Using the algebraic sum method in medical expert systems

In the development of a medical expert system, the choice of algorithms is an important consideration. According to 1979 statistics, some 60% of medical expert systems were based on the Bayes method, 30% were based on a linear discriminant function, matching handle and criterion tree, and 10% were based on other algorithms. Overall diagnostic accuracy rates were generally about 90%. Although the Bayes method has been used very widely, it has some limitations. Its two assumptions are difficult to satisfy in computer-assisted diagnostic systems, and it does not do well in solving the contradiction between the low frequency of a disease manifestation and the high specificity of the manifestation. A weighted summation method can better solve this problem, since the diagnostic value can be adjusted according to the real importance of each item of diagnostic information. The weighted summation method has been widely used in the development of many medical expert systems, such as the earliest expert system of traditional Chinese medicine: “The Computer Program for the Diagnosis and Treatment of Liver Disease Based on the Principle of Dialectical Treatment”. It is concluded that the algebraic sum method is an efficient, simple, and convenient mathematical model for the development of medical expert systems