Classifying AI-Powered prediction models for disability progression using the Tamir-Based complex fuzzy Aczel–Alsina WASPAS method

Abstract

Abstract Tracking the development of disability conditions presents significant challenges due to uncertainty, imprecision, and dynamic health progression patterns. Traditional multi-criteria decision-making (MCDM) techniques often struggle with such complex and fuzzy medical data. To address this gap, we propose a novel classification framework based on Tamir’s complex fuzzy Aczel-Alsina weighted aggregated sum product assessment (WASPAS) approach. This hybrid model incorporates complex fuzzy logic to handle multidimensional uncertainty and utilizes the Aczel-Alsina function for flexible aggregation. We apply this method to evaluate and classify AI-powered predictive models used for monitoring disability progression. The proposed framework not only improves classification accuracy but also enhances decision support in healthcare planning. A case study validates the robustness, sensitivity, and effectiveness of the proposed method in real-world disability tracking scenarios.