Hybrid neural networks with virtual flows in in medical risk classifiers

Abstract

Modern medical risk classification systems focus on traditional risk factors and modeling methods. The available modeling tools do not allow reliable prediction of the of disease severity. In this study we develop prediction model of recurrent myocardial infarction in the rehabilitation period using several health variables generated in virtual flows. Hybrid decision modules with health data flows were used to build prognostic model for the prediction of disease. The vector of input information features consists of two subvectors: the first reflects real flows, the second reflects virtual flows. Complex interrelations among input data are modelled using Neural Network structure. The model classification quality of the intellectual cardiovascular catastrophe prediction system was tested on a sample composed of 230 patients who had acute myocardial infarction. For prediction, three categories of risk factors were identified: traditional factors, factors associated with stressful overloads, and risk factors derived from bio-impedance studies. During the rehabilitation period, the level of molecular products of lipid peroxidation and the antioxidant potential of blood serum were also studied. Experimental studies of various modifications of the proposed classifier model were conducted, consisting of sequential disconnection from the aggregator of solutions of “weak” classifiers at various hierarchical levels. The mathematical model show predictions accuracy of correct prognosis for the risk of myocardial infarction exceeding 0.86. Prediction quality indicators are higher than the known ASCORE cardiovascular catastrophe prediction system, on average, by 14%.