Telehealth streams reduction based on pattern recognition techniques for events detection and efficient storage in EHR.

This work proposes a framework for telehealth streams analysis, founded on a pattern recognition technique that evaluates the similarity between multi-sensorial biosignals. The strategy combines the Haar wavelet with the Karhunen-Loève transforms to describe biosignals by means of a reduced set of parameters. These, that reflect the dynamic behavior of the biosignals, can support the detection of relevant clinical conditions. Moreover, the simplicity and fast execution of the proposed approach allow its application in real-time operation, as well as provide a practical way to manage historical electronic health records: i) common and uncommon behaviors can be distinguished; ii) the creation of different models, tailored to specific conditions can be efficiently stored. The efficiency of the methodology is assessed through its performance analysis, namely by computing the required number of operations and the compression rate. Its effectiveness is evaluated in the prediction of decompensation episodes using biosignals daily collected in the myHeart study (blood pressure, weight, respiration and heart rates).