Publication details

Feasibility Study of an Interactive Medical Diagnostic Wikipedia

Conference Paper (international conference)

Grim Jiří

serial: SPMS 2016 Stochastic and Physical Monitoring Systems, p. 31-45

action: SPMS 2016 Stochastic and Physical Monitoring Systems, (Prague - Dobřichovice, CZ, 20.06.2016-24.06.2016)

project(s): GA14-02652S, GA ČR, GA14-10911S, GA ČR

keywords: Multivariate statistics, Medical diagnostics, Product mixtures, Incomplete data, Sequential classification, EM algorithm

preview: Download

abstract (eng):

Considering different application possibilities of product distribution mixtures we have proposed three formal tools in the last years, which can be used to accumulate decision-making know-how from particular diagnostic cases. First, we have developed a structural mixture model to estimate multidimensional probability distributions from incomplete and possibly weighted data vectors. Second, we have shown that the estimated product mixture can be used as a knowledge base for the Probabilistic Expert System (PES) to infer conclusions from definite or even uncertain input information. Finally we have shown that, by using product mixtures, we can exactly optimize sequential decision-making by means of the Shannon formula of conditional informativity. We combine the above statistical tools in the framework of an interactive open-access medical diagnostic system with automatic accumulation of decision-making knowledge.