Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients

IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (N...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Arsela Prelaj [verfasserIn] Edoardo Gregorio Galli [verfasserIn] Vanja Miskovic [verfasserIn] Mattia Pesenti [verfasserIn] Giuseppe Viscardi [verfasserIn] Benedetta Pedica [verfasserIn] Laura Mazzeo [verfasserIn] Achille Bottiglieri [verfasserIn] Leonardo Provenzano [verfasserIn] Andrea Spagnoletti [verfasserIn] Roberto Marinacci [verfasserIn] Alessandro De Toma [verfasserIn] Claudia Proto [verfasserIn] Roberto Ferrara [verfasserIn] Marta Brambilla [verfasserIn] Mario Occhipinti [verfasserIn] Sara Manglaviti [verfasserIn] Giulia Galli [verfasserIn] Diego Signorelli [verfasserIn] Claudia Giani [verfasserIn] Teresa Beninato [verfasserIn] Chiara Carlotta Pircher [verfasserIn] Alessandro Rametta [verfasserIn] Sokol Kosta [verfasserIn] Michele Zanitti [verfasserIn] Maria Rosa Di Mauro [verfasserIn] Arturo Rinaldi [verfasserIn] Settimio Di Gregorio [verfasserIn] Martinetti Antonia [verfasserIn] Marina Chiara Garassino [verfasserIn] Filippo G. M. de Braud [verfasserIn] Marcello Restelli [verfasserIn] Giuseppe Lo Russo [verfasserIn] Monica Ganzinelli [verfasserIn] Francesco Trovò [verfasserIn] Alessandra Laura Giulia Pedrocchi [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment

Übergeordnetes Werk:	In: Frontiers in Oncology - Frontiers Media S.A., 2012, 12(2023)
Übergeordnetes Werk:	volume:12 ; year:2023

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3389/fonc.2022.1078822

Katalog-ID:	DOAJ081622465

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ081622465
003	DE-627
005	20230310220850.0
007	cr uuu---uuuuu
008	230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3389/fonc.2022.1078822 \|2 doi
035			\|a (DE-627)DOAJ081622465
035			\|a (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a RC254-282
100	0		\|a Arsela Prelaj \|e verfasserin \|4 aut
245	1	0	\|a Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients
264		1	\|c 2023
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.
650		4	\|a non-small cell lung cancer
650		4	\|a immunotherapy
650		4	\|a machine learning
650		4	\|a explainable artificial intelligence
650		4	\|a treatment
653		0	\|a Neoplasms. Tumors. Oncology. Including cancer and carcinogens
700	0		\|a Arsela Prelaj \|e verfasserin \|4 aut
700	0		\|a Edoardo Gregorio Galli \|e verfasserin \|4 aut
700	0		\|a Edoardo Gregorio Galli \|e verfasserin \|4 aut
700	0		\|a Edoardo Gregorio Galli \|e verfasserin \|4 aut
700	0		\|a Vanja Miskovic \|e verfasserin \|4 aut
700	0		\|a Mattia Pesenti \|e verfasserin \|4 aut
700	0		\|a Giuseppe Viscardi \|e verfasserin \|4 aut
700	0		\|a Giuseppe Viscardi \|e verfasserin \|4 aut
700	0		\|a Benedetta Pedica \|e verfasserin \|4 aut
700	0		\|a Laura Mazzeo \|e verfasserin \|4 aut
700	0		\|a Laura Mazzeo \|e verfasserin \|4 aut
700	0		\|a Laura Mazzeo \|e verfasserin \|4 aut
700	0		\|a Achille Bottiglieri \|e verfasserin \|4 aut
700	0		\|a Achille Bottiglieri \|e verfasserin \|4 aut
700	0		\|a Leonardo Provenzano \|e verfasserin \|4 aut
700	0		\|a Leonardo Provenzano \|e verfasserin \|4 aut
700	0		\|a Andrea Spagnoletti \|e verfasserin \|4 aut
700	0		\|a Andrea Spagnoletti \|e verfasserin \|4 aut
700	0		\|a Roberto Marinacci \|e verfasserin \|4 aut
700	0		\|a Alessandro De Toma \|e verfasserin \|4 aut
700	0		\|a Claudia Proto \|e verfasserin \|4 aut
700	0		\|a Roberto Ferrara \|e verfasserin \|4 aut
700	0		\|a Marta Brambilla \|e verfasserin \|4 aut
700	0		\|a Mario Occhipinti \|e verfasserin \|4 aut
700	0		\|a Sara Manglaviti \|e verfasserin \|4 aut
700	0		\|a Giulia Galli \|e verfasserin \|4 aut
700	0		\|a Diego Signorelli \|e verfasserin \|4 aut
700	0		\|a Diego Signorelli \|e verfasserin \|4 aut
700	0		\|a Claudia Giani \|e verfasserin \|4 aut
700	0		\|a Claudia Giani \|e verfasserin \|4 aut
700	0		\|a Teresa Beninato \|e verfasserin \|4 aut
700	0		\|a Teresa Beninato \|e verfasserin \|4 aut
700	0		\|a Chiara Carlotta Pircher \|e verfasserin \|4 aut
700	0		\|a Chiara Carlotta Pircher \|e verfasserin \|4 aut
700	0		\|a Alessandro Rametta \|e verfasserin \|4 aut
700	0		\|a Alessandro Rametta \|e verfasserin \|4 aut
700	0		\|a Sokol Kosta \|e verfasserin \|4 aut
700	0		\|a Michele Zanitti \|e verfasserin \|4 aut
700	0		\|a Maria Rosa Di Mauro \|e verfasserin \|4 aut
700	0		\|a Arturo Rinaldi \|e verfasserin \|4 aut
700	0		\|a Settimio Di Gregorio \|e verfasserin \|4 aut
700	0		\|a Martinetti Antonia \|e verfasserin \|4 aut
700	0		\|a Marina Chiara Garassino \|e verfasserin \|4 aut
700	0		\|a Marina Chiara Garassino \|e verfasserin \|4 aut
700	0		\|a Filippo G. M. de Braud \|e verfasserin \|4 aut
700	0		\|a Filippo G. M. de Braud \|e verfasserin \|4 aut
700	0		\|a Marcello Restelli \|e verfasserin \|4 aut
700	0		\|a Giuseppe Lo Russo \|e verfasserin \|4 aut
700	0		\|a Monica Ganzinelli \|e verfasserin \|4 aut
700	0		\|a Francesco Trovò \|e verfasserin \|4 aut
700	0		\|a Alessandra Laura Giulia Pedrocchi \|e verfasserin \|4 aut
773	0	8	\|i In \|t Frontiers in Oncology \|d Frontiers Media S.A., 2012 \|g 12(2023) \|w (DE-627)684965518 \|w (DE-600)2649216-7 \|x 2234943X \|7 nnns
773	1	8	\|g volume:12 \|g year:2023
856	4	0	\|u https://doi.org/10.3389/fonc.2022.1078822 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 \|z kostenfrei
856	4	0	\|u https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2234-943X \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
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_2003
912			\|a GBV_ILN_2014
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 12 \|j 2023

Indexfelder

author_variant	a p ap a p ap e g g egg e g g egg e g g egg v m vm m p mp g v gv g v gv b p bp l m lm l m lm l m lm a b ab a b ab l p lp l p lp a s as a s as r m rm a d t adt c p cp r f rf m b mb m o mo s m sm g g gg d s ds d s ds c g cg c g cg t b tb t b tb c c p ccp c c p ccp a r ar a r ar s k sk m z mz m r d m mrdm a r ar s d g sdg m a ma m c g mcg m c g mcg f g m d b fgmdb f g m d b fgmdb m r mr g l r glr m g mg f t ft a l g p algp
matchkey_str	article:2234943X:2023----::eloldttbidxlialtutotyriiilnelgneoesopeitooimn
hierarchy_sort_str	2023
callnumber-subject-code	RC
publishDate	2023
allfields	10.3389/fonc.2022.1078822 doi (DE-627)DOAJ081622465 (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5 DE-627 ger DE-627 rakwb eng RC254-282 Arsela Prelaj verfasserin aut Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients. non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment Neoplasms. Tumors. Oncology. Including cancer and carcinogens Arsela Prelaj verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Vanja Miskovic verfasserin aut Mattia Pesenti verfasserin aut Giuseppe Viscardi verfasserin aut Giuseppe Viscardi verfasserin aut Benedetta Pedica verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Achille Bottiglieri verfasserin aut Achille Bottiglieri verfasserin aut Leonardo Provenzano verfasserin aut Leonardo Provenzano verfasserin aut Andrea Spagnoletti verfasserin aut Andrea Spagnoletti verfasserin aut Roberto Marinacci verfasserin aut Alessandro De Toma verfasserin aut Claudia Proto verfasserin aut Roberto Ferrara verfasserin aut Marta Brambilla verfasserin aut Mario Occhipinti verfasserin aut Sara Manglaviti verfasserin aut Giulia Galli verfasserin aut Diego Signorelli verfasserin aut Diego Signorelli verfasserin aut Claudia Giani verfasserin aut Claudia Giani verfasserin aut Teresa Beninato verfasserin aut Teresa Beninato verfasserin aut Chiara Carlotta Pircher verfasserin aut Chiara Carlotta Pircher verfasserin aut Alessandro Rametta verfasserin aut Alessandro Rametta verfasserin aut Sokol Kosta verfasserin aut Michele Zanitti verfasserin aut Maria Rosa Di Mauro verfasserin aut Arturo Rinaldi verfasserin aut Settimio Di Gregorio verfasserin aut Martinetti Antonia verfasserin aut Marina Chiara Garassino verfasserin aut Marina Chiara Garassino verfasserin aut Filippo G. M. de Braud verfasserin aut Filippo G. M. de Braud verfasserin aut Marcello Restelli verfasserin aut Giuseppe Lo Russo verfasserin aut Monica Ganzinelli verfasserin aut Francesco Trovò verfasserin aut Alessandra Laura Giulia Pedrocchi verfasserin aut In Frontiers in Oncology Frontiers Media S.A., 2012 12(2023) (DE-627)684965518 (DE-600)2649216-7 2234943X nnns volume:12 year:2023 https://doi.org/10.3389/fonc.2022.1078822 kostenfrei https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 kostenfrei https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full kostenfrei https://doaj.org/toc/2234-943X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_2003 GBV_ILN_2014 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 12 2023
spelling	10.3389/fonc.2022.1078822 doi (DE-627)DOAJ081622465 (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5 DE-627 ger DE-627 rakwb eng RC254-282 Arsela Prelaj verfasserin aut Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients. non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment Neoplasms. Tumors. Oncology. Including cancer and carcinogens Arsela Prelaj verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Vanja Miskovic verfasserin aut Mattia Pesenti verfasserin aut Giuseppe Viscardi verfasserin aut Giuseppe Viscardi verfasserin aut Benedetta Pedica verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Achille Bottiglieri verfasserin aut Achille Bottiglieri verfasserin aut Leonardo Provenzano verfasserin aut Leonardo Provenzano verfasserin aut Andrea Spagnoletti verfasserin aut Andrea Spagnoletti verfasserin aut Roberto Marinacci verfasserin aut Alessandro De Toma verfasserin aut Claudia Proto verfasserin aut Roberto Ferrara verfasserin aut Marta Brambilla verfasserin aut Mario Occhipinti verfasserin aut Sara Manglaviti verfasserin aut Giulia Galli verfasserin aut Diego Signorelli verfasserin aut Diego Signorelli verfasserin aut Claudia Giani verfasserin aut Claudia Giani verfasserin aut Teresa Beninato verfasserin aut Teresa Beninato verfasserin aut Chiara Carlotta Pircher verfasserin aut Chiara Carlotta Pircher verfasserin aut Alessandro Rametta verfasserin aut Alessandro Rametta verfasserin aut Sokol Kosta verfasserin aut Michele Zanitti verfasserin aut Maria Rosa Di Mauro verfasserin aut Arturo Rinaldi verfasserin aut Settimio Di Gregorio verfasserin aut Martinetti Antonia verfasserin aut Marina Chiara Garassino verfasserin aut Marina Chiara Garassino verfasserin aut Filippo G. M. de Braud verfasserin aut Filippo G. M. de Braud verfasserin aut Marcello Restelli verfasserin aut Giuseppe Lo Russo verfasserin aut Monica Ganzinelli verfasserin aut Francesco Trovò verfasserin aut Alessandra Laura Giulia Pedrocchi verfasserin aut In Frontiers in Oncology Frontiers Media S.A., 2012 12(2023) (DE-627)684965518 (DE-600)2649216-7 2234943X nnns volume:12 year:2023 https://doi.org/10.3389/fonc.2022.1078822 kostenfrei https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 kostenfrei https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full kostenfrei https://doaj.org/toc/2234-943X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_2003 GBV_ILN_2014 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 12 2023
allfields_unstemmed	10.3389/fonc.2022.1078822 doi (DE-627)DOAJ081622465 (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5 DE-627 ger DE-627 rakwb eng RC254-282 Arsela Prelaj verfasserin aut Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients. non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment Neoplasms. Tumors. Oncology. Including cancer and carcinogens Arsela Prelaj verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Vanja Miskovic verfasserin aut Mattia Pesenti verfasserin aut Giuseppe Viscardi verfasserin aut Giuseppe Viscardi verfasserin aut Benedetta Pedica verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Achille Bottiglieri verfasserin aut Achille Bottiglieri verfasserin aut Leonardo Provenzano verfasserin aut Leonardo Provenzano verfasserin aut Andrea Spagnoletti verfasserin aut Andrea Spagnoletti verfasserin aut Roberto Marinacci verfasserin aut Alessandro De Toma verfasserin aut Claudia Proto verfasserin aut Roberto Ferrara verfasserin aut Marta Brambilla verfasserin aut Mario Occhipinti verfasserin aut Sara Manglaviti verfasserin aut Giulia Galli verfasserin aut Diego Signorelli verfasserin aut Diego Signorelli verfasserin aut Claudia Giani verfasserin aut Claudia Giani verfasserin aut Teresa Beninato verfasserin aut Teresa Beninato verfasserin aut Chiara Carlotta Pircher verfasserin aut Chiara Carlotta Pircher verfasserin aut Alessandro Rametta verfasserin aut Alessandro Rametta verfasserin aut Sokol Kosta verfasserin aut Michele Zanitti verfasserin aut Maria Rosa Di Mauro verfasserin aut Arturo Rinaldi verfasserin aut Settimio Di Gregorio verfasserin aut Martinetti Antonia verfasserin aut Marina Chiara Garassino verfasserin aut Marina Chiara Garassino verfasserin aut Filippo G. M. de Braud verfasserin aut Filippo G. M. de Braud verfasserin aut Marcello Restelli verfasserin aut Giuseppe Lo Russo verfasserin aut Monica Ganzinelli verfasserin aut Francesco Trovò verfasserin aut Alessandra Laura Giulia Pedrocchi verfasserin aut In Frontiers in Oncology Frontiers Media S.A., 2012 12(2023) (DE-627)684965518 (DE-600)2649216-7 2234943X nnns volume:12 year:2023 https://doi.org/10.3389/fonc.2022.1078822 kostenfrei https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 kostenfrei https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full kostenfrei https://doaj.org/toc/2234-943X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_2003 GBV_ILN_2014 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 12 2023
allfieldsGer	10.3389/fonc.2022.1078822 doi (DE-627)DOAJ081622465 (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5 DE-627 ger DE-627 rakwb eng RC254-282 Arsela Prelaj verfasserin aut Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients. non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment Neoplasms. Tumors. Oncology. Including cancer and carcinogens Arsela Prelaj verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Vanja Miskovic verfasserin aut Mattia Pesenti verfasserin aut Giuseppe Viscardi verfasserin aut Giuseppe Viscardi verfasserin aut Benedetta Pedica verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Achille Bottiglieri verfasserin aut Achille Bottiglieri verfasserin aut Leonardo Provenzano verfasserin aut Leonardo Provenzano verfasserin aut Andrea Spagnoletti verfasserin aut Andrea Spagnoletti verfasserin aut Roberto Marinacci verfasserin aut Alessandro De Toma verfasserin aut Claudia Proto verfasserin aut Roberto Ferrara verfasserin aut Marta Brambilla verfasserin aut Mario Occhipinti verfasserin aut Sara Manglaviti verfasserin aut Giulia Galli verfasserin aut Diego Signorelli verfasserin aut Diego Signorelli verfasserin aut Claudia Giani verfasserin aut Claudia Giani verfasserin aut Teresa Beninato verfasserin aut Teresa Beninato verfasserin aut Chiara Carlotta Pircher verfasserin aut Chiara Carlotta Pircher verfasserin aut Alessandro Rametta verfasserin aut Alessandro Rametta verfasserin aut Sokol Kosta verfasserin aut Michele Zanitti verfasserin aut Maria Rosa Di Mauro verfasserin aut Arturo Rinaldi verfasserin aut Settimio Di Gregorio verfasserin aut Martinetti Antonia verfasserin aut Marina Chiara Garassino verfasserin aut Marina Chiara Garassino verfasserin aut Filippo G. M. de Braud verfasserin aut Filippo G. M. de Braud verfasserin aut Marcello Restelli verfasserin aut Giuseppe Lo Russo verfasserin aut Monica Ganzinelli verfasserin aut Francesco Trovò verfasserin aut Alessandra Laura Giulia Pedrocchi verfasserin aut In Frontiers in Oncology Frontiers Media S.A., 2012 12(2023) (DE-627)684965518 (DE-600)2649216-7 2234943X nnns volume:12 year:2023 https://doi.org/10.3389/fonc.2022.1078822 kostenfrei https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 kostenfrei https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full kostenfrei https://doaj.org/toc/2234-943X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_2003 GBV_ILN_2014 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 12 2023
allfieldsSound	10.3389/fonc.2022.1078822 doi (DE-627)DOAJ081622465 (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5 DE-627 ger DE-627 rakwb eng RC254-282 Arsela Prelaj verfasserin aut Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients. non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment Neoplasms. Tumors. Oncology. Including cancer and carcinogens Arsela Prelaj verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Edoardo Gregorio Galli verfasserin aut Vanja Miskovic verfasserin aut Mattia Pesenti verfasserin aut Giuseppe Viscardi verfasserin aut Giuseppe Viscardi verfasserin aut Benedetta Pedica verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Laura Mazzeo verfasserin aut Achille Bottiglieri verfasserin aut Achille Bottiglieri verfasserin aut Leonardo Provenzano verfasserin aut Leonardo Provenzano verfasserin aut Andrea Spagnoletti verfasserin aut Andrea Spagnoletti verfasserin aut Roberto Marinacci verfasserin aut Alessandro De Toma verfasserin aut Claudia Proto verfasserin aut Roberto Ferrara verfasserin aut Marta Brambilla verfasserin aut Mario Occhipinti verfasserin aut Sara Manglaviti verfasserin aut Giulia Galli verfasserin aut Diego Signorelli verfasserin aut Diego Signorelli verfasserin aut Claudia Giani verfasserin aut Claudia Giani verfasserin aut Teresa Beninato verfasserin aut Teresa Beninato verfasserin aut Chiara Carlotta Pircher verfasserin aut Chiara Carlotta Pircher verfasserin aut Alessandro Rametta verfasserin aut Alessandro Rametta verfasserin aut Sokol Kosta verfasserin aut Michele Zanitti verfasserin aut Maria Rosa Di Mauro verfasserin aut Arturo Rinaldi verfasserin aut Settimio Di Gregorio verfasserin aut Martinetti Antonia verfasserin aut Marina Chiara Garassino verfasserin aut Marina Chiara Garassino verfasserin aut Filippo G. M. de Braud verfasserin aut Filippo G. M. de Braud verfasserin aut Marcello Restelli verfasserin aut Giuseppe Lo Russo verfasserin aut Monica Ganzinelli verfasserin aut Francesco Trovò verfasserin aut Alessandra Laura Giulia Pedrocchi verfasserin aut In Frontiers in Oncology Frontiers Media S.A., 2012 12(2023) (DE-627)684965518 (DE-600)2649216-7 2234943X nnns volume:12 year:2023 https://doi.org/10.3389/fonc.2022.1078822 kostenfrei https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 kostenfrei https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full kostenfrei https://doaj.org/toc/2234-943X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_2003 GBV_ILN_2014 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 12 2023
language	English
source	In Frontiers in Oncology 12(2023) volume:12 year:2023
sourceStr	In Frontiers in Oncology 12(2023) volume:12 year:2023
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment Neoplasms. Tumors. Oncology. Including cancer and carcinogens
isfreeaccess_bool	true
container_title	Frontiers in Oncology
authorswithroles_txt_mv	Arsela Prelaj @@aut@@ Edoardo Gregorio Galli @@aut@@ Vanja Miskovic @@aut@@ Mattia Pesenti @@aut@@ Giuseppe Viscardi @@aut@@ Benedetta Pedica @@aut@@ Laura Mazzeo @@aut@@ Achille Bottiglieri @@aut@@ Leonardo Provenzano @@aut@@ Andrea Spagnoletti @@aut@@ Roberto Marinacci @@aut@@ Alessandro De Toma @@aut@@ Claudia Proto @@aut@@ Roberto Ferrara @@aut@@ Marta Brambilla @@aut@@ Mario Occhipinti @@aut@@ Sara Manglaviti @@aut@@ Giulia Galli @@aut@@ Diego Signorelli @@aut@@ Claudia Giani @@aut@@ Teresa Beninato @@aut@@ Chiara Carlotta Pircher @@aut@@ Alessandro Rametta @@aut@@ Sokol Kosta @@aut@@ Michele Zanitti @@aut@@ Maria Rosa Di Mauro @@aut@@ Arturo Rinaldi @@aut@@ Settimio Di Gregorio @@aut@@ Martinetti Antonia @@aut@@ Marina Chiara Garassino @@aut@@ Filippo G. M. de Braud @@aut@@ Marcello Restelli @@aut@@ Giuseppe Lo Russo @@aut@@ Monica Ganzinelli @@aut@@ Francesco Trovò @@aut@@ Alessandra Laura Giulia Pedrocchi @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	684965518
id	DOAJ081622465
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ081622465</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230310220850.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fonc.2022.1078822</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ081622465</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5</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">RC254-282</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Arsela Prelaj</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</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">IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">non-small cell lung cancer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">immunotherapy</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">explainable artificial intelligence</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">treatment</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Neoplasms. Tumors. Oncology. Including cancer and carcinogens</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Arsela Prelaj</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Edoardo Gregorio Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Edoardo Gregorio Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Edoardo Gregorio Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Vanja Miskovic</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mattia Pesenti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giuseppe Viscardi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giuseppe Viscardi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Benedetta Pedica</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laura Mazzeo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laura Mazzeo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laura Mazzeo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Achille Bottiglieri</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Achille Bottiglieri</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Leonardo Provenzano</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Leonardo Provenzano</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Andrea Spagnoletti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Andrea Spagnoletti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Roberto Marinacci</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandro De Toma</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Proto</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Roberto Ferrara</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marta Brambilla</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mario Occhipinti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sara Manglaviti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giulia Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Diego Signorelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Diego Signorelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Giani</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Giani</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Teresa Beninato</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Teresa Beninato</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chiara Carlotta Pircher</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chiara Carlotta Pircher</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandro Rametta</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandro Rametta</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sokol Kosta</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michele Zanitti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Maria Rosa Di Mauro</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Arturo Rinaldi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Settimio Di Gregorio</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Martinetti Antonia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marina Chiara Garassino</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marina Chiara Garassino</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Filippo G. M. de Braud</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Filippo G. M. de Braud</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marcello Restelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giuseppe Lo Russo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Monica Ganzinelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Francesco Trovò</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandra Laura Giulia Pedrocchi</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">Frontiers in Oncology</subfield><subfield code="d">Frontiers Media S.A., 2012</subfield><subfield code="g">12(2023)</subfield><subfield code="w">(DE-627)684965518</subfield><subfield code="w">(DE-600)2649216-7</subfield><subfield code="x">2234943X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:12</subfield><subfield code="g">year:2023</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fonc.2022.1078822</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2234-943X</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">GBV_ILN_11</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_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_2003</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_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">12</subfield><subfield code="j">2023</subfield></datafield></record></collection>
callnumber-first	R - Medicine
author	Arsela Prelaj
spellingShingle	Arsela Prelaj misc RC254-282 misc non-small cell lung cancer misc immunotherapy misc machine learning misc explainable artificial intelligence misc treatment misc Neoplasms. Tumors. Oncology. Including cancer and carcinogens Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients
authorStr	Arsela Prelaj
ppnlink_with_tag_str_mv	@@773@@(DE-627)684965518
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
collection	DOAJ
remote_str	true
callnumber-label	RC254-282
illustrated	Not Illustrated
issn	2234943X
topic_title	RC254-282 Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients non-small cell lung cancer immunotherapy machine learning explainable artificial intelligence treatment
topic	misc RC254-282 misc non-small cell lung cancer misc immunotherapy misc machine learning misc explainable artificial intelligence misc treatment misc Neoplasms. Tumors. Oncology. Including cancer and carcinogens
topic_unstemmed	misc RC254-282 misc non-small cell lung cancer misc immunotherapy misc machine learning misc explainable artificial intelligence misc treatment misc Neoplasms. Tumors. Oncology. Including cancer and carcinogens
topic_browse	misc RC254-282 misc non-small cell lung cancer misc immunotherapy misc machine learning misc explainable artificial intelligence misc treatment misc Neoplasms. Tumors. Oncology. Including cancer and carcinogens
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Frontiers in Oncology
hierarchy_parent_id	684965518
hierarchy_top_title	Frontiers in Oncology
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)684965518 (DE-600)2649216-7
title	Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients
ctrlnum	(DE-627)DOAJ081622465 (DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5
title_full	Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients
author_sort	Arsela Prelaj
journal	Frontiers in Oncology
journalStr	Frontiers in Oncology
callnumber-first-code	R
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
author_browse	Arsela Prelaj Edoardo Gregorio Galli Vanja Miskovic Mattia Pesenti Giuseppe Viscardi Benedetta Pedica Laura Mazzeo Achille Bottiglieri Leonardo Provenzano Andrea Spagnoletti Roberto Marinacci Alessandro De Toma Claudia Proto Roberto Ferrara Marta Brambilla Mario Occhipinti Sara Manglaviti Giulia Galli Diego Signorelli Claudia Giani Teresa Beninato Chiara Carlotta Pircher Alessandro Rametta Sokol Kosta Michele Zanitti Maria Rosa Di Mauro Arturo Rinaldi Settimio Di Gregorio Martinetti Antonia Marina Chiara Garassino Filippo G. M. de Braud Marcello Restelli Giuseppe Lo Russo Monica Ganzinelli Francesco Trovò Alessandra Laura Giulia Pedrocchi
container_volume	12
class	RC254-282
format_se	Elektronische Aufsätze
author-letter	Arsela Prelaj
doi_str_mv	10.3389/fonc.2022.1078822
author2-role	verfasserin
title_sort	real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in nsclc patients
callnumber	RC254-282
title_auth	Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients
abstract	IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.
abstractGer	IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.
abstract_unstemmed	IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_2003 GBV_ILN_2014 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
title_short	Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients
url	https://doi.org/10.3389/fonc.2022.1078822 https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5 https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full https://doaj.org/toc/2234-943X
remote_bool	true
author2	Arsela Prelaj Edoardo Gregorio Galli Vanja Miskovic Mattia Pesenti Giuseppe Viscardi Benedetta Pedica Laura Mazzeo Achille Bottiglieri Leonardo Provenzano Andrea Spagnoletti Roberto Marinacci Alessandro De Toma Claudia Proto Roberto Ferrara Marta Brambilla Mario Occhipinti Sara Manglaviti Giulia Galli Diego Signorelli Claudia Giani Teresa Beninato Chiara Carlotta Pircher Alessandro Rametta Sokol Kosta Michele Zanitti Maria Rosa Di Mauro Arturo Rinaldi Settimio Di Gregorio Martinetti Antonia Marina Chiara Garassino Filippo G. M. de Braud Marcello Restelli Giuseppe Lo Russo Monica Ganzinelli Francesco Trovò Alessandra Laura Giulia Pedrocchi
author2Str	Arsela Prelaj Edoardo Gregorio Galli Vanja Miskovic Mattia Pesenti Giuseppe Viscardi Benedetta Pedica Laura Mazzeo Achille Bottiglieri Leonardo Provenzano Andrea Spagnoletti Roberto Marinacci Alessandro De Toma Claudia Proto Roberto Ferrara Marta Brambilla Mario Occhipinti Sara Manglaviti Giulia Galli Diego Signorelli Claudia Giani Teresa Beninato Chiara Carlotta Pircher Alessandro Rametta Sokol Kosta Michele Zanitti Maria Rosa Di Mauro Arturo Rinaldi Settimio Di Gregorio Martinetti Antonia Marina Chiara Garassino Filippo G. M. de Braud Marcello Restelli Giuseppe Lo Russo Monica Ganzinelli Francesco Trovò Alessandra Laura Giulia Pedrocchi
ppnlink	684965518
callnumber-subject	RC - Internal Medicine
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3389/fonc.2022.1078822
callnumber-a	RC254-282
up_date	2024-07-03T20:58:37.443Z
_version_	1803592995904159744
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ081622465</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230310220850.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fonc.2022.1078822</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ081622465</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJc99b6a5fcaed44e39c58687c3976c7f5</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">RC254-282</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Arsela Prelaj</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</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">IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">non-small cell lung cancer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">immunotherapy</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">explainable artificial intelligence</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">treatment</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Neoplasms. Tumors. Oncology. Including cancer and carcinogens</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Arsela Prelaj</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Edoardo Gregorio Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Edoardo Gregorio Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Edoardo Gregorio Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Vanja Miskovic</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mattia Pesenti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giuseppe Viscardi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giuseppe Viscardi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Benedetta Pedica</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laura Mazzeo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laura Mazzeo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Laura Mazzeo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Achille Bottiglieri</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Achille Bottiglieri</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Leonardo Provenzano</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Leonardo Provenzano</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Andrea Spagnoletti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Andrea Spagnoletti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Roberto Marinacci</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandro De Toma</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Proto</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Roberto Ferrara</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marta Brambilla</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mario Occhipinti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sara Manglaviti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giulia Galli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Diego Signorelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Diego Signorelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Giani</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Claudia Giani</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Teresa Beninato</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Teresa Beninato</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chiara Carlotta Pircher</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chiara Carlotta Pircher</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandro Rametta</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandro Rametta</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sokol Kosta</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Michele Zanitti</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Maria Rosa Di Mauro</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Arturo Rinaldi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Settimio Di Gregorio</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Martinetti Antonia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marina Chiara Garassino</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marina Chiara Garassino</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Filippo G. M. de Braud</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Filippo G. M. de Braud</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Marcello Restelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Giuseppe Lo Russo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Monica Ganzinelli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Francesco Trovò</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Alessandra Laura Giulia Pedrocchi</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">Frontiers in Oncology</subfield><subfield code="d">Frontiers Media S.A., 2012</subfield><subfield code="g">12(2023)</subfield><subfield code="w">(DE-627)684965518</subfield><subfield code="w">(DE-600)2649216-7</subfield><subfield code="x">2234943X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:12</subfield><subfield code="g">year:2023</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fonc.2022.1078822</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/c99b6a5fcaed44e39c58687c3976c7f5</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fonc.2022.1078822/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2234-943X</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">GBV_ILN_11</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_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_2003</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_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">12</subfield><subfield code="j">2023</subfield></datafield></record></collection>
score	7.4021015

Nicht das Richtige dabei?

Schreiben Sie uns!

Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?