Intelligent Analysis of Polysomnograms in a Sleep Apnea Decision Support System

摘要

Automation of the medical diagnosis of the Sleep Apnea Syndrome (SAS) requires an intelligent analysis of the pneumological and neurophysiological signals of the patient that combines both conventional and Artificial Intelligence techniques in order to detect respiratory abnormalities and construct a hypnogram for the patient. Nonetheless, an independent analysis of the signals is, in itself, neither sufficient nor adequate to the problem, and a process of temporal fusion and correlation between the signals is necessary for both a correct classification of the apneic events within a sleep stage framework, and to explain the occurrence of abnormal sleep patterns as a consequence of these events. This is the approach incorporated in SAMOA, a computerised system for respiratory analysis and sleep study, which makes a customised diagnosis for the patient in respect of the possible existence of the Sleep Apnea Syndrome and also classifies the syndrome. In this article, the most important aspects of the system in terms of the information integration and diagnostic processes are described and the validation results obtained are discussed.