Fuzzy logic and machine learning for diabetes risk prediction using modifiable factors

Diabetes mellitus, a global health concern, includes type 1 diabetes, with an uncontrollable risk, and type 2 diabetes, where risk can be managed through lifestyle modifications. This study examines the impact of modifiable risk factors—diet, physical activity, and body mass index (BMI)—on type 2 diabetes development. Using fuzzy logic, binary variables from a healthcare diabetes dataset were transformed into a fuzzy format, generating three output classes: "no diabetes risk," "possible diabetes risk," and "diabetes risk present." The intermediate class, "possible diabetes risk," serves as an alert for adopting healthier lifestyles to mitigate risk. Machine learning was applied to both the original and fuzzy-transformed datasets. While the original dataset provided binary outputs with moderate accuracy and higher computation times, the fuzzy-transformed dataset yielded more nuanced predictions, reduced computation time, and improved classifier performance. This approach enhances diabetes risk assessment and supports proactive interventions.