Remote Pose-Mapping Technique Revolutionizes Cerebral Palsy Patient Evaluation
Originally Published 2 years ago — by MIT News
MIT engineers have developed a method that uses computer vision and machine learning to remotely evaluate the motor function of patients, specifically targeting those with cerebral palsy. By analyzing videos of patients in real-time and detecting patterns of poses, the method can assign a clinical score of motor function. The researchers tested the method on over 1,000 children with cerebral palsy and found that it matched with over 70% accuracy what a clinician had determined during an in-person visit. The team envisions that patients can use their mobile devices to record videos of themselves at home, which can then be analyzed and sent to a doctor for review. The method is also being adapted to evaluate other neurological disorders.