Evaluation of Fuzzy Relation Method for Medical Decision Support

Abstract

The potential of computer based tools to assist physicians in medical decision making, was envisaged five decades ago. Apart from factors like usability, integration with work-flow and natural language processing, lack of decision accuracy of the tools has hindered their utility. Hence, research to develop accurate algorithms for medical decision support tools, is required. Pioneering research in last two decades, has demonstrated the utility of fuzzy set theory for medical domain. Recently, Wagholikar and Deshpande proposed a fuzzy relation based method (FR) for medical diagnosis. In their case studies for heart and infectious diseases, the FR method was found to be better than naive bayes (NB). However, the datasets in their studies were small and included only categorical symptoms. Hence, more evaluative studies are required for drawing general conclusions. In the present paper, we compare the classification performance of FR with NB, for a variety of medical datasets. Our results indicate that the FR method is useful for classification problems in the medical domain, and that FR is marginally better than NB. However, the performance of FR is significantly better for datasets having high proportion of unknown attribute values. Such datasets occur in problems involving linguistic information, where FR can be particularly useful. Our empirical study will benefit medical researchers in the choice of algorithms for decision support tools.

An update and further testing of a knowledge‐based diagnostic clinical decision support system for musculoskeletal disorders of the shoulder for use in a primary care setting

“…This is particularly an issue with a patient's description of their symptoms as they can misunderstand questions or misuse vocabulary to describe a symptom [31,32], resulting in incorrect data input.…”

“…Several authors have tackled this issue through the use of fuzzy logic, where the binary nature of inputs are offset by assigning each input a confidence value to its level of truth when reported [29]. Studies into fuzzy logic being used with naïve classifiers have shown optimal performance over non‐fuzzy systems [29,31,32]. However, the complexity of these systems is greatly increased due to the extra confidence values needed, which ideally require precise training data that may not always be available or easy to attain [31–33].…”

“…Another method of solving this problem is by reducing the ambiguity of patient responses through careful questioning and examination of the patient responses [31,32]. The prototype CDSS was developed only for clinician input, and provides clear prompting and advice on all questioning and physical examinations to allow the clinician to gain accurate responses.…”

A Fuzzy Probabilistic Method for Medical Diagnosis

“…Instead, fuzzy set inferencing would be useful. Fuzzy relation compositions attempt to find the fuzzy relation between the patient's symptoms and the doctor's diagnosis [2,3]. The composition most often used is the max-min composition [4][5][6], which has attained reasonably success for the last thirty years.…”