Ambulatory Detection of Isolated Rapid-Eye-Movement Sleep Behavior Disorder Combining Actigraphy and Questionnaire

Strengths, weaknesses, opportunities, and threats of using AI-enabled technology in sleep medicine: a commentary

Over the past few years, artificial intelligence (AI) has emerged as a powerful tool used to efficiently automate several tasks across multiple domains. Sleep medicine is perfectly positioned to leverage this tool due to the wealth of physiological signals obtained through sleep studies or sleep tracking devices and abundance of accessible clinical data through electronic medical records. However, caution must be applied when utilizing AI, due to intrinsic challenges associated with novel technology. The Artificial Intelligence in Sleep Medicine Committee of the American Academy of Sleep Medicine reviews advancements in AI within the sleep medicine field. In this article, the Artificial Intelligence in Sleep Medicine committee members provide a commentary on the scope of AI technology in sleep medicine. The commentary identifies 3 pivotal areas in sleep medicine that can benefit from AI technologies: clinical care, lifestyle management, and population health management. This article provides a detailed analysis of the strengths, weaknesses, opportunities, and threats associated with using AI-enabled technologies in each pivotal area. Finally, the article broadly reviews barriers and challenges associated with using AI-enabled technologies and offers possible solutions.

CITATION

Bandyopadhyay A, Oks M, Sun H, et al. Strengths, weaknesses, opportunities, and threats of using AI-enabled technology in sleep medicine: a commentary. J Clin Sleep Med. 2024;20(7):1183-1191.

Too little or too much nocturnal movements in Parkinson's disease: A practical guide to managing the unseen

Nocturnal and sleep-related motor disorders in people with Parkinson's disease (PD) have a wide spectrum of manifestations and present a complex clinical picture. Problems can arise due to impaired movement ability (hypokinesias), e.g. nocturnal hypokinesia or early-morning akinesia, or to excessive movement (hyperkinesias), e.g. end-of-the-day dyskinesia, parasomnias, periodic limb movement during sleep and restless legs syndrome. These disorders can have a significant negative impact on the sleep, daytime functional ability, and overall quality of life of individuals with PD and their carers. The debilitating motor issues are often accompanied by a combination of non-motor symptoms, including pain and cramping, which add to the overall burden. Importantly, nocturnal motor disorders encompass a broader timeline than just the period of sleep, often starting in the evening, as well as occurring throughout the night and on awakening, and are not just limited to problems of insomnia or sleep fragmentation. Diagnosis can be challenging as, in many cases, the 'gold standard' assessment method is video polysomnography, which may not be available in all settings. Various validated questionnaires are available to support evaluation, and alternative approaches, using wearable sensors and digital technology, are now being developed to facilitate early diagnosis and monitoring. This review sets out the parameters of what can be considered normal nocturnal movement and describes the clinical manifestations, usual clinical or objective assessment methods, and evidence for optimal management strategies for the common nocturnal motor disorders that neurologists will encounter in people with PD in their clinical practice.

Impaired 24-h activity patterns are associated with an increased risk of Alzheimer's disease, Parkinson's disease, and cognitive decline

BACKGROUND

Sleep-wake regulating circuits are affected during prodromal stages in the pathological progression of both Alzheimer's disease (AD) and Parkinson's disease (PD), and this disturbance can be measured passively using wearable devices. Our objective was to determine whether accelerometer-based measures of 24-h activity are associated with subsequent development of AD, PD, and cognitive decline.

METHODS

This study obtained UK Biobank data from 82,829 individuals with wrist-worn accelerometer data aged 40 to 79 years with a mean (± SD) follow-up of 6.8 (± 0.9) years. Outcomes were accelerometer-derived measures of 24-h activity (derived by cosinor, nonparametric, and functional principal component methods), incident AD and PD diagnosis (obtained through hospitalization or primary care records), and prospective longitudinal cognitive testing.

RESULTS

One hundred eighty-seven individuals progressed to AD and 265 to PD. Interdaily stability (a measure of regularity, hazard ratio [HR] per SD increase 1.25, 95% confidence interval [CI] 1.05-1.48), diurnal amplitude (HR 0.79, CI 0.65-0.96), mesor (mean activity; HR 0.77, CI 0.59-0.998), and activity during most active 10 h (HR 0.75, CI 0.61-0.94), were associated with risk of AD. Diurnal amplitude (HR 0.28, CI 0.23-0.34), mesor (HR 0.13, CI 0.10-0.16), activity during least active 5 h (HR 0.24, CI 0.08-0.69), and activity during most active 10 h (HR 0.20, CI 0.16-0.25) were associated with risk of PD. Several measures were additionally predictive of longitudinal cognitive test performance.

CONCLUSIONS

In this community-based longitudinal study, accelerometer-derived metrics were associated with elevated risk of AD, PD, and accelerated cognitive decline. These findings suggest 24-h rhythm integrity, as measured by affordable, non-invasive wearable devices, may serve as a scalable early marker of neurodegenerative disease.

Performance of the Dreem 2 EEG headband, relative to polysomnography, for assessing sleep in Parkinson's disease

GOAL AND AIMS

To pilot the feasibility and evaluate the performance of an EEG wearable for measuring sleep in individuals with Parkinson's disease.

FOCUS TECHNOLOGY

Dreem Headband, Version 2.

REFERENCE TECHNOLOGY

Polysomnography.

SAMPLE

Ten individuals with Parkinson's disease.

DESIGN

Individuals wore Dreem Headband during a single night of polysomnography.

CORE ANALYTICS

Comparison of summary metrics, bias, and epoch-by-epoch analysis.

ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES

Correlation of summary metrics with demographic and Parkinson's disease characteristics.

CORE OUTCOMES

Summary statistics showed Dreem Headband overestimated several sleep metrics, including total sleep, efficiency, deep sleep, and rapid eye movement sleep, with an exception in light sleep. Epoch-by-epoch analysis showed greater specificity than sensitivity, with adequate accuracy across sleep stages (0.55-0.82).

IMPORTANT SUPPLEMENTAL OUTCOMES

Greater Parkinson's disease duration and rapid eye movement behavior were associated with more wakefulness, and worse Parkinson's disease motor symptoms were associated with less deep sleep.

CORE CONCLUSION

The Dreem Headband performs similarly in Parkinson's disease as it did in non-Parkinson's disease samples and shows promise for improving access to sleep assessment in people with Parkinson's disease.

Clinical neurophysiology of REM parasomnias: Diagnostic aspects and insights into pathophysiology

Parasomnias are due to a transient unstable state dissociation during entry into sleep, within sleep, or during arousal from sleep, and manifest with abnormal sleep related behaviors, perceptions, emotions, dreams, and autonomic nervous system activity. Rapid eye movement (REM) parasomnias include REM sleep behavior disorder (RBD), isolated recurrent sleep paralysis and nightmare disorder. Neurophysiology is key for diagnosing these disorders and provides insights into their pathophysiology. RBD is very well characterized from a neurophysiological point of view, also thank to the fact that polysomnography is needed for the diagnosis. Diagnostic criteria are provided by the American Academy of Sleep Medicine and video-polysomnography guidelines for the diagnosis by the International REM Sleep Behavior Disorder Study Group. Differences between the two sets of criteria are presented and discussed. Availability of polysomnography in RBD provides data on sleep electroencephalography (EEG), electrooculography (EOG) and electromyography (EMG). Sleep EEG in RBD shows e.g. changes in delta and theta power, in sleep spindles and K complexes. EMG during REM sleep is essential for RBD diagnosis and is an important neurodegeneration biomarker. RBD patients present alterations also in wake EEG, autonomic function, evoked potentials, and transcranial magnetic stimulation. Clinical neurophysiological data on recurrent isolated sleep paralysis and nightmare disorder are scant. The few available data provide insights into the pathophysiology of these disorders, demonstrating a state dissociation in recurrent isolated sleep paralysis and suggesting alterations in sleep macro- and microstructure as well as autonomic changes in nightmare disorder.

REM Sleep Behavior Disorder and Its Possible Prodromes in General Population: Prevalence, Polysomnography Findings, and Associated Factors

BACKGROUND AND OBJECTIVES

To evaluate the prevalence of REM sleep behavior disorder (RBD) and its possible prodromal conditions, isolated dream enactment behavior (DEB) and isolated REM without atonia (RWA), in a general population sample, and the factors associated with diagnosis and symptom frequency.

METHODS

From a population-based prospective cohort in Korea, 1,075 participants (age 60.1 ± 7.0 years; range 50-80 years; men 53.7%) completed the RBD screening questionnaire (RBDSQ), a structured telephone interview for the presence and characteristics of repeated DEB, and home polysomnography (PSG). RWA was measured on submentalis EMG, including 30-second epoch-based tonic and phasic activity as well as 3-second mini-epoch-based phasic and any EMG activities. Based on the presence of repeated DEB and any EMG activity of ≥22.3%, we categorized the participants into no RBD, isolated RWA, isolated DEB, and RBD groups.

RESULTS

RBD was diagnosed in 20 participants, isolated RWA in 133 participants, and isolated DEB in 48 participants. Sex and DEB frequency-adjusted prevalence of RBD was 1.4% (95% CI 1.0%-1.8%), isolated RWA was 12.5% (95% CI 11.3%-13.6%), and isolated DEB was 3.4% (95% CI 2.7%-4.1%). Total RBDSQ score was higher in the RBD and isolated DEB groups than in the isolated RWA and no RBD group (median 5 [interquartile range (IQR) 4-6] for RBD, median 4 [IQR 3-6] for isolated DEB, median 2 [IQR 1-3] for isolated RWA, and median 2 [IQR 1-4] for no RBD groups, p < 0.001). RBDSQ score of ≥5 had good specificity but poor positive predictive value (PPV) for RBD (specificity 84.1% and PPV 7.7%) and its prodromal conditions (specificity 85.2% and PPV 29.1%). Among the RWA parameters, any EMG activity showed the best association with the RBD and its possible prodromes (area under the curve, 0.917). Three-second mini-epoch-based EMG activity and phasic EMG activity were correlated with the frequency of DEB (standardized Jonckheere-Terpstra statistic [std. J-T static] for trend = 0.488, p < 0.001, and std. J-T static = 3.265, p = 0.001, respectively).

DISCUSSION

This study provides prevalence estimates of RBD and its possible prodromal conditions based on a structured telephone interview and RWA measurement on PSG from the general population.

REM Behavior Disorder: Implications for PD Therapeutics

PURPOSE

Rapid eye movement (REM) sleep behavior disorder (RBD) is a parasomnia that occurs during REM sleep, characterized by REM sleep without atonia (RSWA) and dream enactment behavior (DEB). RBD is associated with several diseases and medications but most notably is a prodromal feature of synucleinopathies, including Parkinson's disease (PD). This article reviews RBD, its treatments, and implications for PD therapeutics.

RECENT FINDINGS

Recent research recognizes RBD as a prodromal marker of PD, resulting in expansion of basic science and clinical investigations of RBD. Current basic science research investigates the pathophysiology of RBD and explores animal models to allow therapeutic development. Clinical research has focused on natural history observation, as well as potential RBD treatments and their impact on sleep and phenoconversion to neurodegenerative disease. RBD serves as a fresh access point to develop both neuroprotective and symptomatic therapies in PD. These types of investigations are novel and will benefit from the more established basic science infrastructure to develop new interventions.

Monitoring sleep stages with a soft electrode array: Comparison against vPSG and home-based detection of REM sleep without atonia

Sleep disorders are symptomatic hallmarks of a variety of medical conditions. Accurately identifying the specific stage in which these disorders occur is particularly important for the correct diagnosis of non-rapid eye movement and rapid eye movement parasomnias. In-lab polysomnography suffers from limited availability and does not reflect habitual sleep conditions, which is especially important in older adults and those with neurodegenerative diseases. We aimed to explore the feasibility and validity of a new wearable system for accurately measuring sleep at home. The system core technology is soft, printed dry electrode arrays and a miniature data acquisition unit with a cloud-based data storage for offline analysis. The positions of the electrodes allow manual scoring following the American Association of Sleep Medicine guidelines. Fifty participants (21 healthy subjects, mean age 56.6 ± 8.4 years; and 29 patients with Parkinson's disease, 65.4 ± 7.6 years) underwent a polysomnography evaluation with parallel recording with the wearable system. Total agreement between the two systems reached Cohen's kappa (k) of 0.688 with agreement in each stage of: wake k = 0.701; N1 = 0.224; N2 = 0.584; N3 = 0.410; and rapid eye movement = 0.723. Moreover, the system reliably detected rapid eye movement sleep without atonia with a sensitivity of 85.7%. Additionally, a comparison between sleep as measured in the sleep lab with data collected from a night at home showed significantly lower wake after sleep onset at home. The results demonstrate that the system is valid, accurate and allows for the exploration of sleep at home. This new system offers an opportunity to help detect sleep disorders on a larger scale than possible today, fostering better care.

Detection and Characterization of Walking Bouts Using a Single Wrist-Worn Accelerometer in Free-living Conditions

Detection and characterization of abnormalities of movement are important to develop a method for detecting early signs of Parkinson's disease (PD). Most of the current research in detection of characteristic reduction of movements due to PD, known as parkinsonism, requires using a set of invasive sensors in a clinical or controlled environment. Actigraphy has been widely used in medical research as a non-invasive data acquisition method in free-living conditions for long periods of time. The proposed algorithm uses triaxial accelerometer data obtained through actigraphy to detect walking bouts at least 10 seconds long and characterize them using cadence and arm swing. Accurate detection of walking periods is the first step toward the characterization of movement based on gait abnormalities. The algorithm was based on a Walking Score (WS) derived using the value of the auto-correlation function (ACF) for the Resultant acceleration vector. The algorithm achieved a precision of 0.90, recall of 0.77, and F1 score of 0.83 compared to the expert scoring for walking bout detection. We additionally described a method to measure arm swing amplitude.