An intelligent fuzzy inference rule‐based expert recommendation system for predictive diabetes diagnosis

Abstract

Diabetes is one of the most common and hazardous diseases, which can affect almost every organ in the body. Diagnosis of diabetes requires determining all vital parameters related to the disease. However, the nature of the data from those parameters is very uncertain, affecting the process of disease diagnosis. This article proposes an intelligent fuzzy inference rule-based predictive diabetes diagnosis model (IFIR_PDDM), providing content recommendations to patients with diabetes. The suggested model employs an inference technique that medical specialists have validated for recommendations. IFIR_PDDM comprises three elements used to forecast the risk of diabetes disease. Initially, a fuzzy membership function utilizes medical recommendations and statistical methodologies. Medical specialists then validate the mining-based rules using a decision tree rule induction technique. The proposed model predicts the risk of diabetes disease using fuzzy inference based on Mamdani's technique. Based on this information, the recommendations for a normal life, nutrition, exercise, and medications are given to patients. We used an electronic health record (EHR) medical and clinical dataset from the PIMA Indian Diabetes dataset to develop our proposed model and assess its performance. The proposed model takes less time for diabetes diagnosis, and the expert recommendation system uses the fuzzy inference method.

Improved Cattle Disease Diagnosis Based on Fuzzy Logic Algorithms

“…The evaluation of a model using the theory of fuzzy sets is performed by polling an expert system and by developing a fuzzy rule “if… then….”. In this case, an expert is provided with sets of known values of input linguistic parameters suitable for diagnosis in some cases [ 22 , 23 ].…”