An Expert System to Detect Polycystic Ovary Syndrome under Uncertainty

Abstract

This paper describes a prototype of clinical expert system for risk stratification of patients with polycystic ovary syndrome (PCOS). Polycystic ovary syndrome (PCOS) is the most common hormonal disorder among women of reproductive age. It is a heterogeneous disorder of uncertain causes. Since the symptoms of PCOS are seemingly unrelated to one another the condition is often overlooked and undiagnosed. The determination of accurate degree or intensity of PCOS signs is difficult for the physician. Hence, the accuracy of diagnostic process is difficult to achieve. The signs and symptoms of PCOS are usually expressed in qualitative and quantitative ways. Since the qualitative factors can not measured in a quantitative way, various types of uncertainties may occurs such as incompleteness, vagueness, and imprecision. For that, it is necessary to address the issue of uncertainty by using appropriate methodology. However, no existing system is able to address this issue of uncertainty. Therefore, this paper demonstrates the application of a novel method, named belief rule-based inference methodology -RIMER; this prototype can deal with uncertainties in both clinical domain knowledge and clinical data. This paper reports the development of a Belief Rule Based Expert System (BRBES) using RIMER approach, which is capable of detect the PCOS by taking account of signs and symptoms.