Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Learning Diagnostic Reasoning for Decision Support in Toxicology

Nico Oberländer, David Bani-Harouni, Tobias Zellner, Nassir Navab, Florian Eyer, Matthias Keicher

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 clinical validation study, the model indicates a clinical advantage by outperforming an expert toxicologist in identifying the correct poisons (Micro-F1: 0.644 vs. 0.473). 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.

Learning Diagnostic Reasoning for Decision Support in Toxicology

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 clinical validation study, the model indicates a clinical advantage by outperforming an expert toxicologist in identifying the correct poisons (Micro-F1: 0.644 vs. 0.473). 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.

Paper Structure

This paper contains 17 sections, 2 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Problem formulation.
  4. Heterogeneous data fusion.
  5. Output schema.
  6. Reinforcement learning finetuning.
  7. Experiments
  8. Experimental setup.
  9. Baselines.
  10. Finetuned models.
  11. Results and Discussion
  12. Performance comparison against other methods.
  13. Performance comparison against a medical expert.
  14. Ablations.
  15. Qualitative reasoning analysis.
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Overview of DeToxR. Heterogeneous emergency-department data is combined and used to prompt an LLM for diagnostic reasoning and multi-label toxin prediction. The model is trained with GRPO using an F1 and format reward.
  • Figure 2: Comparison of the toxicologist against our model on 25 randomly selected test set cases. For each case, the left column is the toxicologist's prediction, and the right one is the prediction of DeToxR.
  • Figure 3: Excerpts from an example reasoning trace. The patient of the underlying case is intoxicated with opiates, benzodiazepines/z-substances and pregabalin, which DeToxR correctly predicts. Claims in green are supported by the provided data or logically sound, while red ones are not supported or wrong.