Modeling Interpretable Fuzzy Rule-Based Classifiers for Medical Decision Support

Modeling Interpretable Fuzzy Rule-Based Classifiers for Medical Decision Support

Jose M. Alonso (European Centre for Soft Computing, Spain), Ciro Castiello (University of Bari, Italy), Marco Lucarelli (University of Bari, Italy) and Corrado Mencar (University of Bari, Italy)
DOI: 10.4018/978-1-4666-1803-9.ch017
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Decision support systems in Medicine must be easily comprehensible, both for physicians and patients. In this chapter, the authors describe how the fuzzy modeling methodology called HILK (Highly Interpretable Linguistic Knowledge) can be applied for building highly interpretable fuzzy rule-based classifiers (FRBCs) able to provide medical decision support. As a proof of concept, they describe the case study of a real-world scenario concerning the development of an interpretable FRBC that can be used to predict the evolution of the end-stage renal disease (ESRD) in subjects affected by Immunoglobin A Nephropathy (IgAN). The designed classifier provides users with a number of rules which are easy to read and understand. The rules classify the prognosis of ESRD evolution in IgAN-affected subjects by distinguishing three classes (short, medium, long). Experimental results show that the fuzzy classifier is capable of satisfactory accuracy results – in comparison with Multi-Layer Perceptron (MLP) neural networks – and high interpretability of the knowledge base.
Chapter Preview
Top

Background

Current technology enables the acquisition and storage of large amounts of data, thus favoring the digital representation of complex phenomena in almost any field of human interest, being it scientific, commercial, engineering, etc. Medicine is one of such scientific fields where complex phenomena are most frequent, and a thoughtful comprehension of them is of prominent importance for the advance of knowledge at service of human health.

However, making sense of data is not a trivial task, especially when they describe complex phenomena. To this pursuit, Intelligent Data Analysis (IDA) is a methodology that prescribes a set of stages and techniques that can be applied for extracting useful knowledge from massive amounts of data. Nevertheless, IDA requires skillful application of the available techniques, which can only be accomplished by a careful intervention of human experts.

Complete Chapter List

Search this Book:
Reset