Multi-Agent Medical Decision Consensus Matrix System: An Intelligent Collaborative Framework for Oncology MDT Consultations

TL;DR

This paper presents a multi-agent AI system that simulates multidisciplinary oncology team consultations, quantifies consensus using a mathematical matrix, and improves decision quality with reinforcement learning, achieving high accuracy and expert-rated appropriateness.

Contribution

It introduces a novel multi-agent framework with a consensus matrix and reinforcement learning to enhance clinical decision-making and traceability in oncology MDTs.

Findings

Achieved 87.5% accuracy on medical benchmarks.

Consensus rate of 89.3% among agents.

Expert reviewers rated outputs 8.9/10.

Abstract

Multidisciplinary team (MDT) consultations are the gold standard for cancer care decision-making, yet current practice lacks structured mechanisms for quantifying consensus and ensuring decision traceability. We introduce a Multi-Agent Medical Decision Consensus Matrix System that deploys seven specialized large language model agents, including an oncologist, a radiologist, a nurse, a psychologist, a patient advocate, a nutritionist and a rehabilitation therapist, to simulate realistic MDT workflows. The framework incorporates a mathematically grounded consensus matrix that uses Kendall's coefficient of concordance to objectively assess agreement. To further enhance treatment recommendation quality and consensus efficiency, the system integrates reinforcement learning methods, including Q-Learning, PPO and DQN. Evaluation across five medical benchmarks (MedQA, PubMedQA, DDXPlus, MedBullets and SymCat) shows substantial gains over existing approaches, achieving an average accuracy of 87.5% compared with 83.8% for the strongest baseline, a consensus achievement rate of 89.3% and a mean Kendall's W of 0.823. Expert reviewers rated the clinical appropriateness of system outputs at 8.9/10. The system guarantees full evidence traceability through mandatory citations of clinical guidelines and peer-reviewed literature, following GRADE principles. This work advances medical AI by providing structured consensus measurement, role-specialized multi-agent collaboration and evidence-based explainability to improve the quality and efficiency of clinical decision-making.