AUTHOR=Rodriguez-Morilla Beatriz , Estivill Eduard , Estivill-Domènech Carla , Albares Javier , Segarra Francisco , Correa Angel , Campos Manuel , Rol Maria Angeles , Madrid Juan Antonio 

TITLE=Application of Machine Learning Methods to Ambulatory Circadian Monitoring (ACM) for Discriminating Sleep and Circadian Disorders

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 13 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2019.01318

DOI=10.3389/fnins.2019.01318

ISSN=1662-453X

ABSTRACT=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).
The wrist temperature (T), motor activity (A), body position (P) and exposure to environmental light (L) rhythms of 19 healthy controls and 242 patients (PI = 184; DSPD = 58) were assessed during a 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 (5 consecutive hours of lowest values) and TAP-M10 (10 consecutive hours of maximum values), respectively.
The most discriminative parameters as determined by ANOVA, Chi-squared and Information Gain criteria analysis were employed to build a decision tree, using machine learning. This model differentiated between DSPD, onset insomnia, maintenance insomnia, mild insomnia and healthy controls, with accuracy, sensitivity and AUC higher than 85%. 
In conclusion, circadian parameters can be reliably and objectively used to discriminate and characterize different sleep and circadian disorders, such as DSPD and onset insomnia (OI), which are commonly confounded, and between different subtypes of PI. Our findings highlight the importance of considering circadian rhythm assessment in sleep medicine.