Related Experiment Video
Updated: Aug 5, 2026
07:54
Drug-Induced Sleep Endoscopy (DISE) with Target Controlled Infusion (TCI) and Bispectral Analysis in Obstructive Sleep Apnea
Published on: December 6, 2016
Stability analysis of sleep apnea time series using identified models: a case study
Luis Antonio Aguirre1, Alvaro V P Souza
1Lab. de Modelagem Análise e Controle de Sistemas Não-Lineares, Departamento de Engenharia Eletrônica Universidade Federal de Minas Gerais, Av. Antônio Carlos 6627, Belo Horizonte, Minas Gerais 31270-901, Brazil. aguirre@cpdee.ufmg.br
Computers in Biology and Medicine
|March 30, 2004
Summary
Nonlinear models accurately classify sleep apnea breathing patterns. These identified models show promise for computer-based patient monitoring systems.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Sleep Medicine
Background:
- Sleep apnea is a common disorder characterized by abnormal breathing patterns.
- Accurate classification of breathing patterns is crucial for diagnosis and monitoring.
- Existing methods may have limitations in capturing complex physiological dynamics.
Purpose of the Study:
- To investigate the efficacy of identified nonlinear multivariable autonomous models for classifying breathing patterns in sleep apnea patients.
- To assess the potential of these models for computer-based monitoring applications.
Main Methods:
- Development and application of nonlinear multivariable autonomous models.
- Detailed explanation of the model identification procedure.
- Case study implementation for breathing pattern analysis.
Main Results:
- The identified nonlinear models demonstrated effectiveness in classifying breathing patterns.
- The study successfully applied the models to a specific sleep apnea case study.
- Results indicate a strong correlation between model performance and breathing pattern classification.
Conclusions:
- Identified nonlinear multivariable autonomous models are a viable tool for sleep apnea breathing pattern classification.
- These models hold significant potential for enhancing computer-based patient monitoring systems.
- Further research can explore broader clinical applications and model refinements.
