Predicting ICD therapy events through machine learning: bridging clinical predictors and device data
T Chiba, S Wegner, R Haettasch, V Tscholl, N Dagres, W Haverkamp, G Hindricks, F Hohendanner · 2026
Read Predicting ICD therapy events through machine learning: bridging clinical predictors and device data by T Chiba, S Wegner, R Haettasch, V Tscholl, N Dagres, W Haverkamp, G Hindricks, F Hohendanner (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-13302325.txt.
Description
T Chiba and colleagues build, in a 2026 study, a machine learning model that predicts whether a defibrillator patient will actually receive therapy from the device. Many recipients never need a pacing burst or shock, so forecasting could tune follow-up intensity and programming. Routine clinical details and device measurements supplied the model's inputs.
Records covered 516 consecutive patients implanted between 2020 and 2024, with follow-up averaging under three years. A random forest flagged future therapy with strong accuracy on held-out patients, and the highest-risk tenth carried over four times the average event rate. Brief non-sustained fast rhythms, body mass index, lead impedance, and pumping strength drove most predictions. The authors propose the tool for personalised device clinic planning.
Catalog record
| CREATOR | T Chiba, S Wegner, R Haettasch, V Tscholl, N Dagres, W Haverkamp, G Hindricks, F Hohendanner |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |