New AI Tool Helps Assess Severity of Parkinson’s Disease Symptoms
Researchers at the University of Rochester have developed an artificial intelligence (AI) tool that allows people with Parkinson’s disease to remotely assess the severity of their symptoms within minutes. The tool involves users tapping their fingers 10 times in front of a webcam, and the AI model assesses their motor performance on a scale of 0-4. While expert neurologists performed slightly better than the AI model, it outperformed primary care physicians with UPDRS certification.
Doctors typically assess movement disorders and rate the severity using guidelines such as the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). The AI model utilizes the MDS-UPDRS guidelines to provide a rapid assessment, generating computational metrics such as speed, amplitude, frequency, and period. These metrics are interpretable, standardized, repeatable, and consistent with medical guidelines.
In a study with 250 participants with Parkinson’s disease, the AI system’s ratings were compared to those by neurologists and primary care physicians. While the neurologists performed slightly better, the AI model outperformed the primary care physicians. This AI-based tool has significant implications for patients who have difficulty accessing neurologists, getting appointments, or traveling to hospitals, as it can be used outside of the clinic to improve health equity and access.
The research team led by Md. Saiful Islam, a Google PhD fellow, believes that this method can be applied to other motor tasks, allowing for the evaluation of other movement disorders such as ataxia and Huntington’s disease. However, they caution that the AI tool reflects an emerging technology and should not be considered as a definitive measure of the presence or severity of Parkinson’s disease without a physician’s input.
This breakthrough AI tool has the potential to greatly improve the lives of Parkinson’s disease patients by providing a quick and accessible way to assess symptom severity. It is an example of how AI is being integrated into healthcare to serve people outside of the clinic and address issues of health equity and access.
IntelliPrompt curated this article: Read the full story at the original source by clicking here