CMDTS: The Causality-based Medical Diagnosis and Treatment System

Our medical world is replete with clinical data but this data is rarely automatically exploited for bringing more health to our society. Many researches have been conducted in Medical Data Mining, but almost all of them have focused on diagnosing the diseases not treating the patients. In this paper we propose the Causality-based Medical Diagnosis and Treatment System, which can be used to diagnose a patient disease and suggest treatments to her/him. Our proposed system has three main subsystems: Causal Network Extractor, Diagnosis Subsystem and Treatment Suggesting Subsystem. Two main features of our system are: it takes solely observational data as input data and uses the causality-based action mining methodology. Action Mining is relatively a new trend in Data Mining which aims in proposing more actionable patterns to domain experts. We have implemented and tested our proposed method on some real and synthesized data. The results show superiority of our method over current state of the art method. Taking into account the causality results in more reliable treatments and makes it possible to use this system in real world situations.