RESUMO
The present study proposes a classification model for the differential diagnosis of primary insomnia (PI) and delayed sleep phase disorder (DSPD), applying machine learning methods to circadian parameters obtained from ambulatory circadian monitoring (ACM). Nineteen healthy controls and 242 patients (PI = 184; DSPD = 58) were selected for a retrospective and non-interventional study from an anonymized Circadian Health Database (https://kronowizard.um.es/). ACM records wrist temperature (T), motor activity (A), body position (P), and environmental light exposure (L) rhythms during a whole week. Sleep was inferred from the integrated variable TAP (from temperature, activity, and position). Non-parametric analyses of TAP and estimated sleep yielded indexes of interdaily stability (IS), intradaily variability (IV), relative amplitude (RA), and a global circadian function index (CFI). Mid-sleep and mid-wake times were estimated from the central time of TAP-L5 (five consecutive hours of lowest values) and TAP-M10 (10 consecutive hours of maximum values), respectively. The most discriminative parameters, determined by ANOVA, Chi-squared, and information gain criteria analysis, were employed to build a decision tree, using machine learning. This model differentiated between healthy controls, DSPD and three insomnia subgroups (compatible with onset, maintenance and mild insomnia), with accuracy, sensitivity, and AUC >85%. In conclusion, circadian parameters can be reliably and objectively used to discriminate and characterize different sleep and circadian disorders, such as DSPD and OI, which are commonly confounded, and between different subtypes of PI. Our findings highlight the importance of considering circadian rhythm assessment in sleep medicine.
RESUMO
An integrated variable based on the combination of wrist Temperature, motor Activity and body Position (TAP) was previously developed at our laboratory to evaluate the functioning of the circadian system and sleep-wake rhythm under ambulatory conditions. However, the reliability of TAP needed to be validated with polysomnography (PSG). 22 subjects suffering from sleep disorders were monitored for one night with a temperature sensor (iButton), an actimeter (HOBO) and exploratory PSG. Mean waveforms, sensitivity (SE), specificity (SP), agreement rates (AR) and comparisons between TAP and sleep stages were studied. The TAP variable was optimized for SE, SP and AR with respect to each individual variable (SE: 92%; SP: 78%; AR: 86%). These results improved upon estimates previously published for actigraphy. Furthermore, TAP values tended to decrease as sleep depth increased, reaching the lowest point at phase 3. Finally, TAP estimates for sleep latency (SL: 37±9 min), total sleep time (TST: 367±13 min), sleep efficiency (SE: 86.8±1.9%) and number of awakenings (NA>5 min: 3.3±.4) were not significantly different from those obtained with PSG (SL: 29±4 min; SE: 89.9±1.8%; NA>5 min: 2.3±.4), despite the heterogeneity of the sleep pathologies monitored. The TAP variable is a novel measurement for evaluating circadian system status and sleep-wake rhythms with a level of reliability better to that of actigraphy. Furthermore, it allows the evaluation of a patient's sleep-wake rhythm in his/her normal home environment, and at a much lower cost than PSG. Future studies in specific pathologies would verify the relevance of TAP in those conditions.
