A Fuzzy Expert System for Predicting the Risk of Ischemic Stroke Based on Modifiable Risk Factors

Stroke is one of the leading causes of death among neurological disorders. Early identification and control of modifiable risk factors such as blood pressure, blood sugar, cholesterol levels, heart disease, body mass index, and smoking can significantly reduce both the incidence and severity of stroke. However, under varying conditions, these key indicators are often overlooked, which may affect the accuracy of diagnosis. In some cases, physicians may face delays in decision-making, leading to postponed treatment and potentially irreversible harm to the patient. To address this challenge, a fast, accurate, and reliable diagnostic support system is essential. This study proposes a fuzzy expert system for the prediction of ischemic stroke risk based on modifiable and controllable factors. The system was evaluated using data from 120 real patient cases, and its performance was compared with the k-nearest neighbors classification method. The proposed system demonstrated excellent performance, achieving an accuracy of (92.8 ± 4.3)%.