A team of researchers led by Mount Sinai has improved an artificial intelligence (AI)-based algorithm to analyze video recordings of clinical sleep tests, improving the accurate diagnosis of a common sleep disorder affecting more than 80 million people. people in the world. The results of the study were published in the journal Annals of Neurology on January 9.
REM sleep behavior disorder (RBD) is a sleep condition that causes abnormal movements, or physical acts outside of dreams, during the rapid eye movement (REM) phase. RBD that occurs in otherwise healthy adults is called “isolated” RBD. It affects more than a million people in the United States and, in almost all cases, is an early sign of Parkinson’s disease or dementia.
RBD is extremely difficult to diagnose because its symptoms can go unnoticed or be confused with other illnesses. A definitive diagnosis requires that a sleep study, known as a video polysomnogram, be performed by a healthcare professional in a facility with sleep monitoring technology. The data is also subjective and can be difficult to interpret universally based on multiple and complex variables, including sleep stages and amount of muscle activity. Although video data is routinely recorded during a sleep test, it is rarely reviewed and is often deleted after the test is interpreted.
Limited previous work in this area suggested that research-grade 3D cameras might be needed to detect movement during sleep because sheets or blankets would cover the activity. This study is the first to describe the development of an automated machine learning method that analyzes video recordings routinely collected with a 2D camera during nighttime sleep testing. This method also defines additional “classifiers” or characteristics of movements, resulting in an RBD detection accuracy rate of nearly 92%.
This automated approach could be integrated into the clinical workflow when interpreting sleep tests to improve and facilitate diagnosis and avoid missed diagnoses. This method could also be used to inform treatment decisions based on the severity of movements displayed during sleep tests and ultimately help doctors personalize care plans for each patient. »
-Emmanuel Durant, MD, Corresponding author, Associate Professor of Neurology (Movement Disorders) and Medicine (Pulmonary, Critical Care and Sleep Medicine), at the Icahn School of Medicine at Mount Sinai
The Mount Sinai team replicated and expanded a proposal for automated machine learning analysis of movements during sleep studies, created by researchers at the Medical University of Innsbruck in Austria. This approach uses computer vision, a field of artificial intelligence that allows computers to analyze and understand visual data, including images and videos. Building on this framework, Mount Sinai experts used 2D cameras, commonly found in clinical sleep laboratories, to monitor patients’ sleep during the night. The dataset included analysis of recordings at a sleep center from approximately 80 RBD patients and a control group of approximately 90 patients without RBD who suffered from either another sleep disorder or no sleep disorder. sleep disturbance. An automated algorithm that calculated the movement of pixels between consecutive frames in a video was able to detect movement during REM sleep. Experts examined the data to extract the rate, ratio, magnitude and speed of movements, as well as the stillness ratio. They analyzed these five characteristics of short movements to achieve the highest accuracy researchers have ever achieved, 92%.
Researchers from the Swiss Federal Institute of Technology Lausanne (École Polytechnique Fédérale de Lausanne) in Lausanne, Switzerland, contributed to the study by sharing their expertise in computer vision.
