Multimodal deep learning for near term prediction of new onset atrial fibrillation in hospitalized patients
U K Khanolkar, A Y Yadav, R P Pisipati, A M Mann, L A Alomari, E O Otabor, P C Chacko, C B Brent, S P Pappada, A D Deshmukh, A Maan · 2026
Read Multimodal deep learning for near term prediction of new onset atrial fibrillation in hospitalized patients by U K Khanolkar, A Y Yadav, R P Pisipati, A M Mann, L A Alomari, E O Otabor, P C Chacko, C B Brent, S P Pappada, A D Deshmukh, A Maan (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-13299881.txt.
Description
U K Khanolkar and a team fuse heart tracing waveforms with clinical data to predict new atrial fibrillation during hospital stays, in a 2026 modelling study. New rhythm problems during acute illness predict poor outcomes, and simple clinical scores miss cases. Their system trains one network on raw tracings and another on structured variables such as age, heart rate, laboratory values, and medicines.
The fused model beat either single-source model on held-out test data. Threshold tuning trades sensitivity against false alarms: one setting catches most future cases for wide screening, while a stricter setting cuts false alarms sharply when follow-up resources are scarce, the authors report.
Catalog record
| CREATOR | U K Khanolkar, A Y Yadav, R P Pisipati, A M Mann, L A Alomari, E O Otabor, P C Chacko, C B Brent, S P Pappada, A D Deshmukh, A Maan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |