Sleep movements and respiratory coupling as a biobehavioral metric for early Alzheimer's disease in independently dwelling adults.

INTRODUCTION: Sleep disorder is often the first symptom of age-related cognitive decline associated with Alzheimer's disease (AD) observed in primary care. The relationship between sleep and early AD was examined using a patented sleep mattress designed to record respiration and high frequency movement arousals. A machine learning algorithm was developed to classify sleep features associated with early AD. METHOD: Community-dwelling older adults (N = 95; 62-90 years) were recruited in a 3-h catchment area. Study participants were tested on the mattress device in the home bed for 2 days, wore a wrist actigraph for 7 days, and provided sleep diary and sleep disorder self-reports during the 1-week study period. Neurocognitive testing was completed in the home within 30-days of the sleep study. Participant performance on executive and memory tasks, health history and demographics were reviewed by a geriatric clinical team yielding Normal Cognition (n = 45) and amnestic MCI-Consensus (n = 33) groups. A diagnosed MCI group (n = 17) was recruited from a hospital memory clinic following diagnostic series of neuroimaging biomarker assessment and cognitive criteria for AD. RESULTS: In cohort analyses, sleep fragmentation and wake after sleep onset duration predicted poorer executive function, particularly memory performance. Group analyses showed increased sleep fragmentation and total sleep time in the diagnosed MCI group compared to the Normal Cognition group. Machine learning algorithm showed that the time latency between movement arousals and coupled respiratory upregulation could be used as a classifier of diagnosed MCI vs. Normal Cognition cases. ROC diagnostics identified MCI with 87% sensitivity; 89% specificity; and 88% positive predictive value. DISCUSSION: AD sleep phenotype was detected with a novel sleep biometric, time latency, associated with the tight gap between sleep movements and respiratory coupling, which is proposed as a corollary of sleep quality/loss that affects the autonomic regulation of respiration during sleep. Diagnosed MCI was associated with sleep fragmentation and arousal intrusion.

Sleep Signal Analysis for Early Detection of Alzheimer's Disease and Related Dementia (ADRD).

OBJECTIVE: Alzheimer's Disease and Related Dementia (ADRD) is growing at alarming rates, putting research and development of diagnostic methods at the forefront of the biomedical research community. Sleep disorder has been proposed as an early sign of Mild Cognitive Impairment (MCI) in Alzheimer's disease. Although several clinical studies have been conducted to assess sleep and association with early MCI, reliable and efficient algorithms to detect MCI in home-based sleep studies are needed in order to address both healthcare costs and patient discomfort in hospital/lab-based sleep studies. METHODS: In this paper, an innovative MCI detection method is proposed using an overnight recording of movements associated with sleep combined with advanced signal processing and artificial intelligence. A new diagnostic parameter is introduced which is extracted from the correlation between high frequency, sleep-related movements and respiratory changes during sleep. The newly defined parameter, Time-Lag (TL), is proposed as a distinguishing criterion that indicates movement stimulation of brainstem respiratory regulation that may modulate hypoxemia risk during sleep and serve as an effective parameter for early detection of MCI in ADRD. By implementing Neural Networks (NN) and Kernel algorithms with choosing TL as the principle component in MCI detection, high sensitivity (86.75% for NN and 65% for Kernel method), specificity (89.25% and 100%), and accuracy (88% and 82.5%) have been achieved.