<![CDATA[Multidisciplinary team meetings (MDTMs) are central to cancer care. However, consensus can be hard to reach because specialists rely on diverse expertise and uncertain, multi-criteria clinical data. In this paper, we propose a group decision support system (GDSS) that integrates a multi-agent system (MAS) with multi-criteria decision making (MCDM) to structure interactions, aggregate expert preferences, enable real-time evaluation of options based on criteria, and transparently prioritize patients for discussion and intervention. Each specialist is represented by an agent that evaluates cases against shared criteria, while an embedded negotiation protocol enables exchanges and concessions to resolve conflicts and build consensus. We evaluated the GDSS using simulated breast cancer MDTM scenarios generated from a synthetic dataset of MDTM records. Experimental results demonstrate rapid convergence toward a consensual patient prioritization within a few negotiation iterations; in our experiments, agreement on the highest risk patient was reached after four rounds. Sensitivity analysis on subjective inputs, including criteria weights and preference profiles, produced minor changes in the resulting ranking, indicating robustness and stability to preference variations. The system maintains low computational complexity and short execution times, improving the transparency and consistency of MDTM recommendations. These outcomes confirm effectiveness and scalability for complex multidisciplinary clinical decisions.]]>
Copyrights © 2026
