DIFFERENTIAL DIAGNOSTICS MODEL RESEARCH BY MEANS OF THE POTENTIAL FUNCTIONS METHOD FOR NEUROLOGY DISEASES CLASSIFICATION

Abstract

Informatization in medicine offers a lot of opportunities to enhance quality of medical support, accuracy of diagnosis and provides the use of accumulated experience. Modern program systems are utilized now as additional tools to get appropriate advice. This article offers the way to provide help for neurology department doctor of NCSH «OKHMATDYT» during diagnosis determining. It was decided to design the program system for this purpose based on differential diagnostic model. The key problems in differential diagnosis are symptoms similarity between each other in one disease group and the absence of key symptom. Therefore the differential diagnostic model is needed. It is constructed using the potential function method in characteristics space. This characteristics space is formed by 100-200 points - patients with their symptoms. The main feature of this method here is that the decision function is building during recognition step united with learning that became possible with the help of modern powerful computers.