Comment on “A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods”
E. Jayanthi, P.Y. Mallikarjun · 2026
Read Comment on “A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods” by E. Jayanthi, P.Y. Mallikarjun (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/pmc-13631530.txt.
Description
Jayanthi and Mallikarjun write a comment on a trial testing AI heart tracing support for finding weak hearts. Their 2026 letter praises the design: the tool sits inside routine record workflows across five health systems, a step past email alerts in an earlier trial. One flaw draws their fire.
The main endpoint counts detection of low ejection fraction by ultrasound. That count rises whenever clinicians simply order more ultrasounds, whether or not the AI flags the right patients. A yield measure, the share of ordered scans that confirm weakness, sits as a side endpoint only. Without pairing the two, a positive result could mean sharp AI or just more testing. The letter urges elevating yield beside detection so the trial verdict can be read cleanly.
Catalog record
| CREATOR | E. Jayanthi, P.Y. Mallikarjun |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 5 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |