Application of Machine Learning Methods to Ambulatory Circadian Monitoring (ACM) for Discriminating Sleep and Circadian Disorders
Metadatos
Afficher la notice complèteEditorial
Frontiers Media
Materia
Circadian rhythms Wrist temperature Light exposure Delayed sleep phase Decision tree Digital health
Date
2019-12-10Referencia bibliográfica
Rodriguez-Morilla B, Estivill E, Estivill-Domènech C, Albares J, Segarra F, Correa A, Campos M, Rol MA and Madrid JA (2019) Application of Machine Learning Methods to Ambulatory Circadian Monitoring (ACM) for Discriminating Sleep and Circadian Disorders. Front. Neurosci. 13:1318.
Patrocinador
This work was supported by the Ministry of Economy and Competitiveness, the Instituto de Salud Carlos III through CIBERFES (CB16/10/00239) and grants 19899/GERM/15 awarded to JM and the Ministry of Science Innovation and Universities RTI2018-093528-B-I00 to MR (all of them co-financed by FEDER).Résumé
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 TAPM10
(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.