// AI news · 2026-11-14 · Nature
Hierarchical ML for Functional Prognosis in Femoral Fractures
A hierarchical machine learning model was developed to predict functional outcomes in proximal femoral fractures using data from the Japan Rehabilitation Database.
Published 2026-11-14 08:00 (Beijing time)Source NatureAuto-summarised, fact-checked against source
01Summary
The nine-class prognosis problem was decomposed into sequential classification tasks, achieving 0.345 accuracy in internal validation. SHAP analysis was used for interpretability assessment. The approach supports individualized rehabilitation planning and improves preoperative evaluation and early postoperative recovery.
Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.
02Key points
- Model predicts functional outcomes in proximal femoral fractures using hierarchical classification.
- Achieved 0.345 accuracy on internal validation cohort from 2,959 patients.
- SHAP analysis was used to evaluate model interpretability.
- Supports individualized rehabilitation planning and early recovery decisions.
03Source
Nature · published 2026-11-14 08:00 Beijing time
05Related news
- Same source · HGS-BioAbductor: Explainable Survival Modeling and Hypothesis Abduction2026-11-14 · Nature
- Same source · Deep learning and multitask learning no better than tree ensembles for student outcome prediction2026-11-14 · Nature
- Same topic · CerS-Path: Self-supervised Diagnostic System for Cervical Pathology2026-11-14 · Nature
- Same topic · Microsoft posts AI question during service outage2026-11-14 · IT之家
- Same day · AI-Generated Park Layouts Respond to Urban Constraints2026-11-14 · Nature
From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-14 · Archive by date · All AI news · Today