Individuals with MS well served by monitoring with ML
Researchers have innovated a way to diagnose and monitor multiple sclerosis in middle-aged adults by using treadmills and AI-aided gait analysis.
Noting that MS now affects more people between 50 and 60 than any other age group, the team suggests their technique can help personalize therapy regimens by predicting sudden worsening of symptoms.
Senior author Richard Sowers, PhD, and colleagues at the University of Illinois Urbana-Champaign describe their work in IEEE Transactions on Biomedical Engineering.
The team recruited 20 persons with MS and 20 volunteers matched for age, weight, height and sex, having each walk at his or her own pace on a treadmill. The equipment was outfitted with video-based tools for capturing gait patterns, and the subjects walked both undistracted and while carrying on a conversation.
Comparing the MS identification performance of a conventional analysis formula with that of a machine learning model, they found the latter better, recording that it achieved 94% accuracy in one test and 80% in another.
“Given that we have more older adults with MS than younger adults, and the expected continual shift of the peak prevalence of MS into older age groups, the prediction of a tipping point for older persons with MS advancing into sudden worsening may provide improved personalized care,” Sowers et al. comment in their discussion section. “Early detection of these inflection points in older persons with MS may lead to concise and effective detection strategies and in turn benefit both patients as well as clinicians to curtail MS therapy expenses.”
Co-author Manuel Hernandez, PhD, tells the university’s news division that machine learning techniques “seem to work particularly well at spotting complex hidden changes in performance. We hypothesized that these analysis techniques might also be useful in predicting sudden gait changes in persons with MS.”
The study is study is available in full for free (PDF).
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.