SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917546585751552 |
|---|---|
| author | Wang, Xinyu Wu, Hanwei Tai, Zhenghan Lyu, Sicheng Lu, Qincheng Zhao, Ziyu Chi, Jijun Tian, Jingrui Chang, Xiao-Wen Song, Ziyang |
| author_facet | Wang, Xinyu Wu, Hanwei Tai, Zhenghan Lyu, Sicheng Lu, Qincheng Zhao, Ziyu Chi, Jijun Tian, Jingrui Chang, Xiao-Wen Song, Ziyang |
| contents | Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods only predict structured drug codes with limited evidence grounding, while LLM agents can use richer clinical context but may lack safety verification and traceability. At the task level, existing benchmarks often use broad medication categories, which ignore subgroup-level safety differences and can lead to risk overestimation. We introduce the first fine-grained medication recommendation setting based on fourth-level ATC code generation. We propose Safe Prescription Agent (SafeRx-Agent), a knowledge-grounded multi-agent framework that uses patient context, external clinical knowledge, and safety verification to recommend traceable medication sets. Experimental results on MIMIC-III and MIMIC-IV datasets show that SafeRx-Agent improves fine-grained medication prediction accuracy while controlling drug interactions, contraindications, and medication set size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29146 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation Wang, Xinyu Wu, Hanwei Tai, Zhenghan Lyu, Sicheng Lu, Qincheng Zhao, Ziyu Chi, Jijun Tian, Jingrui Chang, Xiao-Wen Song, Ziyang Computation and Language Artificial Intelligence Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods only predict structured drug codes with limited evidence grounding, while LLM agents can use richer clinical context but may lack safety verification and traceability. At the task level, existing benchmarks often use broad medication categories, which ignore subgroup-level safety differences and can lead to risk overestimation. We introduce the first fine-grained medication recommendation setting based on fourth-level ATC code generation. We propose Safe Prescription Agent (SafeRx-Agent), a knowledge-grounded multi-agent framework that uses patient context, external clinical knowledge, and safety verification to recommend traceable medication sets. Experimental results on MIMIC-III and MIMIC-IV datasets show that SafeRx-Agent improves fine-grained medication prediction accuracy while controlling drug interactions, contraindications, and medication set size. |
| title | SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.29146 |