Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling
<jats:p>Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate the effect of small sample size, we introduce a pre-training approach, <jats:bold>P</jats:bold>atient <jats:bold>C</jats:bold>ontras...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022
|
| Online Access: | https://hdl.handle.net/1721.1/143901 |
| _version_ | 1826214546606391296 |
|---|---|
| author | Diamant, Nathaniel Reinertsen, Erik Song, Steven Aguirre, Aaron D Stultz, Collin M Batra, Puneet |
| author2 | Massachusetts Institute of Technology. Research Laboratory of Electronics |
| author_facet | Massachusetts Institute of Technology. Research Laboratory of Electronics Diamant, Nathaniel Reinertsen, Erik Song, Steven Aguirre, Aaron D Stultz, Collin M Batra, Puneet |
| author_sort | Diamant, Nathaniel |
| collection | MIT |
| description | <jats:p>Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate the effect of small sample size, we introduce a pre-training approach, <jats:bold>P</jats:bold>atient <jats:bold>C</jats:bold>ontrastive <jats:bold>L</jats:bold>earning of <jats:bold>R</jats:bold>epresentations (PCLR), which creates latent representations of electrocardiograms (ECGs) from a large number of unlabeled examples using contrastive learning. The resulting representations are expressive, performant, and practical across a wide spectrum of clinical tasks. We develop PCLR using a large health care system with over 3.2 million 12-lead ECGs and demonstrate that training linear models on PCLR representations achieves a 51% performance increase, on average, over six training set sizes and four tasks (sex classification, age regression, and the detection of left ventricular hypertrophy and atrial fibrillation), relative to training neural network models from scratch. We also compared PCLR to three other ECG pre-training approaches (supervised pre-training, unsupervised pre-training with an autoencoder, and pre-training using a contrastive multi ECG-segment approach), and show significant performance benefits in three out of four tasks. We found an average performance benefit of 47% over the other models and an average of a 9% performance benefit compared to best model for each task. We release PCLR to enable others to extract ECG representations at <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/broadinstitute/ml4h/tree/master/model_zoo/PCLR" xlink:type="simple">https://github.com/broadinstitute/ml4h/tree/master/model_zoo/PCLR</jats:ext-link>.</jats:p> |
| first_indexed | 2024-09-23T16:07:31Z |
| format | Article |
| id | mit-1721.1/143901 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:07:31Z |
| publishDate | 2022 |
| publisher | Public Library of Science (PLoS) |
| record_format | dspace |
| spelling | mit-1721.1/1439012023-01-18T20:31:47Z Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling Diamant, Nathaniel Reinertsen, Erik Song, Steven Aguirre, Aaron D Stultz, Collin M Batra, Puneet Massachusetts Institute of Technology. Research Laboratory of Electronics Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Harvard University--MIT Division of Health Sciences and Technology <jats:p>Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate the effect of small sample size, we introduce a pre-training approach, <jats:bold>P</jats:bold>atient <jats:bold>C</jats:bold>ontrastive <jats:bold>L</jats:bold>earning of <jats:bold>R</jats:bold>epresentations (PCLR), which creates latent representations of electrocardiograms (ECGs) from a large number of unlabeled examples using contrastive learning. The resulting representations are expressive, performant, and practical across a wide spectrum of clinical tasks. We develop PCLR using a large health care system with over 3.2 million 12-lead ECGs and demonstrate that training linear models on PCLR representations achieves a 51% performance increase, on average, over six training set sizes and four tasks (sex classification, age regression, and the detection of left ventricular hypertrophy and atrial fibrillation), relative to training neural network models from scratch. We also compared PCLR to three other ECG pre-training approaches (supervised pre-training, unsupervised pre-training with an autoencoder, and pre-training using a contrastive multi ECG-segment approach), and show significant performance benefits in three out of four tasks. We found an average performance benefit of 47% over the other models and an average of a 9% performance benefit compared to best model for each task. We release PCLR to enable others to extract ECG representations at <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/broadinstitute/ml4h/tree/master/model_zoo/PCLR" xlink:type="simple">https://github.com/broadinstitute/ml4h/tree/master/model_zoo/PCLR</jats:ext-link>.</jats:p> 2022-07-20T17:33:16Z 2022-07-20T17:33:16Z 2022 2022-07-20T17:03:37Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/143901 Diamant, Nathaniel, Reinertsen, Erik, Song, Steven, Aguirre, Aaron D, Stultz, Collin M et al. 2022. "Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling." PLoS Computational Biology, 18 (2). en 10.1371/JOURNAL.PCBI.1009862 PLoS Computational Biology Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Public Library of Science (PLoS) PLoS |
| spellingShingle | Diamant, Nathaniel Reinertsen, Erik Song, Steven Aguirre, Aaron D Stultz, Collin M Batra, Puneet Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling |
| title | Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling |
| title_full | Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling |
| title_fullStr | Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling |
| title_full_unstemmed | Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling |
| title_short | Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling |
| title_sort | patient contrastive learning a performant expressive and practical approach to electrocardiogram modeling |
| url | https://hdl.handle.net/1721.1/143901 |
| work_keys_str_mv | AT diamantnathaniel patientcontrastivelearningaperformantexpressiveandpracticalapproachtoelectrocardiogrammodeling AT reinertsenerik patientcontrastivelearningaperformantexpressiveandpracticalapproachtoelectrocardiogrammodeling AT songsteven patientcontrastivelearningaperformantexpressiveandpracticalapproachtoelectrocardiogrammodeling AT aguirreaarond patientcontrastivelearningaperformantexpressiveandpracticalapproachtoelectrocardiogrammodeling AT stultzcollinm patientcontrastivelearningaperformantexpressiveandpracticalapproachtoelectrocardiogrammodeling AT batrapuneet patientcontrastivelearningaperformantexpressiveandpracticalapproachtoelectrocardiogrammodeling |