The Application of MATEC (Multi-AI Agent Team Care) Framework in Sepsis Care

TL;DR

This study addresses limited access to sepsis expertise in under-resourced hospitals by proposing MATEC, a Multi-AI Agent Team Care framework that deploys a team of specialized AI agents for diagnosis, treatment planning, risk prediction, and care coordination. In a pilot with ten attending physicians evaluating a web-based interface, participants rated usefulness and accuracy highly, with cross-verified outputs and care-gap analyses supported by dedicated agents addressing social determinants of health and patient safety. The results suggest that multi-agent collaboration can augment frontline clinicians, streamline sepsis workflows, and potentially improve outcomes, while underscoring the need for electronic health record integration and larger-scale validation. Overall, MATEC demonstrates a scalable, modular approach to augmenting rural and under-resourced healthcare delivery through specialized AI agents and structured collaboration.

Abstract

Under-resourced or rural hospitals have limited access to medical specialists and healthcare professionals, which can negatively impact patient outcomes in sepsis. To address this gap, we developed the MATEC (Multi-AI Agent Team Care) framework, which integrates a team of specialized AI agents for sepsis care. The sepsis AI agent team includes five doctor agents, four health professional agents, and a risk prediction model agent, with an additional 33 doctor agents available for consultations. Ten attending physicians at a teaching hospital evaluated this framework, spending approximately 40 minutes on the web-based MATEC application and participating in the 5-point Likert scale survey (rated from 1-unfavorable to 5-favorable). The physicians found the MATEC framework very useful (Median=4, P=0.01), and very accurate (Median=4, P<0.01). This pilot study demonstrates that a Multi-AI Agent Team Care framework (MATEC) can potentially be useful in assisting medical professionals, particularly in under-resourced hospital settings.

Figures (7)

• Figure 1:
• Figure 2:
• Figure 3: MATEC framework web-based user interface.
• Figure 4: Example output from sepsis medical team and social work AI agent. A case with sepsis due to endocarditis
• Figure 5: Example of Care Gap Analysis.