Machine Learning for medical rehabilitation
summary
Describes a case study using deep learning and vision tools—specifically DeeperCut and ArtTrack—to extract human pose and gait from images and use those measurements to predict medical rehabilitation outcomes. Covers building and training the model for gait understanding, adapting a generic model to work with Indian patients, and considerations of trust and accuracy for ML in healthcare.
AI-written summary · about
chapters (9)
- 0:00Start
- 0:47Challenges in Rehabilitation
- 5:21Clinical Protocols
- 8:21Body Estimation
- 12:12Pose Estimation
- 13:35Pose Recognition
- 15:10Gait Recognition
- 17:33Sentiment Analysis
- 24:02Gait Measurement
related talks
58mHealthcare with AI of the Future
25mDeep Learning in Biomedicine: Challenges and Opportunities
47mMachine Learning in Healthcare: Techniques and Applications
28mEnhancing Upper Limb Rehabilitation with Unsupervised Machine Learning Models
20mMachine Learning in Cardiology
18mMedical AI Beyond Prediction: From Normative Learning to Agentic Healthcare AI
24mMachine Learning & Medical Imaging: The Future of Early Cancer Detection
20mDiagnostic Medical application of ML