FEAT: A Multi-Agent Forensic AI System with Domain-Adapted Large Language Model for Automated Cause-of-Death Analysis

2025-08-11

AI Summary

Forensic cause-of-death determination faces systemic challenges—including workforce shortages, high inter-expert diagnostic variability, and insufficient standardization—particularly in high-volume forensic systems such as China’s. To address these, we propose the first multi-agent AI system specifically designed for forensic pathology. Our approach innovatively integrates domain-adapted large language models, tool-augmented reasoning, hierarchical retrieval-augmented generation (RAG), and a human-in-the-loop verification loop. The system supports task decomposition, evidentiary analysis, reflective memory, and holistic conclusion synthesis. Evaluated on a multicenter cohort of real-world cases spanning six major geographic regions in China, it achieves significantly higher cause-of-death classification accuracy than existing AI methods. Blind evaluation shows strong agreement with forensic expert consensus (Cohen’s κ = 0.89) and markedly improves detection of subtle pathological and contextual evidence—advancing forensic autopsy toward automation, standardization, and interpretability.

Technology Category

• Multiagent Systems: Other Foundations of Multi Agent Systems
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Forensic cause-of-death determination faces systemic challenges, including workforce shortages and diagnostic variability, particularly in high-volume systems like China's medicolegal infrastructure. We introduce FEAT (ForEnsic AgenT), a multi-agent AI framework that automates and standardizes death investigations through a domain-adapted large language model. FEAT's application-oriented architecture integrates: (i) a central Planner for task decomposition, (ii) specialized Local Solvers for evidence analysis, (iii) a Memory & Reflection module for iterative refinement, and (iv) a Global Solver for conclusion synthesis. The system employs tool-augmented reasoning, hierarchical retrieval-augmented generation, forensic-tuned LLMs, and human-in-the-loop feedback to ensure legal and medical validity. In evaluations across diverse Chinese case cohorts, FEAT outperformed state-of-the-art AI systems in both long-form autopsy analyses and concise cause-of-death conclusions. It demonstrated robust generalization across six geographic regions and achieved high expert concordance in blinded validations. Senior pathologists validated FEAT's outputs as comparable to those of human experts, with improved detection of subtle evidentiary nuances. To our knowledge, FEAT is the first LLM-based AI agent system dedicated to forensic medicine, offering scalable, consistent death certification while maintaining expert-level rigor. By integrating AI efficiency with human oversight, this work could advance equitable access to reliable medicolegal services while addressing critical capacity constraints in forensic systems.

Problem

• Automates forensic cause-of-death analysis using AI
• Addresses workforce shortages and diagnostic variability
• Ensures legal and medical validity in conclusions

Innovation

• Multi-agent AI framework for death investigations
• Domain-adapted large language model
• Tool-augmented reasoning and hierarchical generation