Effective decision-making is crucial in cardiovascular emergencies, where timely and accurate interventions directly influence patient outcomes. However, conventional decision-support approaches often struggle to cope with the intrinsic uncertainty, heterogeneity, and coexistence of multiple conflicting risk factors inherent in complex cardiovascular data. To address these challenges, this study introduces a novel fuzzy framework, namely the linear Diophantine \(\mathscr {M}\) -polar fuzzy set (LD \(\mathscr {M}\) PFS). The distinctive feature of LD \(\mathscr {M}\) PFS lies in its ability to model \(\mathscr {M}\) -polar information, which fundamentally differentiates it from linear Diophantine fuzzy sets (LDFSs) and their existing extensions by enabling the simultaneous representation of multiple, possibly conflicting, polar evaluations. This capability is particularly vital for capturing the multifaceted nature of cardiovascular risk assessment. In addition, two new aggregation operators the linear Diophantine \(\mathscr {M}\) -polar fuzzy weighted averaging (LD \(\mathscr {M}\) -FWA) operator and the linear Diophantine \(\mathscr {M}\) -polar fuzzy weighted geometric (LD \(\mathscr {M}\) -FWG) operator are developed to ensure robust and flexible aggregation of uncertain and multipolar information. Based on these operators, a novel multi-attribute decision-making (MADM) algorithm is proposed, which systematically evaluates and ranks alternatives through evidential reasoning and score functions to identify the most appropriate decision. The proposed framework significantly enhances the accuracy, reliability, and interpretability of emergency cardiovascular decision-making and demonstrates strong potential for extension to other complex medical decision-support applications.
