Automated Analysis of 2D Camera Recordings Improves Detection of Isolated REM Sleep Behavior Disorder

WEDNESDAY, Jan. 15, 2025 (HealthDay News) — Automated analysis of two-dimensional (2D) camera recordings can improve performance for detecting isolated rapid eye movement (REM) sleep behavior disorder (iRBD), according to a study published online Jan. 9 in the Annals of Neurology.

Mohamed Abdelfattah, from École Polytechnique Fédérale de Lausanne in Switzerland, and colleagues evaluated the effectiveness of automated analysis of movements recorded on a 2D conventional camera to detect iRBD. The analysis included 172 video-polysomnogram recordings from a clinical sleep center (81 patients with iRBD and 91 non-RBD healthy controls [63 with a range of other sleep disorders and 28 healthy sleepers]).

The researchers found that patients with iRBD showed a higher number of shorter movements and immobility periods. Accuracies for detecting iRBD ranged from 84.9 percent (with two features) to 87.2 percent (with five features). The highest accuracy was seen by combining all five features but only analyzing short (0.1- to 2-second duration) movements (91.9 percent). Seven of the 11 patients with iRBD without noticeable movements during video-polysomnogram were correctly identified.

“This approach could be implemented in clinical sleep laboratories to facilitate and improve the diagnosis of iRBD,” the authors write. “Coupled with automated detection of REM sleep, it should also be tested in the home environment using conventional infrared cameras to detect and/or monitor RBD.”

Abstract/Full Text