Automatic recognition of obstructive sleep apnoea syndrome using power spectral analysis of electrocardiogram and hidden markov models

Obstructive sleep apnoea syndrome (OSA) is a very common disorder in breathing during sleep. OSA is considered as clinically relevant when the breath stops during more than 10 seconds and occurs more than five times per sleep hour. In this work, we investigate a noninvasive automatic approach to classify sleep apnoea events based on power spectral analysis for the feature extraction of the ECG records and Hidden Markov Models (HMMs). Based on Bayesian Inference Criterion (BIC), the proposed HMM training algorithm is able to select the optimal number of states corresponding to each set of training features. For every state number, each iteration is initialized by the most appropriate model using data clustering, and by the rejection of the least probable state of the previous iteration. Both off-line and on-line schemes have been proposed. Only electrocardiogram (ECG) records are considered for the detection of OSA. In this preliminary work, we report training procedures and validation results of the models on whole night digitized ECG signals recorded from 70 subjects with normal and OSA breathing events obtained from the physionet database. Cardiovascular disease (CVD) being the number one killer for many of the developed nations, real-time patient monitoring via the mobile phone network is increasingly becoming popular. The CVD patients, as subscribers for the CVD monitoring service providers, access to the facilities before initiating the dedicated services. However, this authentication must be secured, since the service providers often hold sensitive health information of their subscribers. In this paper, we propose a fully automated and integrated cardiovascular patient authentication system using patients ECG as a biometric entity. The proposed ECG recognition method is up to 12 time faster than existing ECG based biometric algorithms, requires up to 6.5 times less template storage, needs only 2.49 (average) acquisition time with the a high accuracy rate (up to 95%) when experimented a small population size of 15. With this new authentication mechanism in place, the cardiovascular patients no longer need to provide additional details like user name or password for identification purposes to access their health monitoring facility, making the remote tele-cardiology application faster than existing authentication approaches.