Diagnosing REM sleep behavior disorder based on history alone can be challenging for sleep specialists, particularly since video polysomnography is not always accepted by patients or the dream-enacting behaviors required for diagnosis may not manifest during a single night of sleep testing. Researchers have now identified a two-step convenient screening method to detect REM sleep behavior disorder at home—using technology already present in most wearable sleep and fitness trackers.
In a study conducted at Stanford Sleep Center from April to December 2021 and published in Movement Disorders, over 80 participants were monitored who wore a wearable device on their wrist for at least 14 nights and completed both a questionnaire and a sleep diary reporting any abnormal behaviors during sleep. A machine learning classifier using high-frequency (1-second resolution) actigraphy and a short patient survey for detecting idiopathic REM sleep behavior disorder with high accuracy and precision. Video-based studies show that in REM sleep behavior disorder, a majority of movements are simple, nonpurposeful twitches more prominent in the arms, so the researchers designed two actigraphy features with higher discriminative value, long immobile bouts and twitch activity.
Because REM sleep behavior disorder is associated with an underlying α-synucleinopathy, more commonly Parkinson’s disease or dementia with Lewy bodies, a convenient screening method can mean additional lead time for patients to prepare or even trial therapies.
The findings showed that sleep disturbances related to Parkinson’s disease are detectable using wearable wrist devices such as Apple Watch or Fitbit. This new screening method could diagnose a very common subtype of Parkinson’s disease years before the conventional methods of diagnosis, which require a clinical examination by an experienced neurologist, according to a press release by Mount Sinai Health System. At-risk populations could receive care and counseling sooner and receive neuroprotective therapies before the neurodegenerative process has caused irreversible brain damage.
“We need reliable and scalable screening methods for detecting Parkinson’s in order to develop effective therapies and select candidates to receive effective therapies,” says Emmanuel During, MD, associate professor of neurology and medicine at the Icahn School of Medicine at Mount Sinai, in a press release. “There is now an opportunity for the academic, pharma, and technology sectors to collaboratively partner to develop and apply this prevention screening method in the elderly population at risk for Parkinson’s disease.”
In the study, researchers analyzed home actigraphy data to determine movement during sleep and reviewed the nine-item questionnaire from the cohort, which included over 40 patients with isolated REM sleep behavior disorder, over 20 patients with other sleep disorders, and over 20 patients with no sleep disorders as controls.
The questionnaire asked participants to report experiencing any abnormal movements during sleep or common early symptoms associated with Parkinson’s disease, such as loss of smell and dizziness. Using actigraphy data from the wearables, the researchers developed a framework for classification of movements and tested the approach in a machine-learning model.
Likewise, they also developed an approach from the questionnaire data to test on a machine-learning model. Once both actigraphy and questionnaire models were developed, the researchers created a two-dimensional prediction model for isolated REM sleep behavior disorder.
The actigraphy classifier analyzing movements during sleep could detect isolated REM sleep behavior disorder with 92.9% accuracy. By comparison, all questionnaires combined achieved 91.7% accuracy, exceeding the performance of the Innsbruck RBD Inventory questionnaire alone (86.9% accuracy).
Concordant predictions between actigraphy and questionnaires reached a specificity and precision of 100% with 88.1% sensitivity and outperformed any combination of actigraphy and a single question on the questionnaire about early Parkinson’s disease symptoms.
A two-step approach using questionnaire first, followed by ambulatory actigraphy for 10 days in those who screen positive, could select individuals at highest risk of idiopathic REM sleep behavior disorder and thereby result in higher positive predictive value (100% in this small sample of 84 subjects), before confirmatory video polysomnography.