Fuzzy Logic-Based Clinical Decision Making for Early Detection and Management of Cardiovascular Diseases

Abstract: The use of Fuzzy Logic to create a Mamdani-based Clinical Decision-Making Model is useful in assessing the Risk of Cardiovascular Diseases based on several Key Clinical Parameters including Glycated Hemoglobin (HbA1c), Low-Density Lipoprotein Cholesterol (LDL-C), and Body Mass Index (BMI). A Three Dimensional Surface Analysis was conducted and demonstrated smooth transition between different Risk Levels. Also, Numerical Case Studies were conducted that showed clinically meaningful results. For example, an individual with (LDL-C = 150 mg/dL, HbA1c = 6.2%, BMI = 31 kg/m²) had a Defuzzified Risk Score of 81.55 which would indicate High Cardiac Risk. The proposed model is a simple, transparent and computationally inexpensive method for Personalized Assessment of the Risk of Cardiovascular Disease and Early Intervention.

Keywords: Cardiovascular disease, Fuzzy logic, Mamdani fuzzy inference system, Clinical decision support system, LDL cholesterol HbA1c