Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers
The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Lopes, Ricardo R. [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs - Tacheci, Ilja ELSEVIER, 2014, an international journal, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:131 ; year:2021 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.compbiomed.2021.104262 |
|---|
| Katalog-ID: |
ELV053423585 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV053423585 | ||
| 003 | DE-627 | ||
| 005 | 20230626034818.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210910s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2021.104262 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica |
| 035 | |a (DE-627)ELV053423585 | ||
| 035 | |a (ELSEVIER)S0010-4825(21)00056-1 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 082 | 0 | 4 | |a 570 |q VZ |
| 084 | |a BIODIV |q DE-30 |2 fid | ||
| 084 | |a 35.70 |2 bkl | ||
| 084 | |a 42.12 |2 bkl | ||
| 084 | |a 42.15 |2 bkl | ||
| 100 | 1 | |a Lopes, Ricardo R. |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers |
| 264 | 1 | |c 2021transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. | ||
| 520 | |a The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. | ||
| 650 | 7 | |a Deep learning |2 Elsevier | |
| 650 | 7 | |a Transfer learning |2 Elsevier | |
| 650 | 7 | |a Cardiomyopathy |2 Elsevier | |
| 650 | 7 | |a Genetic heart disease |2 Elsevier | |
| 650 | 7 | |a Phospholamban |2 Elsevier | |
| 650 | 7 | |a ECG analysis |2 Elsevier | |
| 700 | 1 | |a Bleijendaal, Hidde |4 oth | |
| 700 | 1 | |a Ramos, Lucas A. |4 oth | |
| 700 | 1 | |a Verstraelen, Tom E. |4 oth | |
| 700 | 1 | |a Amin, Ahmad S. |4 oth | |
| 700 | 1 | |a Wilde, Arthur A.M. |4 oth | |
| 700 | 1 | |a Pinto, Yigal M. |4 oth | |
| 700 | 1 | |a de Mol, Bas A.J.M. |4 oth | |
| 700 | 1 | |a Marquering, Henk A. |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Tacheci, Ilja ELSEVIER |t Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs |d 2014 |d an international journal |g Amsterdam [u.a.] |w (DE-627)ELV012617792 |
| 773 | 1 | 8 | |g volume:131 |g year:2021 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.compbiomed.2021.104262 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a FID-BIODIV | ||
| 912 | |a SSG-OLC-PHA | ||
| 912 | |a GBV_ILN_11 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_39 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_120 | ||
| 912 | |a GBV_ILN_257 | ||
| 936 | b | k | |a 35.70 |j Biochemie: Allgemeines |q VZ |
| 936 | b | k | |a 42.12 |j Biophysik |q VZ |
| 936 | b | k | |a 42.15 |j Zellbiologie |q VZ |
| 951 | |a AR | ||
| 952 | |d 131 |j 2021 |h 0 | ||
| author_variant |
r r l rr rrl |
|---|---|
| matchkey_str |
lopesricardorbleijendaalhidderamoslucasa:2021----:mrvneetoadormaedtcinfaeeeihatiesuigrnfrerignplctotp |
| hierarchy_sort_str |
2021transfer abstract |
| bklnumber |
35.70 42.12 42.15 |
| publishDate |
2021 |
| allfields |
10.1016/j.compbiomed.2021.104262 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica (DE-627)ELV053423585 (ELSEVIER)S0010-4825(21)00056-1 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Lopes, Ricardo R. verfasserin aut Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Elsevier Bleijendaal, Hidde oth Ramos, Lucas A. oth Verstraelen, Tom E. oth Amin, Ahmad S. oth Wilde, Arthur A.M. oth Pinto, Yigal M. oth de Mol, Bas A.J.M. oth Marquering, Henk A. oth Enthalten in Elsevier Science Tacheci, Ilja ELSEVIER Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs 2014 an international journal Amsterdam [u.a.] (DE-627)ELV012617792 volume:131 year:2021 pages:0 https://doi.org/10.1016/j.compbiomed.2021.104262 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA GBV_ILN_11 GBV_ILN_22 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_65 GBV_ILN_120 GBV_ILN_257 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 131 2021 0 |
| spelling |
10.1016/j.compbiomed.2021.104262 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica (DE-627)ELV053423585 (ELSEVIER)S0010-4825(21)00056-1 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Lopes, Ricardo R. verfasserin aut Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Elsevier Bleijendaal, Hidde oth Ramos, Lucas A. oth Verstraelen, Tom E. oth Amin, Ahmad S. oth Wilde, Arthur A.M. oth Pinto, Yigal M. oth de Mol, Bas A.J.M. oth Marquering, Henk A. oth Enthalten in Elsevier Science Tacheci, Ilja ELSEVIER Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs 2014 an international journal Amsterdam [u.a.] (DE-627)ELV012617792 volume:131 year:2021 pages:0 https://doi.org/10.1016/j.compbiomed.2021.104262 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA GBV_ILN_11 GBV_ILN_22 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_65 GBV_ILN_120 GBV_ILN_257 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 131 2021 0 |
| allfields_unstemmed |
10.1016/j.compbiomed.2021.104262 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica (DE-627)ELV053423585 (ELSEVIER)S0010-4825(21)00056-1 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Lopes, Ricardo R. verfasserin aut Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Elsevier Bleijendaal, Hidde oth Ramos, Lucas A. oth Verstraelen, Tom E. oth Amin, Ahmad S. oth Wilde, Arthur A.M. oth Pinto, Yigal M. oth de Mol, Bas A.J.M. oth Marquering, Henk A. oth Enthalten in Elsevier Science Tacheci, Ilja ELSEVIER Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs 2014 an international journal Amsterdam [u.a.] (DE-627)ELV012617792 volume:131 year:2021 pages:0 https://doi.org/10.1016/j.compbiomed.2021.104262 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA GBV_ILN_11 GBV_ILN_22 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_65 GBV_ILN_120 GBV_ILN_257 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 131 2021 0 |
| allfieldsGer |
10.1016/j.compbiomed.2021.104262 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica (DE-627)ELV053423585 (ELSEVIER)S0010-4825(21)00056-1 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Lopes, Ricardo R. verfasserin aut Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Elsevier Bleijendaal, Hidde oth Ramos, Lucas A. oth Verstraelen, Tom E. oth Amin, Ahmad S. oth Wilde, Arthur A.M. oth Pinto, Yigal M. oth de Mol, Bas A.J.M. oth Marquering, Henk A. oth Enthalten in Elsevier Science Tacheci, Ilja ELSEVIER Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs 2014 an international journal Amsterdam [u.a.] (DE-627)ELV012617792 volume:131 year:2021 pages:0 https://doi.org/10.1016/j.compbiomed.2021.104262 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA GBV_ILN_11 GBV_ILN_22 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_65 GBV_ILN_120 GBV_ILN_257 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 131 2021 0 |
| allfieldsSound |
10.1016/j.compbiomed.2021.104262 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica (DE-627)ELV053423585 (ELSEVIER)S0010-4825(21)00056-1 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Lopes, Ricardo R. verfasserin aut Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Elsevier Bleijendaal, Hidde oth Ramos, Lucas A. oth Verstraelen, Tom E. oth Amin, Ahmad S. oth Wilde, Arthur A.M. oth Pinto, Yigal M. oth de Mol, Bas A.J.M. oth Marquering, Henk A. oth Enthalten in Elsevier Science Tacheci, Ilja ELSEVIER Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs 2014 an international journal Amsterdam [u.a.] (DE-627)ELV012617792 volume:131 year:2021 pages:0 https://doi.org/10.1016/j.compbiomed.2021.104262 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA GBV_ILN_11 GBV_ILN_22 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_65 GBV_ILN_120 GBV_ILN_257 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 131 2021 0 |
| language |
English |
| source |
Enthalten in Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs Amsterdam [u.a.] volume:131 year:2021 pages:0 |
| sourceStr |
Enthalten in Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs Amsterdam [u.a.] volume:131 year:2021 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Biochemie: Allgemeines Biophysik Zellbiologie |
| institution |
findex.gbv.de |
| topic_facet |
Deep learning Transfer learning Cardiomyopathy Genetic heart disease Phospholamban ECG analysis |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs |
| authorswithroles_txt_mv |
Lopes, Ricardo R. @@aut@@ Bleijendaal, Hidde @@oth@@ Ramos, Lucas A. @@oth@@ Verstraelen, Tom E. @@oth@@ Amin, Ahmad S. @@oth@@ Wilde, Arthur A.M. @@oth@@ Pinto, Yigal M. @@oth@@ de Mol, Bas A.J.M. @@oth@@ Marquering, Henk A. @@oth@@ |
| publishDateDaySort_date |
2021-01-01T00:00:00Z |
| hierarchy_top_id |
ELV012617792 |
| dewey-sort |
3610 |
| id |
ELV053423585 |
| 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">ELV053423585</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626034818.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.compbiomed.2021.104262</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV053423585</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0010-4825(21)00056-1</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="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">35.70</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.12</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.15</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lopes, Ricardo R.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Deep learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Transfer learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Cardiomyopathy</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Genetic heart disease</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Phospholamban</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">ECG analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bleijendaal, Hidde</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ramos, Lucas A.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Verstraelen, Tom E.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Amin, Ahmad S.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wilde, Arthur A.M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pinto, Yigal M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">de Mol, Bas A.J.M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Marquering, Henk A.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Tacheci, Ilja ELSEVIER</subfield><subfield code="t">Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs</subfield><subfield code="d">2014</subfield><subfield code="d">an international journal</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV012617792</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:131</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.compbiomed.2021.104262</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</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_11</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_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_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_257</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">35.70</subfield><subfield code="j">Biochemie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.12</subfield><subfield code="j">Biophysik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.15</subfield><subfield code="j">Zellbiologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">131</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Lopes, Ricardo R. |
| spellingShingle |
Lopes, Ricardo R. ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers |
| authorStr |
Lopes, Ricardo R. |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV012617792 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health 570 - Life sciences; biology |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis Elsevier |
| topic |
ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis |
| topic_unstemmed |
ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis |
| topic_browse |
ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier Deep learning Elsevier Transfer learning Elsevier Cardiomyopathy Elsevier Genetic heart disease Elsevier Phospholamban Elsevier ECG analysis |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
h b hb l a r la lar t e v te tev a s a as asa a a w aa aaw y m p ym ymp m b a d mba mbad h a m ha ham |
| hierarchy_parent_title |
Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs |
| hierarchy_parent_id |
ELV012617792 |
| dewey-tens |
610 - Medicine & health 570 - Life sciences; biology |
| hierarchy_top_title |
Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV012617792 |
| title |
Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers |
| ctrlnum |
(DE-627)ELV053423585 (ELSEVIER)S0010-4825(21)00056-1 |
| title_full |
Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers |
| author_sort |
Lopes, Ricardo R. |
| journal |
Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs |
| journalStr |
Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology 500 - Science |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Lopes, Ricardo R. |
| container_volume |
131 |
| class |
610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Lopes, Ricardo R. |
| doi_str_mv |
10.1016/j.compbiomed.2021.104262 |
| dewey-full |
610 570 |
| title_sort |
improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: an application to phospholamban p.arg14del mutation carriers |
| title_auth |
Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers |
| abstract |
The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. |
| abstractGer |
The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. |
| abstract_unstemmed |
The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA GBV_ILN_11 GBV_ILN_22 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_65 GBV_ILN_120 GBV_ILN_257 |
| title_short |
Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers |
| url |
https://doi.org/10.1016/j.compbiomed.2021.104262 |
| remote_bool |
true |
| author2 |
Bleijendaal, Hidde Ramos, Lucas A. Verstraelen, Tom E. Amin, Ahmad S. Wilde, Arthur A.M. Pinto, Yigal M. de Mol, Bas A.J.M. Marquering, Henk A. |
| author2Str |
Bleijendaal, Hidde Ramos, Lucas A. Verstraelen, Tom E. Amin, Ahmad S. Wilde, Arthur A.M. Pinto, Yigal M. de Mol, Bas A.J.M. Marquering, Henk A. |
| ppnlink |
ELV012617792 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth oth oth oth |
| doi_str |
10.1016/j.compbiomed.2021.104262 |
| up_date |
2024-07-06T18:54:49.934Z |
| _version_ |
1803856998495682560 |
| 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">ELV053423585</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626034818.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.compbiomed.2021.104262</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001328.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV053423585</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0010-4825(21)00056-1</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="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">35.70</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.12</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.15</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lopes, Ricardo R.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The pathogenic mutation p.Arg14del in the gene encoding Phospholamban (PLN) is known to cause cardiomyopathy and leads to increased risk of sudden cardiac death. Automatic tools might improve the detection of patients with this rare disease. Deep learning is currently the state-of-the-art in signal processing but requires large amounts of data to train the algorithms. In situations with relatively small amounts of data, like PLN, transfer learning may improve accuracy. We propose an ECG-based detection of the PLN mutation using transfer learning from a model originally trained for sex identification. The sex identification model was trained with 256,278 ECGs and subsequently finetuned for PLN detection (155 ECGs of patients with PLN) with two control groups: a balanced age/sex matched group and a randomly selected imbalanced population. The data was split in 10 folds and 20% of the training data was used for validation and early stopping. The models were evaluated with the area under the receiver operating characteristic curve (AUROC) of the testing data. We used gradient activation for explanation of the prediction models. The models trained with transfer learning outperformed the models trained from scratch for both the balanced (AUROC 0.87 vs AUROC 0.71) and imbalanced (AUROC 0.0.90 vs AUROC 0.65) population. The proposed approach was able to improve the accuracy of a rare disease detection model by transfer learning information from a non-manual annotated and abundant label with only limited data available.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Deep learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Transfer learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Cardiomyopathy</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Genetic heart disease</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Phospholamban</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">ECG analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bleijendaal, Hidde</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ramos, Lucas A.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Verstraelen, Tom E.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Amin, Ahmad S.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wilde, Arthur A.M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pinto, Yigal M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">de Mol, Bas A.J.M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Marquering, Henk A.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Tacheci, Ilja ELSEVIER</subfield><subfield code="t">Sa1349 Impact of Water Load Test on the Gastric Myoelectric Activity in Experimental Pigs</subfield><subfield code="d">2014</subfield><subfield code="d">an international journal</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV012617792</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:131</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.compbiomed.2021.104262</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</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_11</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_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_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_257</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">35.70</subfield><subfield code="j">Biochemie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.12</subfield><subfield code="j">Biophysik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.15</subfield><subfield code="j">Zellbiologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">131</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.400916 |