Meta-heuristic and machine learning based functional capacity prediction using gait parameters in patients with heart failure
Aylin Tanriverdi Eyolcu, Ayşe Doğru, Selim Buyrukoğlu, Sema Savci, Buse Ozcan Kahraman, Mehmet Birhan Yilmaz · 2026
Read Meta-heuristic and machine learning based functional capacity prediction using gait parameters in patients with heart failure by Aylin Tanriverdi Eyolcu, Ayşe Doğru, Selim Buyrukoğlu, Sema Savci, Buse Ozcan Kahraman, Mehmet Birhan Yilmaz (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-13473135.txt.
Description
Aylin Tanriverdi Eyolcu and five colleagues tested in 2026 whether walking patterns measured by a wearable sensor could predict how far heart failure patients can walk. Functional capacity, usually judged by a six-minute walk test, guides treatment and prognosis, yet clinic tests take time and staff. Seventy patients wore an inertial sensor while walking. The team fed stride and movement measures into four machine learning models, each tuned by four optimisation methods, with results checked by ten-fold cross-validation.
A hybrid pairing particle swarm optimisation with a CatBoost model performed best, explaining most of the variation in walking distance, with an average error of about 11 metres. Right stride length and overall walking speed carried the most weight in predictions. The authors present gait-based prediction as highly accurate in this small sample, while stressing that it needs testing in larger groups before it can support clinical decisions.
Catalog record
| CREATOR | Aylin Tanriverdi Eyolcu, Ayşe Doğru, Selim Buyrukoğlu, Sema Savci, Buse Ozcan Kahraman, Mehmet Birhan Yilmaz |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |