SyncAI.news, a Varaisys broadcasting
Learning Diagnostic Reasoning for Decision Support in Toxicology
NO

Nico Oberl\"ander, David Bani-Harouni, Tobias Zellner, Nassir Navab, Florian Eyer, Matthias Keicher

· 1 min read

ResearcharXiv cs.CL

Learning Diagnostic Reasoning for Decision Support in Toxicology

arXiv:2603.29608v2 Announce Type: replace Abstract: Acute poly-substance intoxication requires rapid, life-saving decisions under substantial uncertainty, as clinicians must rely on incomplete ingestion details and nonspecific symptoms. Effective diagnostic reasoning in this chaotic environment requires fusing unstructured, non-medical narratives (e.g. paramedic scene descriptions and unreliable patient self-reports or known histories), with structured medical data like vital signs. While Large Language Models (LLMs) show potential for processing such heterogeneous inputs, they struggle in this setting, often underperforming simple baselines that rely solely on patient histories. To address this, we present DeToxR (Decision-support for Toxicology with Reasoning), the first adaptation of Reinforcement Learning (RL) to emergency toxicology. We design a robust data-fusion engine for multi-label prediction across 14 substance classes based on an LLM finetuned with Group Relative Policy Optimization (GRPO). We optimize the model's reasoning directly using a clinical performance reward. By formulating a multi-label agreement metric as the reward signal, the model is explicitly penalized for missing co-ingested substances and hallucinating absent poisons. Our model significantly outperforms its unadapted base LLM counterpart and supervised baselines. Furthermore, in a preliminary clinical validation study, the model indicates a clinical advantage by achieving higher micro-F1 (0.644 vs 0.473) and recall in identifying the correct poisons. These results demonstrate the potential of RL-aligned LLMs to synthesize unstructured pre-clinical narratives and structured medical data for decision support in high-stakes environments.

Original source

This story was published by arXiv cs.CL and written by Nico Oberl\"ander, David Bani-Harouni, Tobias Zellner, Nassir Navab, Florian Eyer, Matthias Keicher. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News