Robust technological solutions for smart healthcare systems using an integrated Sugeno-Weber aggregation framework under q-fractional fuzzy information

Artificial intelligence and robotics have brought in important complexities in the selection of the best possible technological solutions in modern healthcare systems. This study proposes a new multi-attribute decision making framework which overcomes these problems by using the concept of q-fractional fuzzy sets and the Sugeno-Weber aggregation operators. The proposed framework is a parameterized structure that is flexible, unlike conventional approaches that are fixed on aggregation mechanisms, which reflect the uncertainties that are captured in clinical evaluations. Six different aggregation operators are presented, each suited to the different preferences of decision-makers and different information structures. Our proposed methodology is demonstrated in a comprehensive case study of the five Alternatives AI-based healthcare systems that we have identified and evaluated based on four clinical criteria: diagnostic accuracy, response time, implementation complexity, and costs/scalability trade-offs. The results indicate that Sugeno-Weber parameter is capable of controlling the interaction strength between aggregated values, and the q-fractional parameter increases the representation space of uncertain expert judgments. Our results show that hybrid operators are able to combine the averaging and geometric tendencies well, and that all six operators produce highly stable rankings even in situations where there are conflicting performance indicators. The proposed framework not only enables transparent and interpretable decision making in healthcare technology assessment but also offers a mathematical framework whose structure, subject to the empirical scope and limitations of the present single case study, may be adaptable to other multi-criteria decision-making problems involving comparable forms of uncertainty.