroline Hayward verfasserin aut David J. Porteous verfasserin aut Riccardo E. Marioni verfasserin aut Alexander Uhrig verfasserin aut Heinz Zoller verfasserin aut Judith Löffler-Ragg verfasserin aut Markus A. Keller verfasserin aut Ivan Tancevski verfasserin aut John F. Timms verfasserin aut Alexey Zaikin verfasserin aut Stefan Hippenstiel verfasserin aut Michael Ramharter verfasserin aut Holger Müller-Redetzky verfasserin aut Martin Witzenrath verfasserin aut Norbert Suttorp verfasserin aut Kathryn Lilley verfasserin aut Michael Mülleder verfasserin aut Leif Erik Sander verfasserin aut Florian Kurth verfasserin aut Markus Ralser verfasserin aut In PLOS Digital Health Public Library of Science (PLoS), 2022 1(2022), 1 (DE-627)1786633930 (DE-600)3106944-7 27673170 nnns volume:1 year:2022 number:1 https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 kostenfrei https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI kostenfrei https://doaj.org/toc/2767-3170 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2014 GBV_ILN_2522 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 1 2022 1
allfieldsGer	(DE-627)DOAJ081861427 (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7 DE-627 ger DE-627 rakwb eng R858-859.7 Vadim Demichev verfasserin aut A proteomic survival predictor for COVID-19 patients in intensive care 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors. Computer applications to medicine. Medical informatics Pinkus Tober-Lau verfasserin aut Tatiana Nazarenko verfasserin aut Oliver Lemke verfasserin aut Simran Kaur Aulakh verfasserin aut Harry J. Whitwell verfasserin aut Annika Röhl verfasserin aut Anja Freiwald verfasserin aut Mirja Mittermaier verfasserin aut Lukasz Szyrwiel verfasserin aut Daniela Ludwig verfasserin aut Clara Correia-Melo verfasserin aut Lena J. Lippert verfasserin aut Elisa T. Helbig verfasserin aut Paula Stubbemann verfasserin aut Nadine Olk verfasserin aut Charlotte Thibeault verfasserin aut Nana-Maria Grüning verfasserin aut Oleg Blyuss verfasserin aut Spyros Vernardis verfasserin aut Matthew White verfasserin aut Christoph B. Messner verfasserin aut Michael Joannidis verfasserin aut Thomas Sonnweber verfasserin aut Sebastian J. Klein verfasserin aut Alex Pizzini verfasserin aut Yvonne Wohlfarter verfasserin aut Sabina Sahanic verfasserin aut Richard Hilbe verfasserin aut Benedikt Schaefer verfasserin aut Sonja Wagner verfasserin aut Felix Machleidt verfasserin aut Carmen Garcia verfasserin aut Christoph Ruwwe-Glösenkamp verfasserin aut Tilman Lingscheid verfasserin aut Laure Bosquillon de Jarcy verfasserin aut Miriam S. Stegemann verfasserin aut Moritz Pfeiffer verfasserin aut Linda Jürgens verfasserin aut Sophy Denker verfasserin aut Daniel Zickler verfasserin aut Claudia Spies verfasserin aut Andreas Edel verfasserin aut Nils B. Müller verfasserin aut Philipp Enghard verfasserin aut Aleksej Zelezniak verfasserin aut Rosa Bellmann-Weiler verfasserin aut Günter Weiss verfasserin aut Archie Campbell verfasserin aut Caroline Hayward verfasserin aut David J. Porteous verfasserin aut Riccardo E. Marioni verfasserin aut Alexander Uhrig verfasserin aut Heinz Zoller verfasserin aut Judith Löffler-Ragg verfasserin aut Markus A. Keller verfasserin aut Ivan Tancevski verfasserin aut John F. Timms verfasserin aut Alexey Zaikin verfasserin aut Stefan Hippenstiel verfasserin aut Michael Ramharter verfasserin aut Holger Müller-Redetzky verfasserin aut Martin Witzenrath verfasserin aut Norbert Suttorp verfasserin aut Kathryn Lilley verfasserin aut Michael Mülleder verfasserin aut Leif Erik Sander verfasserin aut Florian Kurth verfasserin aut Markus Ralser verfasserin aut In PLOS Digital Health Public Library of Science (PLoS), 2022 1(2022), 1 (DE-627)1786633930 (DE-600)3106944-7 27673170 nnns volume:1 year:2022 number:1 https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 kostenfrei https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI kostenfrei https://doaj.org/toc/2767-3170 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2014 GBV_ILN_2522 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 1 2022 1
allfieldsSound	(DE-627)DOAJ081861427 (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7 DE-627 ger DE-627 rakwb eng R858-859.7 Vadim Demichev verfasserin aut A proteomic survival predictor for COVID-19 patients in intensive care 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors. Computer applications to medicine. Medical informatics Pinkus Tober-Lau verfasserin aut Tatiana Nazarenko verfasserin aut Oliver Lemke verfasserin aut Simran Kaur Aulakh verfasserin aut Harry J. Whitwell verfasserin aut Annika Röhl verfasserin aut Anja Freiwald verfasserin aut Mirja Mittermaier verfasserin aut Lukasz Szyrwiel verfasserin aut Daniela Ludwig verfasserin aut Clara Correia-Melo verfasserin aut Lena J. Lippert verfasserin aut Elisa T. Helbig verfasserin aut Paula Stubbemann verfasserin aut Nadine Olk verfasserin aut Charlotte Thibeault verfasserin aut Nana-Maria Grüning verfasserin aut Oleg Blyuss verfasserin aut Spyros Vernardis verfasserin aut Matthew White verfasserin aut Christoph B. Messner verfasserin aut Michael Joannidis verfasserin aut Thomas Sonnweber verfasserin aut Sebastian J. Klein verfasserin aut Alex Pizzini verfasserin aut Yvonne Wohlfarter verfasserin aut Sabina Sahanic verfasserin aut Richard Hilbe verfasserin aut Benedikt Schaefer verfasserin aut Sonja Wagner verfasserin aut Felix Machleidt verfasserin aut Carmen Garcia verfasserin aut Christoph Ruwwe-Glösenkamp verfasserin aut Tilman Lingscheid verfasserin aut Laure Bosquillon de Jarcy verfasserin aut Miriam S. Stegemann verfasserin aut Moritz Pfeiffer verfasserin aut Linda Jürgens verfasserin aut Sophy Denker verfasserin aut Daniel Zickler verfasserin aut Claudia Spies verfasserin aut Andreas Edel verfasserin aut Nils B. Müller verfasserin aut Philipp Enghard verfasserin aut Aleksej Zelezniak verfasserin aut Rosa Bellmann-Weiler verfasserin aut Günter Weiss verfasserin aut Archie Campbell verfasserin aut Caroline Hayward verfasserin aut David J. Porteous verfasserin aut Riccardo E. Marioni verfasserin aut Alexander Uhrig verfasserin aut Heinz Zoller verfasserin aut Judith Löffler-Ragg verfasserin aut Markus A. Keller verfasserin aut Ivan Tancevski verfasserin aut John F. Timms verfasserin aut Alexey Zaikin verfasserin aut Stefan Hippenstiel verfasserin aut Michael Ramharter verfasserin aut Holger Müller-Redetzky verfasserin aut Martin Witzenrath verfasserin aut Norbert Suttorp verfasserin aut Kathryn Lilley verfasserin aut Michael Mülleder verfasserin aut Leif Erik Sander verfasserin aut Florian Kurth verfasserin aut Markus Ralser verfasserin aut In PLOS Digital Health Public Library of Science (PLoS), 2022 1(2022), 1 (DE-627)1786633930 (DE-600)3106944-7 27673170 nnns volume:1 year:2022 number:1 https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 kostenfrei https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI kostenfrei https://doaj.org/toc/2767-3170 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2014 GBV_ILN_2522 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 1 2022 1
language	English
source	In PLOS Digital Health 1(2022), 1 volume:1 year:2022 number:1
sourceStr	In PLOS Digital Health 1(2022), 1 volume:1 year:2022 number:1
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	Computer applications to medicine. Medical informatics
isfreeaccess_bool	true
container_title	PLOS Digital Health
authorswithroles_txt_mv	Vadim Demichev @@aut@@ Pinkus Tober-Lau @@aut@@ Tatiana Nazarenko @@aut@@ Oliver Lemke @@aut@@ Simran Kaur Aulakh @@aut@@ Harry J. Whitwell @@aut@@ Annika Röhl @@aut@@ Anja Freiwald @@aut@@ Mirja Mittermaier @@aut@@ Lukasz Szyrwiel @@aut@@ Daniela Ludwig @@aut@@ Clara Correia-Melo @@aut@@ Lena J. Lippert @@aut@@ Elisa T. Helbig @@aut@@ Paula Stubbemann @@aut@@ Nadine Olk @@aut@@ Charlotte Thibeault @@aut@@ Nana-Maria Grüning @@aut@@ Oleg Blyuss @@aut@@ Spyros Vernardis @@aut@@ Matthew White @@aut@@ Christoph B. Messner @@aut@@ Michael Joannidis @@aut@@ Thomas Sonnweber @@aut@@ Sebastian J. Klein @@aut@@ Alex Pizzini @@aut@@ Yvonne Wohlfarter @@aut@@ Sabina Sahanic @@aut@@ Richard Hilbe @@aut@@ Benedikt Schaefer @@aut@@ Sonja Wagner @@aut@@ Felix Machleidt @@aut@@ Carmen Garcia @@aut@@ Christoph Ruwwe-Glösenkamp @@aut@@ Tilman Lingscheid @@aut@@ Laure Bosquillon de Jarcy @@aut@@ Miriam S. Stegemann @@aut@@ Moritz Pfeiffer @@aut@@ Linda Jürgens @@aut@@ Sophy Denker @@aut@@ Daniel Zickler @@aut@@ Claudia Spies @@aut@@ Andreas Edel @@aut@@ Nils B. Müller @@aut@@ Philipp Enghard @@aut@@ Aleksej Zelezniak @@aut@@ Rosa Bellmann-Weiler @@aut@@ Günter Weiss @@aut@@ Archie Campbell @@aut@@ Caroline Hayward @@aut@@ David J. Porteous @@aut@@ Riccardo E. Marioni @@aut@@ Alexander Uhrig @@aut@@ Heinz Zoller @@aut@@ Judith Löffler-Ragg @@aut@@ Markus A. Keller @@aut@@ Ivan Tancevski @@aut@@ John F. Timms @@aut@@ Alexey Zaikin @@aut@@ Stefan Hippenstiel @@aut@@ Michael Ramharter @@aut@@ Holger Müller-Redetzky @@aut@@ Martin Witzenrath @@aut@@ Norbert Suttorp @@aut@@ Kathryn Lilley @@aut@@ Michael Mülleder @@aut@@ Leif Erik Sander @@aut@@ Florian Kurth @@aut@@ Markus Ralser @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	1786633930
id	DOAJ081861427
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ081861427</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502075257.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ081861427</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">R858-859.7</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Vadim Demichev</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A proteomic survival predictor for COVID-19 patients in intensive care</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors.</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Computer applications to medicine. Medical informatics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Pinkus Tober-Lau</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Tatiana Nazarenko</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Oliver Lemke</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Simran Kaur Aulakh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Harry J. Whitwell</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Annika Röhl</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Anja Freiwald</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mirja Mittermaier</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Lukasz Szyrwiel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daniela Ludwig</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Clara Correia-Melo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Lena J. Lippert</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Elisa T. Helbig</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Paula Stubbemann</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nadine Olk</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Charlotte Thibeault</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nana-Maria Grüning</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Oleg Blyuss</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Spyros Vernardis</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Matthew White</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Christoph B. Messner</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michael Joannidis</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Thomas Sonnweber</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sebastian J. Klein</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alex Pizzini</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yvonne Wohlfarter</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sabina Sahanic</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Richard Hilbe</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Benedikt Schaefer</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sonja Wagner</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Felix Machleidt</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Carmen Garcia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Christoph Ruwwe-Glösenkamp</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Tilman Lingscheid</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laure Bosquillon de Jarcy</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Miriam S. Stegemann</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Moritz Pfeiffer</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Linda Jürgens</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sophy Denker</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daniel Zickler</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Spies</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Andreas Edel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nils B. Müller</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Philipp Enghard</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Aleksej Zelezniak</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Rosa Bellmann-Weiler</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Günter Weiss</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Archie Campbell</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Caroline Hayward</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">David J. Porteous</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Riccardo E. Marioni</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alexander Uhrig</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Heinz Zoller</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Judith Löffler-Ragg</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Markus A. Keller</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ivan Tancevski</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">John F. Timms</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alexey Zaikin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Stefan Hippenstiel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michael Ramharter</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Holger Müller-Redetzky</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Martin Witzenrath</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Norbert Suttorp</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kathryn Lilley</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michael Mülleder</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Leif Erik Sander</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Florian Kurth</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Markus Ralser</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">PLOS Digital Health</subfield><subfield code="d">Public Library of Science (PLoS), 2022</subfield><subfield code="g">1(2022), 1</subfield><subfield code="w">(DE-627)1786633930</subfield><subfield code="w">(DE-600)3106944-7</subfield><subfield code="x">27673170</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:1</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:1</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2767-3170</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_206</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">1</subfield><subfield code="j">2022</subfield><subfield code="e">1</subfield></datafield></record></collection>
callnumber-first	R - Medicine
author	Vadim Demichev
spellingShingle	Vadim Demichev misc R858-859.7 misc Computer applications to medicine. Medical informatics A proteomic survival predictor for COVID-19 patients in intensive care
authorStr	Vadim Demichev
ppnlink_with_tag_str_mv	@@773@@(DE-627)1786633930
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	R858-859
illustrated	Not Illustrated
issn	27673170
topic_title	R858-859.7 A proteomic survival predictor for COVID-19 patients in intensive care
topic	misc R858-859.7 misc Computer applications to medicine. Medical informatics
topic_unstemmed	misc R858-859.7 misc Computer applications to medicine. Medical informatics
topic_browse	misc R858-859.7 misc Computer applications to medicine. Medical informatics
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	PLOS Digital Health
hierarchy_parent_id	1786633930
hierarchy_top_title	PLOS Digital Health
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)1786633930 (DE-600)3106944-7
title	A proteomic survival predictor for COVID-19 patients in intensive care
ctrlnum	(DE-627)DOAJ081861427 (DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7
title_full	A proteomic survival predictor for COVID-19 patients in intensive care
author_sort	Vadim Demichev
journal	PLOS Digital Health
journalStr	PLOS Digital Health
callnumber-first-code	R
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2022
contenttype_str_mv	txt
author_browse	Vadim Demichev Pinkus Tober-Lau Tatiana Nazarenko Oliver Lemke Simran Kaur Aulakh Harry J. Whitwell Annika Röhl Anja Freiwald Mirja Mittermaier Lukasz Szyrwiel Daniela Ludwig Clara Correia-Melo Lena J. Lippert Elisa T. Helbig Paula Stubbemann Nadine Olk Charlotte Thibeault Nana-Maria Grüning Oleg Blyuss Spyros Vernardis Matthew White Christoph B. Messner Michael Joannidis Thomas Sonnweber Sebastian J. Klein Alex Pizzini Yvonne Wohlfarter Sabina Sahanic Richard Hilbe Benedikt Schaefer Sonja Wagner Felix Machleidt Carmen Garcia Christoph Ruwwe-Glösenkamp Tilman Lingscheid Laure Bosquillon de Jarcy Miriam S. Stegemann Moritz Pfeiffer Linda Jürgens Sophy Denker Daniel Zickler Claudia Spies Andreas Edel Nils B. Müller Philipp Enghard Aleksej Zelezniak Rosa Bellmann-Weiler Günter Weiss Archie Campbell Caroline Hayward David J. Porteous Riccardo E. Marioni Alexander Uhrig Heinz Zoller Judith Löffler-Ragg Markus A. Keller Ivan Tancevski John F. Timms Alexey Zaikin Stefan Hippenstiel Michael Ramharter Holger Müller-Redetzky Martin Witzenrath Norbert Suttorp Kathryn Lilley Michael Mülleder Leif Erik Sander Florian Kurth Markus Ralser
container_volume	1
class	R858-859.7
format_se	Elektronische Aufsätze
author-letter	Vadim Demichev
author2-role	verfasserin
title_sort	proteomic survival predictor for covid-19 patients in intensive care
callnumber	R858-859.7
title_auth	A proteomic survival predictor for COVID-19 patients in intensive care
abstract	Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors.
abstractGer	Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors.
abstract_unstemmed	Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_73 GBV_ILN_74 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2014 GBV_ILN_2522 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	1
title_short	A proteomic survival predictor for COVID-19 patients in intensive care
url	https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI https://doaj.org/toc/2767-3170
remote_bool	true
author2	Pinkus Tober-Lau Tatiana Nazarenko Oliver Lemke Simran Kaur Aulakh Harry J. Whitwell Annika Röhl Anja Freiwald Mirja Mittermaier Lukasz Szyrwiel Daniela Ludwig Clara Correia-Melo Lena J. Lippert Elisa T. Helbig Paula Stubbemann Nadine Olk Charlotte Thibeault Nana-Maria Grüning Oleg Blyuss Spyros Vernardis Matthew White Christoph B. Messner Michael Joannidis Thomas Sonnweber Sebastian J. Klein Alex Pizzini Yvonne Wohlfarter Sabina Sahanic Richard Hilbe Benedikt Schaefer Sonja Wagner Felix Machleidt Carmen Garcia Christoph Ruwwe-Glösenkamp Tilman Lingscheid Laure Bosquillon de Jarcy Miriam S. Stegemann Moritz Pfeiffer Linda Jürgens Sophy Denker Daniel Zickler Claudia Spies Andreas Edel Nils B. Müller Philipp Enghard Aleksej Zelezniak Rosa Bellmann-Weiler Günter Weiss Archie Campbell Caroline Hayward David J. Porteous Riccardo E. Marioni Alexander Uhrig Heinz Zoller Judith Löffler-Ragg Markus A. Keller Ivan Tancevski John F. Timms Alexey Zaikin Stefan Hippenstiel Michael Ramharter Holger Müller-Redetzky Martin Witzenrath Norbert Suttorp Kathryn Lilley Michael Mülleder Leif Erik Sander Florian Kurth Markus Ralser
author2Str	Pinkus Tober-Lau Tatiana Nazarenko Oliver Lemke Simran Kaur Aulakh Harry J. Whitwell Annika Röhl Anja Freiwald Mirja Mittermaier Lukasz Szyrwiel Daniela Ludwig Clara Correia-Melo Lena J. Lippert Elisa T. Helbig Paula Stubbemann Nadine Olk Charlotte Thibeault Nana-Maria Grüning Oleg Blyuss Spyros Vernardis Matthew White Christoph B. Messner Michael Joannidis Thomas Sonnweber Sebastian J. Klein Alex Pizzini Yvonne Wohlfarter Sabina Sahanic Richard Hilbe Benedikt Schaefer Sonja Wagner Felix Machleidt Carmen Garcia Christoph Ruwwe-Glösenkamp Tilman Lingscheid Laure Bosquillon de Jarcy Miriam S. Stegemann Moritz Pfeiffer Linda Jürgens Sophy Denker Daniel Zickler Claudia Spies Andreas Edel Nils B. Müller Philipp Enghard Aleksej Zelezniak Rosa Bellmann-Weiler Günter Weiss Archie Campbell Caroline Hayward David J. Porteous Riccardo E. Marioni Alexander Uhrig Heinz Zoller Judith Löffler-Ragg Markus A. Keller Ivan Tancevski John F. Timms Alexey Zaikin Stefan Hippenstiel Michael Ramharter Holger Müller-Redetzky Martin Witzenrath Norbert Suttorp Kathryn Lilley Michael Mülleder Leif Erik Sander Florian Kurth Markus Ralser
ppnlink	1786633930
callnumber-subject	R - General Medicine
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
callnumber-a	R858-859.7
up_date	2024-07-03T22:22:09.944Z
_version_	1803598251894505472
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ081861427</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502075257.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ081861427</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJca9c7a2e20b1488b8dd4b7e2dbf10ad7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">R858-859.7</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Vadim Demichev</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A proteomic survival predictor for COVID-19 patients in intensive care</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Additional tools are also needed to monitor treatment, including experimental therapies in clinical trials. Comprehensively capturing human physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index, and APACHE II score showed limited performance in predicting the COVID-19 outcome. Instead, the quantification of 321 plasma protein groups at 349 timepoints in 50 critically ill patients receiving invasive mechanical ventilation revealed 14 proteins that showed trajectories different between survivors and non-survivors. A predictor trained on proteomic measurements obtained at the first time point at maximum treatment level (i.e. WHO grade 7), which was weeks before the outcome, achieved accurate classification of survivors (AUROC 0.81). We tested the established predictor on an independent validation cohort (AUROC 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that plasma proteomics can give rise to prognostic predictors substantially outperforming current prognostic markers in intensive care. Author summary Healthcare systems around the world are struggling to accommodate high numbers of the most severely ill patients with COVID-19. Moreover, the pandemic creates a pressing need to accelerate clinical trials investigating potential new therapeutics. While various biomarkers can discriminate and predict the future course of disease for patients of different disease severity, prognosis remains difficult for patient groups with similar disease severity, e.g. patients requiring intensive care. Established risk assessments in intensive care medicine such as the SOFA or APACHE II show only limited reliability in predicting future disease outcomes for COVID-19. In this study we hypothesized that the plasma proteome, which reflects the complete set of proteins that are expressed by an organism and are present in the blood, and which is known to comprehensively capture the host response to COVID-19, can be leveraged to allow for prediction of survival in the most critically ill patients with COVID-19. Here, we found 14 proteins, which over time changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. Using a machine learning model which combines the measurements of multiple proteins, we were able to accurately predict survival in critically ill patients with COVID-19 from single blood samples, weeks before the outcome, substantially outperforming established risk predictors.</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Computer applications to medicine. Medical informatics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Pinkus Tober-Lau</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Tatiana Nazarenko</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Oliver Lemke</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Simran Kaur Aulakh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Harry J. Whitwell</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Annika Röhl</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Anja Freiwald</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mirja Mittermaier</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Lukasz Szyrwiel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daniela Ludwig</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Clara Correia-Melo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Lena J. Lippert</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Elisa T. Helbig</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Paula Stubbemann</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nadine Olk</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Charlotte Thibeault</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nana-Maria Grüning</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Oleg Blyuss</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Spyros Vernardis</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Matthew White</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Christoph B. Messner</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michael Joannidis</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Thomas Sonnweber</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sebastian J. Klein</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alex Pizzini</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yvonne Wohlfarter</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sabina Sahanic</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Richard Hilbe</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Benedikt Schaefer</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sonja Wagner</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Felix Machleidt</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Carmen Garcia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Christoph Ruwwe-Glösenkamp</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Tilman Lingscheid</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laure Bosquillon de Jarcy</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Miriam S. Stegemann</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Moritz Pfeiffer</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Linda Jürgens</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sophy Denker</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daniel Zickler</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Spies</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Andreas Edel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nils B. Müller</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Philipp Enghard</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Aleksej Zelezniak</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Rosa Bellmann-Weiler</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Günter Weiss</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Archie Campbell</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Caroline Hayward</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">David J. Porteous</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Riccardo E. Marioni</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alexander Uhrig</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Heinz Zoller</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Judith Löffler-Ragg</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Markus A. Keller</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ivan Tancevski</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">John F. Timms</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alexey Zaikin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Stefan Hippenstiel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michael Ramharter</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Holger Müller-Redetzky</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Martin Witzenrath</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Norbert Suttorp</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kathryn Lilley</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michael Mülleder</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Leif Erik Sander</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Florian Kurth</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Markus Ralser</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">PLOS Digital Health</subfield><subfield code="d">Public Library of Science (PLoS), 2022</subfield><subfield code="g">1(2022), 1</subfield><subfield code="w">(DE-627)1786633930</subfield><subfield code="w">(DE-600)3106944-7</subfield><subfield code="x">27673170</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:1</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:1</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/ca9c7a2e20b1488b8dd4b7e2dbf10ad7</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931303/?tool=EBI</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2767-3170</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_206</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">1</subfield><subfield code="j">2022</subfield><subfield code="e">1</subfield></datafield></record></collection>
score	7.4012136

Nicht das Richtige dabei?

Schreiben Sie uns!

A proteomic survival predictor for COVID-19 patients in intensive care

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?