A Fuzzy Logic–Based Intelligent System for Early Risk Identification of Pancreatic Ductal Adenocarcinoma

Abstract Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive malignancies, often diagnosed at an advanced stage due to the absence of early clinical symptoms. Early identification and risk stratification are therefore crucial to improving patient outcomes and survival rates. This study presents an intelligent decision-support system based on fuzzy logic for the early identification and categorization of PDAC risk using patient clinical data. Key input parameters such as age at diagnosis, tumor classification, treatment type, and vital status are incorporated into a Fuzzy Inference System (FIS). The proposed model classifies patients into Low, Medium, and High-Risk groups using a transparent rule-based reasoning mechanism. The Mamdani-type fuzzy logic approach enables effective handling of uncertainty and imprecision inherent in medical data, while maintaining interpretability for clinical decision-making. Experimental evaluation demonstrates that the proposed system can effectively support early risk assessment and assist clinicians in diagnosis and treatment planning. The results highlight the potential of fuzzy logic–based models as reliable and interpretable tools for early PDAC risk prediction.