Neuro-Symbolic Resolution of Recommendation Conflicts in Multimorbidity Clinical Guidelines

arXiv cs.CL / 4/21/2026

📰 NewsDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that fragmented and logically contradictory clinical guidelines become especially harmful for multimorbidity cases, creating clinician confusion and injecting “catastrophic noise” into AI systems like standard RAG that can hallucinate.
It proposes a neuro-symbolic pipeline that converts unstructured clinical recommendations into formal symbolic logic via a multi-agent system, then verifies redundancies and conflicts using a SAT (satisfiability) solver.
The authors build a hierarchical taxonomy of rule interactions and find that most detected issues fall into a “Local Conflict” category caused by interactions between comorbidities.
In evaluations on 12 authoritative SGLT2 inhibitor guideline documents, 90.6% of conflicts are classified as Local, while single-disease-focused guideline logic does not adequately address this structure.
The approach outperforms LLM baselines for conflict detection, achieving an F1 score of 0.861, and emphasizes that logical verification should occur before retrieval as a new standard for medical knowledge coordination in AI.

Abstract

Clinical guidelines, typically developed by independent specialty societies, inherently exhibit substantial fragmentation, redundancy, and logical contradiction. These inconsistencies, particularly when applied to patients with multimorbidity, not only cause cognitive dissonance for clinicians but also introduce catastrophic noise into AI systems, rendering the standard Retrieval-Augmented Generation (RAG) system fragile and prone to hallucination. To address this fundamental reliability crisis, we introduce a Neuro-Symbolic framework that automates the detection of recommendation redundancies and conflicts. Our pipeline employs a multi-agent system to translate unstructured clinical natural language into rigorous symbolic logic language, which is then verified by a Satisfiability (SAT) solver. By formulating a hierarchical taxonomy of logical rule interactions, we identify a critical category termed Local Conflict - a decision conflict arising from the intersection of comorbidities. Evaluating our system on a curated benchmark of 12 authoritative SGLT2 inhibitor guidelines, we reveal that 90.6% of conflicts are Local, a structural complexity that single-disease guidelines fail to address. While state-of-the-art LLMs fail in detecting these conflicts, our neuro-symbolic approach achieves an F1 score of 0.861. This work demonstrates that logical verification must precede retrieval, establishing a new technical standard for automated knowledge coordination in medical AI.