OMGs: A multi-agent system supporting MDT decision-making across the ovarian tumour care continuum

2026-02-14

AI Summary

This study addresses the challenge of limited access to multidisciplinary team (MDT) consensus for ovarian tumor patients in resource-constrained settings. To this end, it proposes OMGs—the first multi-agent AI system dedicated to comprehensive ovarian tumor management—which generates transparent, evidence-based MDT-style recommendations through collaborative deliberation among domain-specific agents that integrate clinical knowledge and interpretable reasoning. The work introduces the novel SPEAR multidimensional evaluation framework to quantitatively assess recommendation quality. In a multicenter study, OMGs’ recommendations demonstrated high alignment with expert MDT consensus (4.45 vs. 4.53 on a 5-point scale) and provided stronger evidentiary support (4.57 vs. 3.92). When applied to 59 patients, OMGs significantly enhanced the robustness and evidence-based quality of decision-making by frontline clinicians.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Ovarian tumour management has increasingly relied on multidisciplinary tumour board (MDT) deliberation to address treatment complexity and disease heterogeneity. However, most patients worldwide lack access to timely expert consensus, particularly in resource-constrained centres where MDT resources are scarce or unavailable. Here we present OMGs (Ovarian tumour Multidisciplinary intelligent aGent System), a multi-agent AI framework where domain-specific agents deliberate collaboratively to integrate multidisciplinary evidence and generate MDT-style recommendations with transparent rationales. To systematically evaluate MDT recommendation quality, we developed SPEAR (Safety, Personalization, Evidence, Actionability, Robustness) and validated OMGs across diverse clinical scenarios spanning the care continuum. In multicentre re-evaluation, OMGs achieved performance comparable to expert MDT consensus ($4.45 \pm 0.30$ versus $4.53 \pm 0.23$), with higher Evidence scores (4.57 versus 3.92). In prospective multicentre evaluation (59 patients), OMGs demonstrated high concordance with routine MDT decisions. Critically, in paired human-AI studies, OMGs most substantially enhanced clinicians'recommendations in Evidence and Robustness, the dimensions most compromised when multidisciplinary expertise is unavailable. These findings suggest that multi-agent deliberative systems can achieve performance comparable to expert MDT consensus, with potential to expand access to specialized oncology expertise in resource-limited settings.

Problem

• ovarian tumour
• multidisciplinary tumour board
• healthcare access
• resource-constrained settings
• clinical decision-making

Innovation

• multi-agent system
• MDT decision-making
• SPEAR evaluation framework
• ovarian tumour care
• AI clinical decision support