Insomnia Characterization: From Hypnogram to Graph Spectral Theory

• Published in: IEEE transactions on biomedical engineering Vol. 63; no. 10; pp. 2211 - 2219
• Main Authors: Chaparro-Vargas, Ramiro, Ahmed, Beena, Wessel, Niels, Penzel, Thomas, Cvetkovic, Dean
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2016
• Subjects: Autoregressive processes; Biological system modeling; Brain modeling; Computational modeling; Electroencephalography; Fuzzy Logic; graph spectral theory; Humans; insomnia; Logistic Models; Logistics; polysomnogram (PSG); Polysomnography - methods; Signal Processing, Computer-Assisted; Sleep; Sleep - physiology; Sleep Initiation and Maintenance Disorders - diagnosis; Sleep Initiation and Maintenance Disorders - physiopathology; sleep onset period
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2016.2515261

Objective: To quantify and differentiate control and insomnia sleep onset patterns through biomedical signal processing of overnight polysomnograms. Methods: The approach consisted of three tandem modules: 1) biosignal processing module, which used state-space time-varying autoregressive moving average (TVARMA) processes with recursive particle filter, 2) hypnogram generation module that implemented a fuzzy inference system (F'S), and 3) insomnia characterization module that discriminated between control and subjects with insomnia using a logistic regression model trained with a set of similarity measures (d 1 , d 2 , d 3 , d 4 ). The study employed sleep onset periods from 16 control and 16 subjects with insomnia. Results: Statespaced TVARMA processes with recursive particle filtering provided resilience to nonlinear, nonstationary, and non-Gaussian conditions of biosignals. F'S managed automated sleep scoring robust to intersubjects' and interraters' variability. The similarity distances quantified in a scalar measure the transitions amongst sleep onset stages, computed from expert and automated hypnograms. A statistical set of unpaired two-tailed t-tests suggested that distances d 1 , d 2 , and d 3 had larger statistical significance (p d 1 <; 6.5 × 10 -5 , p d 2 <; 2.1 × 10 -4 , p d 3 <; 4.5 × 10 -7 ) to characterize sleeping patterns. The logistic regression model classified control and subjects with insomnia with sensitivity 87%, specificity 75%, and accuracy 81%. Conclusion: Our approach can perform a supportive role in either biosignal processing, sleep staging, insomnia characterization, or all the previous, coping with time-consuming procedures and massive data volumes of standard protocols. Significance: The introduction of graph spectral theory and logistic regression for the diagnosis of insomnia represents a novel concept, attempting to describe complex sleep dynamics throughout transitions networks and scalar measures.