A Decision Tree-Initialised Neuro-fuzzy Approach for Clinical Decision Support

Apart from the need for superior accuracy, healthcare applications of intelligent systems also demand deployment interpretable machine learning models which allow clinicians to interrogate and validate extracted medical knowledge. Fuzzy rule-based are generally considered that able reflect associations between conditions associated symptoms, through use linguistic if-then statements. Systems built on top fuzzy sets particular appealing since they enable tolerance vague imprecise concepts often embedded in entities such as symptom description test results. They facilitate an approximate reasoning framework mimics human supports delivery expertise expressed statements ‘weight low’ or ‘glucose level high’ while describing symptoms. This paper proposes approach by performing data-driven accurate rule bases clinical decision support. The starts with generation a crisp base tree mechanism, capable capturing simple structures. is then transformed into base, forms input adaptive network-based inference system (ANFIS), thereby further optimising parameters both antecedents consequents. Experimental studies popular data benchmarks demonstrate proposed work learn compact involving antecedents, statistically better comparable performance those achieved state-of-the-art classifiers.