Development and validation of machine learning models for predicting rehabilitation non-response after knee arthroplasty
Niclas J. Hubel, Ferdinand Prüfer, Walter Bily, David Schneider, Bernhard Holzner, Michael J. Fischer, Vincent Grote · 2026
Read Development and validation of machine learning models for predicting rehabilitation non-response after knee arthroplasty by Niclas J. Hubel, Ferdinand Prüfer, Walter Bily, David Schneider, Bernhard Holzner, Michael J. Fischer, Vincent Grote (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-13630954.txt.
Description
Niclas Hubel and co-authors built machine learning models in 2026 to predict which knee replacement patients will gain little from rehabilitation. Rehab after this surgery helps most patients, but some leave without a gain large enough to matter in daily life.
The team used registry data from four Austrian centres, covering more than 5,400 patients from 2018 to 2024. Models predicted poor response fairly well across three outcomes: quality of life, a knee specific score, and a timed standing and walking test. How patients scored on arrival was the strongest predictor, with better starters less likely to show a large gain. The authors flag this ceiling effect and call for sharper outcome definitions.
Catalog record
| CREATOR | Niclas J. Hubel, Ferdinand Prüfer, Walter Bily, David Schneider, Bernhard Holzner, Michael J. Fischer, Vincent Grote |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |