Researchers have developed a multi-output regression model, NODE, to predict multiple clinical outcomes for older adults recovering from lower-limb fractures or hip replacements. The study utilized the MAISON-LLF dataset, incorporating multimodal sensor data and clinical assessments over eight weeks. By jointly predicting outcomes such as social isolation, functional recovery scores, and mobility tests, the model achieved a Mean Squared Error of 3.96 and a Mean Absolute Error of 1.02, outperforming single-output models. Feature analysis using SHAP highlighted the importance of multimodal sensors in accurately estimating patient recovery trajectories. AI
IMPACT This research demonstrates the potential for AI to improve personalized care and quality of life for older adults by providing a more holistic assessment of recovery.
RANK_REASON Academic paper detailing a novel machine learning model for clinical outcome prediction. [lever_c_demoted from research: ic=1 ai=1.0]
- 30-Second Chair Stand Test Predicts Countermovement Jump Performance in Young Adults
- MAISON-LLF
- NODE
- Oxford Hip Score
- Oxford Knee Score
- Pratik K. Mishra
- Shap
- Social Isolation Scale
- Timed Up and Go test
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
