Yoshiaki Matsumoto

An automated program for mental stress and apnea/hypopnea events detection

The development of computer-aided diagnosis tools for detecting specific health-related events occurrences is of a great importance in the medical practice nowadays. Actually, health professionals still use manual methods for screening physiological data to get valuable information. This task becomes fastidious when the data is very long. In this paper, we present a new and simple method, we called windowed detrended fluctuation analysis (WDFA), for the detection of health-related events in physiological data. This method is based on the calculation of local energy of detrended profile of RR series obtained from the ECG signal. Data acquired during night containing apnea and hypopnea episodes and mental stress related data were used. Experiments showed that it is possible to detect apnea or hypopnea events and mental stress time episodes. Our method is well suited for the analysis of long time series data and the detection of abrupt changes in physiological data.