Researchers at the Massachusetts Institute of Technology (MIT) have revealed a new pose-mapping technique to remotely evaluate motor functions in patients with cerebral palsy.
Combining both computer vision and machine-learning techniques, the method analyses videos of patients in real time and computes a clinical score of motor function based on patterns of poses that it detects in video frames.
Cerebral palsy affects a person’s ability to move and maintain balance and posture and currently impacts approximately 18 million people worldwide.
For some parents of patients with the condition, going to the doctor can be challenging and stressful, as clinicians need to regularly evaluate the child in person, often taking an hour at a time.
After testing the method on videos of over 1,000 children with cerebral palsy, the researchers found that the method could process each video and assign a clinical score that matched with over 70% accuracy what a clinician had previously determined during an in-person visit.
The remote method can be run on a range of mobile devices so that patients can be evaluated simply from home by taking a video and loading it into the programme to be analysed and assigned a clinical score or level of progress.
MIT researchers are now tailoring the method to evaluate children with metachromatic leukodytrophy, a rare genetic disorder that affects the central and peripheral nervous systems.
Hermano Krebs, principal research scientist at MIT’s Department of Mechanical Engineering, said: “In the future, this might also help us predict how patients would respond to interventions sooner… because we could evaluate them more often, to see if an intervention is having an impact.”
As well as improving care and reducing the overall cost of health care, the method could also “be easily expandable to other disabilities such as stroke or Parkinson’s disease once it is tested in that population using appropriate metrics for adults,” said Alberto Esquenazi, chief medical officer at Moss Rehabilitation Hospital, Philadelphia.