Time-Dependent ECG-AI Prediction of Fatal Coronary Heart Disease: A Retrospective Study
Liam Butler, Alexander Ivanov, Turgay Celik, Ibrahim Karabayir, Lokesh Chinthala, Mohammad S. Tootooni, Byron C. Jaeger, Luke T. Patterson, Adam J. Doerr, David D. McManus, Robert L. Davis, David Herrington, Oguz Akbilgic · 2024
Read Time-Dependent ECG-AI Prediction of Fatal Coronary Heart Disease: A Retrospective Study by Liam Butler, Alexander Ivanov, Turgay Celik, Ibrahim Karabayir, Lokesh Chinthala, Mohammad S. Tootooni, Byron C. Jaeger, Luke T. Patterson, Adam J. Doerr, David D. McManus, Robert L. Davis, David Herrington, Oguz Akbilgic (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11678222.txt.
Description
Liam Butler and co-authors build AI models that predict fatal heart disease from heart tracings, in work from 2024. Fatal coronary disease strikes about 650 thousand people a year in the United States. A ten-second tracing is cheap and painless, so a strong model could screen widely.
Training data came from over fifty thousand patients at one medical center. Two networks were built, one using all twelve leads and one using a single lead. Their outputs fed risk models that also used age and clinical facts. A second hospital system supplied outside test data. The single-lead model's success matters, since simple wearables capture just one lead.
Catalog record
| CREATOR | Liam Butler, Alexander Ivanov, Turgay Celik, Ibrahim Karabayir, Lokesh Chinthala, Mohammad S. Tootooni, Byron C. Jaeger, Luke T. Patterson, Adam J. Doerr, David D. McManus, Robert L. Davis, David Herrington, Oguz Akbilgic |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |