Strategies for prediction of cardio-vascular status without explicit modeling
Teresa Rocha, Simão Paredes, P. Carvalho, Jorge M. O. Henriques · 2016
This work presents a strategy for the prediction of biosignals' future trend, based on a case based reasoning procedure. The proposed scheme is supported on the hypothesis that the future evolution of a given biosignal (template) can be estimated from similar patterns existent in a historic dataset. The first step consists in the application of a simple and efficient measure to evaluate the similarity between biosignal time series. Then, using the similar patterns identified by the similarity process, a predictive scheme is introduced. The proposed approach, which does not use an explicit model, considers the wavelet decomposition of the signals (template and similar patterns) to determine the most representative trend at each of the several decomposition levels. These trends are then aggregated to derive the required biosignal future estimation. The strategy was validated using vital signals (heart rate, blood pressure and weight) daily collected during the myHeart tele-monitoring study, in particular in the assessment of the hypertension risk.