An intuitionistic fuzzy Dombi–Archimedean RANCOM–AROMAN framework for AI-enabled telemedicine platform selection

Abstract

Artificial intelligence (AI)-enabled telemedicine platform selection involves multiple conflicting criteria and uncertain expert judgments. Conventional multi-criteria decision-making (MCDM) approaches often fail to preserve membership, non-membership, and hesitation throughout the complete decision process. Existing intuitionistic fuzzy Dombi models lack fully integrated aggregation, criterion weighting, dual-normalization fusion, and ranking mechanisms with rigorous endpoint treatment. This study develops a mathematically consistent and robust intuitionistic fuzzy Dombi--Archimedean (IFDA) decision framework that integrates IFDA--RANCOM--AROMAN to manage uncertain evaluations from criterion weighting to final ranking. IFDA--RANCOM determines criterion weights, whereas IFDA--AROMAN performs dual normalization, fuzzy fusion, benefit--cost utility construction, and alternative ranking. The framework is illustrated through the selection of six AI-enabled telemedicine platforms for rural healthcare. The obtained weights are omega =  (0.36,0.28,0.20,0.12,0.04), and the baseline ranking is (A3 > A2  > A5 > A1 > A6 > A4). RANCOM--AROMAN reproduces the same complete ranking, while other methods confirm a similar leading group. The leading alternatives remain stable under parameter variations and ( ± 15%) criterion-weight perturbations. The framework provides a reproducible uncertainty-preserving decision mechanism. The proposed model offers a rigorous and robust tool for complex fuzzy decision-making applications.