Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms
Abstract The feasibility and value of linking electrocardiogram (ECG) data to longitudinal population-level administrative health data to facilitate the development of a learning healthcare system has not been fully explored. We developed ECG-based machine learning models to predict risk of mortalit...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-023-00765-3 |
| _version_ | 1827609253454544896 |
|---|---|
| author | Weijie Sun Sunil Vasu Kalmady Nariman Sepehrvand Amir Salimi Yousef Nademi Kevin Bainey Justin A. Ezekowitz Russell Greiner Abram Hindle Finlay A. McAlister Roopinder K. Sandhu Padma Kaul |
| author_facet | Weijie Sun Sunil Vasu Kalmady Nariman Sepehrvand Amir Salimi Yousef Nademi Kevin Bainey Justin A. Ezekowitz Russell Greiner Abram Hindle Finlay A. McAlister Roopinder K. Sandhu Padma Kaul |
| author_sort | Weijie Sun |
| collection | DOAJ |
| description | Abstract The feasibility and value of linking electrocardiogram (ECG) data to longitudinal population-level administrative health data to facilitate the development of a learning healthcare system has not been fully explored. We developed ECG-based machine learning models to predict risk of mortality among patients presenting to an emergency department or hospital for any reason. Using the 12-lead ECG traces and measurements from 1,605,268 ECGs from 748,773 healthcare episodes of 244,077 patients (2007–2020) in Alberta, Canada, we developed and validated ResNet-based Deep Learning (DL) and gradient boosting-based XGBoost (XGB) models to predict 30-day, 1-year, and 5-year mortality. The models for 30-day, 1-year, and 5-year mortality were trained on 146,173, 141,072, and 111,020 patients and evaluated on 97,144, 89,379, and 55,650 patients, respectively. In the evaluation cohort, 7.6%, 17.3%, and 32.9% patients died by 30-days, 1-year, and 5-years, respectively. ResNet models based on ECG traces alone had good-to-excellent performance with area under receiver operating characteristic curve (AUROC) of 0.843 (95% CI: 0.838–0.848), 0.812 (0.808–0.816), and 0.798 (0.792–0.803) for 30-day, 1-year and 5-year prediction, respectively; and were superior to XGB models based on ECG measurements with AUROC of 0.782 (0.776–0.789), 0.784 (0.780–0.788), and 0.746 (0.740–0.751). This study demonstrates the validity of ECG-based DL mortality prediction models at the population-level that can be leveraged for prognostication at point of care. |
| first_indexed | 2024-03-09T07:29:40Z |
| format | Article |
| id | doaj.art-db1c2fd99ca3440ea1b8986df5321667 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T07:29:40Z |
| publishDate | 2023-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-db1c2fd99ca3440ea1b8986df53216672023-12-03T06:46:06ZengNature Portfolionpj Digital Medicine2398-63522023-02-016111210.1038/s41746-023-00765-3Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiogramsWeijie Sun0Sunil Vasu Kalmady1Nariman Sepehrvand2Amir Salimi3Yousef Nademi4Kevin Bainey5Justin A. Ezekowitz6Russell Greiner7Abram Hindle8Finlay A. McAlister9Roopinder K. Sandhu10Padma Kaul11Department of Computing Science, University of AlbertaDepartment of Computing Science, University of AlbertaCanadian VIGOUR Centre, Department of Medicine, University of AlbertaDepartment of Computing Science, University of AlbertaDepartment of Computing Science, University of AlbertaCanadian VIGOUR Centre, Department of Medicine, University of AlbertaCanadian VIGOUR Centre, Department of Medicine, University of AlbertaDepartment of Computing Science, University of AlbertaDepartment of Computing Science, University of AlbertaCanadian VIGOUR Centre, Department of Medicine, University of AlbertaCanadian VIGOUR Centre, Department of Medicine, University of AlbertaCanadian VIGOUR Centre, Department of Medicine, University of AlbertaAbstract The feasibility and value of linking electrocardiogram (ECG) data to longitudinal population-level administrative health data to facilitate the development of a learning healthcare system has not been fully explored. We developed ECG-based machine learning models to predict risk of mortality among patients presenting to an emergency department or hospital for any reason. Using the 12-lead ECG traces and measurements from 1,605,268 ECGs from 748,773 healthcare episodes of 244,077 patients (2007–2020) in Alberta, Canada, we developed and validated ResNet-based Deep Learning (DL) and gradient boosting-based XGBoost (XGB) models to predict 30-day, 1-year, and 5-year mortality. The models for 30-day, 1-year, and 5-year mortality were trained on 146,173, 141,072, and 111,020 patients and evaluated on 97,144, 89,379, and 55,650 patients, respectively. In the evaluation cohort, 7.6%, 17.3%, and 32.9% patients died by 30-days, 1-year, and 5-years, respectively. ResNet models based on ECG traces alone had good-to-excellent performance with area under receiver operating characteristic curve (AUROC) of 0.843 (95% CI: 0.838–0.848), 0.812 (0.808–0.816), and 0.798 (0.792–0.803) for 30-day, 1-year and 5-year prediction, respectively; and were superior to XGB models based on ECG measurements with AUROC of 0.782 (0.776–0.789), 0.784 (0.780–0.788), and 0.746 (0.740–0.751). This study demonstrates the validity of ECG-based DL mortality prediction models at the population-level that can be leveraged for prognostication at point of care.https://doi.org/10.1038/s41746-023-00765-3 |
| spellingShingle | Weijie Sun Sunil Vasu Kalmady Nariman Sepehrvand Amir Salimi Yousef Nademi Kevin Bainey Justin A. Ezekowitz Russell Greiner Abram Hindle Finlay A. McAlister Roopinder K. Sandhu Padma Kaul Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms npj Digital Medicine |
| title | Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms |
| title_full | Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms |
| title_fullStr | Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms |
| title_full_unstemmed | Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms |
| title_short | Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms |
| title_sort | towards artificial intelligence based learning health system for population level mortality prediction using electrocardiograms |
| url | https://doi.org/10.1038/s41746-023-00765-3 |
| work_keys_str_mv | AT weijiesun towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT sunilvasukalmady towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT narimansepehrvand towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT amirsalimi towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT yousefnademi towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT kevinbainey towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT justinaezekowitz towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT russellgreiner towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT abramhindle towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT finlayamcalister towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT roopinderksandhu towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms AT padmakaul towardsartificialintelligencebasedlearninghealthsystemforpopulationlevelmortalitypredictionusingelectrocardiograms |