Intelligent Decision-Making in Diabetes Diagnosis: An Exploration of Multi-Granularity Three-Way Decisions
Liyin Wang, Anna Wang, Xueqing Fan, Yu-Ting Cheng · 2023
Diabetes, a chronic metabolic disease prevalent in real world, poses challenges due to its complex ambiguity and uncertainty in diagnosis and treatment. To address these issues, this paper proposes an intelligent decision-making framework that combines triangular fuzzy sets (TFSs), multigranularity (MG) three-way decision (TWD) and MABAC (Multi-Attribute Border Approximation Area Comparison). First, granular computing is applied to cope with the uncertainty of diabetes disease data by transforming it into an MG representation. Next, the MG TWD method is utilized to categorize the diagnosis and treatment of the disease into different levels, leading to a comprehensive evaluation and the final diagnosis result. Additionally, TFSs are employed to describe the fuzzy characteristics of diabetes and remedy plans, whereas the MABAC method is used to compare and evaluate different plans, ultimately selecting the optimal treatment strategy. By applying these methods, we effectively address the ambiguity and uncertainty associated with diabetes diagnosis and treatment. The intelligent decision-making framework offers more accurate and reliable diagnosis results, serving as a scientific foundation for doctors to develop personalized treatment plans. Moreover, this study holds significant value in advancing the field of diabetes diagnosis and treatment, offering new ideas and methods to improve the quality of life and health outcomes for diabetes patients.