Optimizing Cancer Treatment Decisions through Density based-Fuzzy Clustering and Multi-Criteria Decision Making Techniques

Source abstract

The increasing complexity and uncertainty in medical data, including electronic health records, imaging studies, and laboratory results, pose significant challenges for healthcare analytics. Traditional clustering techniques struggle to manage incomplete and noisy data, necessitating more robust methodologies. This study presents a hybrid decision-support framework that integrates fuzzy density-based clustering with fuzzy multicriteria decision-making to improve healthcare decision-making under uncertainty. By using fuzzy cubic numbers, the proposed model enhances patient stratification, treatment ranking, and resource allocation. Applications include chronic disease management, pandemic response, and predictive analytics for early disease detection. The approach is particularly relevant for ICU prioritization, ventilator allocation, and real-time monitoring using wearable medical devices. Case study validation in oncology demonstrates that this hybrid framework significantly improves decision accuracy while reducing the cognitive burden on healthcare professionals. Sensitivity analysis confirms robustness across parameter variations, and comparative evaluation shows advantages over traditional approaches in handling clinical uncertainty.