An Expert Selection System for Medical Diagnosis

This paper introduces an expert selection system that uses learning and finds the best expert to assign to each patient based on the context of the patient. The context may include a variety of information related to the patient's health condition, age, gender, previous drug doses etc. In this the most relevant information is embedded in only a few contexts. The relevant contexts may be different for different health conditions. A new class of algorithms were introduced for discovering the most relevant contexts and the best clinic and expert to use to make a diagnosis given a patient's contexts. The problem with the existing system is that, it uses Learn the EXpert algorithm (LEX) which assigns a single expert to each patient, whether an own expert of the clinic or another clinic's expert. The proposed system assigns multiple experts to patients with complex diseases.