News
Video
Author(s):
The associate professor of neurology at the Icahn School of Medicine at Mount Sinai explained how his team validated an iRBD actigraphy classifier across new devices and datasets to enhance early, scalable screening for neurodegenerative disease. [WATCH TIME: 5 minutes]
WATCH TIME: 5 minutes
"We know isolated RBD is a precursor to neurodegenerative diseases, but most cases remain undiagnosed for years. This classifier proves we can use home devices to identify high-risk individuals earlier and more affordably."
Rapid eye movement (REM) sleep behavior disorder (RBD) is characterized by enactment of motor behaviors correlating with vivid dreams in REM sleep and demonstrated loss of the normal REM atonia. This disorder has been increasingly linked to other conditions, such as a-synuclein-related neurodegenerative disease, including Parkinson disease (PD), dementia with Lewy bodies (DLB), and multiple system atrophy. A 2013 study found that 80% of patients with the isolated form of RBD (iRBD) will progress to clinically defined PD or DLB within 15 years of first diagnosis. These data, along with other studies, have raised the awareness and importance of identifying patients at risk for iRBD.1
Nocturnal wrist actigraphy has shown promise in detecting iRBD by measuring sleep-related motor activity; however, it relies on diary-defined sleep periods, which are not always available. At the 2025 SLEEP Annual Meeting, held June 8-11, in Seattle, Washington. Emmanuel During, MD, an associate professor of neurology at the Icahn School of Medicine at Mount Sinai, presented a talk on the validation of a novel actigraphy-based classifier developed to detect iRBD using wearable devices. Originally trained on data from a high-resolution actigraph, the classifier was successfully tested on a large external dataset from Hong Kong using a different, lower resolution actigraph.
During, who works both in the Department of Neurology and the Department of Medicine at Mount Sinai, sat down with NeurologyLive® during the meeting to discuss the talk and study findings in greater detail. In the interview, During spoke on the research supporting the classifier’s potential scalability across devices and populations, marking a major step forward in accessible, at-home iRBD screening. Above all, he noted how this breakthrough may impact early identification of synucleinopathies such as PD and DLB.
Click here for more SLEEP 2025 coverage.
Keep your finger on the pulse of neurology—subscribe to NeurologyLive for expert interviews, new data, and breakthrough treatment updates.