Insomnia Characterization

From Hypnogram to Graph Spectral Theory

Ramiro Chaparro-Vargas, Beena Ahmed, Niels Wessel, Thomas Penzel, Dean Cvetkovic

Research output: Contribution to journalArticle

Abstract

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 (FIS), 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 (d1, d2, d3, d4). The study employed sleep onset periods from 16 control and 16 subjects with insomnia. Results: State-spaced TVARMA processes with recursive particle filtering provided resilience to nonlinear, nonstationary, and non-Gaussian conditions of biosignals. FIS 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 d1, d2, and d3 had larger statistical significance (pd1<6.5 × 10-5,pd2<2.1 × 10-4,pd3<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.

Original languageEnglish
Article number7373576
Pages (from-to)2211-2219
Number of pages9
JournalIEEE Transactions on Biomedical Engineering
Volume63
Issue number10
DOIs
Publication statusPublished - 1 Oct 2016

Fingerprint

Logistics
Fuzzy inference
Processing
Sleep
Network protocols
Biomedical signal processing

Keywords

  • Fuzzy logic
  • graph spectral theory
  • insomnia
  • polysomnogram (PSG)
  • sleep onset period

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Insomnia Characterization : From Hypnogram to Graph Spectral Theory. / Chaparro-Vargas, Ramiro; Ahmed, Beena; Wessel, Niels; Penzel, Thomas; Cvetkovic, Dean.

In: IEEE Transactions on Biomedical Engineering, Vol. 63, No. 10, 7373576, 01.10.2016, p. 2211-2219.

Research output: Contribution to journalArticle

Chaparro-Vargas, R, Ahmed, B, Wessel, N, Penzel, T & Cvetkovic, D 2016, 'Insomnia Characterization: From Hypnogram to Graph Spectral Theory', IEEE Transactions on Biomedical Engineering, vol. 63, no. 10, 7373576, pp. 2211-2219. https://doi.org/10.1109/TBME.2016.2515261
Chaparro-Vargas, Ramiro ; Ahmed, Beena ; Wessel, Niels ; Penzel, Thomas ; Cvetkovic, Dean. / Insomnia Characterization : From Hypnogram to Graph Spectral Theory. In: IEEE Transactions on Biomedical Engineering. 2016 ; Vol. 63, No. 10. pp. 2211-2219.
@article{ff5bce3cd54942508be9146435c29917,
title = "Insomnia Characterization: From Hypnogram to Graph Spectral Theory",
abstract = "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 (FIS), 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 (d1, d2, d3, d4). The study employed sleep onset periods from 16 control and 16 subjects with insomnia. Results: State-spaced TVARMA processes with recursive particle filtering provided resilience to nonlinear, nonstationary, and non-Gaussian conditions of biosignals. FIS 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 d1, d2, and d3 had larger statistical significance (pd1<6.5 × 10-5,pd2<2.1 × 10-4,pd3<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.",
keywords = "Fuzzy logic, graph spectral theory, insomnia, polysomnogram (PSG), sleep onset period",
author = "Ramiro Chaparro-Vargas and Beena Ahmed and Niels Wessel and Thomas Penzel and Dean Cvetkovic",
year = "2016",
month = "10",
day = "1",
doi = "10.1109/TBME.2016.2515261",
language = "English",
volume = "63",
pages = "2211--2219",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - Insomnia Characterization

T2 - From Hypnogram to Graph Spectral Theory

AU - Chaparro-Vargas, Ramiro

AU - Ahmed, Beena

AU - Wessel, Niels

AU - Penzel, Thomas

AU - Cvetkovic, Dean

PY - 2016/10/1

Y1 - 2016/10/1

N2 - 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 (FIS), 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 (d1, d2, d3, d4). The study employed sleep onset periods from 16 control and 16 subjects with insomnia. Results: State-spaced TVARMA processes with recursive particle filtering provided resilience to nonlinear, nonstationary, and non-Gaussian conditions of biosignals. FIS 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 d1, d2, and d3 had larger statistical significance (pd1<6.5 × 10-5,pd2<2.1 × 10-4,pd3<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.

AB - 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 (FIS), 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 (d1, d2, d3, d4). The study employed sleep onset periods from 16 control and 16 subjects with insomnia. Results: State-spaced TVARMA processes with recursive particle filtering provided resilience to nonlinear, nonstationary, and non-Gaussian conditions of biosignals. FIS 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 d1, d2, and d3 had larger statistical significance (pd1<6.5 × 10-5,pd2<2.1 × 10-4,pd3<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.

KW - Fuzzy logic

KW - graph spectral theory

KW - insomnia

KW - polysomnogram (PSG)

KW - sleep onset period

UR - http://www.scopus.com/inward/record.url?scp=84991386871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991386871&partnerID=8YFLogxK

U2 - 10.1109/TBME.2016.2515261

DO - 10.1109/TBME.2016.2515261

M3 - Article

VL - 63

SP - 2211

EP - 2219

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

M1 - 7373576

ER -