False positive rate of modern ICMs according to guideline-defined annotation rules
N Varma, A Lazarus, A Menet, P Defaye, P Mabo, E Crespin · 2026
Read False positive rate of modern ICMs according to guideline-defined annotation rules by N Varma, A Lazarus, A Menet, P Defaye, P Mabo, E Crespin (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-13302768.txt.
Description
N Varma and co-authors measure, in a 2026 study, how many alerts from modern implanted heart monitors turn out to be clinically pointless when judged by strict guideline rules. Clinics drown in device transmissions, and each brand pre-filters differently. An independent committee re-read episodes under one standard annotation scheme.
The dataset held 2,659 episodes from 1,710 patients carrying monitors from four major makers. Among devices without built-in artificial intelligence, about forty-five percent of episodes were non-actionable and a fifth were unreadable or uncertain. Artificial intelligence models did better on real events but left even more episodes in the uncertain bucket. Pause alerts misled most often, frequently caused by undersensing, and the authors demand better universal analysis tools.
Catalog record
| CREATOR | N Varma, A Lazarus, A Menet, P Defaye, P Mabo, E Crespin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |