Across a European non-interactive multimorbidity benchmark, an Asian interactive multimorbidity benchmark, and an Asian non-interactive cross-guideline benchmark, ATLAS achieves the strongest complete-decision performance among the compared systems.
Abstract
Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on conditions, medications, and geriatric risks that users may omit. We introduce ATLAS, a coupled graph--policy distillation framework for patient-adaptive medication safety. ATLAS structures guideline evidence as a medication-safety graph. Targeted questions update the patient state and distill relevant relations into a patient-specific medication conflict graph (PMCG). A risk-first multi-agent policy uses the PMCG to screen contraindications, assess cautions and monitoring needs, identify safer alternatives, and verify the final medication plan. We also introduce GeriMedBench, an interactive benchmark that tests safety-critical information acquisition and evidence-based decision revision. Across a European non-interactive multimorbidity benchmark, an Asian interactive multimorbidity benchmark, and an Asian non-interactive cross-guideline benchmark, ATLAS achieves the strongest complete-decision performance among the compared systems. On the European non-interactive multimorbidity benchmark, it exceeds the strongest proprietary LLM baseline by 53.73 points in Strict Success Rate and 14.63 points in overall safety reasoning score (OSRS), with no unsafe recommendations under the automated evaluator. A blinded clinician evaluation gives ATLAS higher mean ratings across all five criteria and flags potentially unsafe recommendations in one ATLAS case and two Gemini cases.
RxGuard is a novel decision-oriented framework that formulates medication combination recommendation as utility maximization under explicit feasibility constraints and improves both recommendation performance and safety, while providing consistent, decision-aligned auditing.
Hang Wang, Hang Dong, Lu Liu· Proceedings of the 32nd ACM...· 0 citations
The evaluation revealed that the integration of LLM-based extraction with a pharmacotherapy knowledge graph enhanced safety-oriented clinical decision support and provided more accurate and traceable answers than traditional RAG.
V. Ryzhenko, Bogdan Burlaka, I. Belenichev et al.· Frontiers in Medicine· 0 citations
These findings support supervised use of large language models and evaluation approaches that assess reasoning and prioritisation as well as target detection and should not be interpreted as evidence that one model is clinically superior in real-world practice.
Kubra Cingar Alpay, D. Ozata, T. Gedik et al.· BMC Geriatrics· 0 citations
Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthcare navigation. We present a multi-agent large language model (LLM) system that identifies multiple intents, maps each to a task-specific agent, executes them in parall...
Hyungjun Kim, Taehan Lee, Soojin Cheon· 0 citations
RTSANet is proposed, which integrates inter-visit drug similarity and external adverse drug reaction information, and captures medication relationships across visits, enhances drug representations with safety-related knowledge, and generates more accurate and safer medication combinations.
Yuan-Yuan Zhang, Zhen-Nuo Wang, Shuang Du et al.· Computer Methods in Biomecha...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.