An ECG biomarker for sudden cardiac death discovered with deep learning
Ziad Obermeyer, Alexander Schubert, James Ross, Sendhil Mullainathan, Markus Lingman · 2026
Read An ECG biomarker for sudden cardiac death discovered with deep learning by Ziad Obermeyer, Alexander Schubert, James Ross, Sendhil Mullainathan, Markus Lingman (2026) 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/PMC13323061.txt.
Description
Ziad Obermeyer and co-authors train deep learning on electrocardiograms to flag sudden cardiac death risk, in a 2026 study linking all ECGs in a Swedish region to death records. The standard marker, left ventricular ejection fraction, misses most such deaths and flags many low-risk people.
Their model marked a small high-risk group, given as 2.2 percent of the sample, whose yearly rate of sudden cardiac death beat that of the low ejection fraction group. Most model-flagged patients were not flagged by ejection fraction at all. Checks in a United States health system and a Taiwanese registry supported the signal. A paired generative model made the waveform pattern visible for study.
Catalog record
| CREATOR | Ziad Obermeyer, Alexander Schubert, James Ross, Sendhil Mullainathan, Markus Lingman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67223 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |