Algorithms for Monitoring the Effectiveness of Therapeutic and Rehabilitation Procedures Based on Clinical Blood Analysis Indicators in the Medical Decision Support System

Abstract

The purpose of research is development of algorithms for a computer system for monitoring the effectiveness of therapeutic procedures in terms of clinical blood analysis.Methods. A set of algorithms has been developed for a computer system for monitoring the effectiveness of medicinal prescriptions based on the results of a clinical blood test, including an algorithm for analyzing the dynamics of intercellular ratios in a clinical blood test, an algorithm for filling in a database, an algorithm for forming a base of decisive rules, an algorithm for analyzing the sensitivity of a decisive rule.Results. To determine the effectiveness of the treatment plan, it is proposed to evaluate intercluster distances between clustered pathological conditions using the PNN-FNN-FNN* neural network, built on a hybrid basis using probabilistic neural networks and fuzzy decision-making logic. The proposed structure of the PNN-FNN-FNN* hybrid neural network contains three macrolayers. The number of modules in macrolayers is equal to the number of selected clusters of the monitored disease. The first macrolayer consists of blocks of probabilistic neural networks, the number of which in each module is determined by the number of segments allocated in the space of informative features. The second and third macrolayers consist of two-layer fuzzy neural networks. The fuzzy neural network module with the FNN* structure is a block-type macrolayer, each of the blocks of which consists of two layers.Conclusion. Approbation of monitoring algorithms was carried out on an experimental group of patients with benign prostatic hyperplasia and patients with prostate cancer. Experimental studies of the classification quality indicators of a hybrid neural network with the PNN-FNN-FNN* structure in monitoring the effectiveness of treatment of urological patients have shown diagnostic indicators that allow us to recommend it for use in medical decision support systems when monitoring the effectiveness of treatment of urological patients.