Aristotle University Of Thessaloniki (AUTH)
Μελέτη αναπνευστικού σήματος σε ασθενείς με σύνδρομο αποφρακτικών απνοιών κατά τον ύπνο με τη βοήθεια της πολυπλοκότητας και άλλων βιοσημάτων και βιοπαραμέτρων
Abstract
dc:descriptionIntroduction: Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a common sleep disorder which requires the time and money consuming method of full polysomnography to be diagnosed. Alternative methods for initial screening are sought. Aim: The prediction of Apnea-Hypopnea Index (AHI) in patients suspected to suffer from OSAHS using a linear regression model and a decision tree model based on nonlinear analysis of three respiratory signals during sleep instead of performing full polysomnography. Patients-Methods: One hundred randomized patients referred to the sleep unit of a tertiary care hospital underwent full polysomnography and their tests were manually scored. Three nonlinear indices (Largest Lyapunov Exponent-LLE, Detrended Fluctuation Analysis-DFA and Approximate Entropy-APEN) were extracted from three respiratory biosignals (airflow from a nasal cannula-F, thoracic belt movement-T and Oxygen saturation from pulse oximetry-SpO₂) and provided input to a data mining application for the creation of predictive models for AHI. Results: A linear regression model which includes the variables: Body Mass Index (BMI), Time with SpO₂<90%, LLE and DFA from both F and T presented a correlation coefficient r2 = 0.77 in predicting AHI. With a cutoff value of ΑΗΙ=5, the displayed sensitivity and specificity were 82% and 57% in discrimination between sufferers from OSAHS and normal subjects. Similarly, the produced decision tree for the discrimination between patients and normal using the variables: Epworth, sex, time with SpO₂<90%, LLE and DFA from both F and T, presented sensitivity and specificity of 75% and 74%, respectively. Conclusion: A reliable prediction of the presence of OSAHS is possible with the use of linear and nonlinear indices from only 3 respiratory signals during sleep. The proposed models could be used in the initial screening of patients with suspected OSAHS utilizing a practical and relatively cheap methodology.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2011
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Καϊμακάμης, Ευάγγελος
- Kaimakamis, Evangelos
Subjects
dc:subject × 24- Εκθέτης lyapunov
- Μη γραμμική ανάλυση
- Πολυσωματογραφική μελέτη ύπνου
- Προβλεπτικό μοντέλο
- ΣΑΑΥΥ
- AHI
- APEN
- DFA
- Apnea - hypopnea index
- Approximate entropy
- Detrended fluctuation analysis
- Largest lyapunov exponent
- Nonlinear analysis
- OSAHS
- Polysomnography
- Return maps
- Ιατρική και Επιστήμες Υγείας
- Κλινική Ιατρική
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Medical and Health Sciences
- Clinical Medicine
- Natural Sciences
- Computer and Information Sciences
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/28864