MedGellan: LLM-Generated Medical Guidance to Support Physicians

2025/07/06 by Debodeep Banerjee, Banerjee, Debodeep, Burcu Sayin +5
Engineering · Medicine · #Advances in Oncology and Radiotherapy #Artificial Intelligence (cs.AI) #Biomedical and Engineering Education #Computation and Language (cs.CL) #FOS: Computer and information sciences #Health and Medical Research Impacts

paper · pdf · doi:10.48550/arxiv.2507.04431

openalex publication_date 2025/07/06 · openalex created_date 2025/10/20 · openalex updated_date 2026/07/28

Abstract

Medical decision-making is a critical task, where errors can result in serious, potentially life-threatening consequences. While full automation remains challenging, hybrid frameworks that combine machine intelligence with human oversight offer a practical alternative. In this paper, we present MedGellan, a lightweight, annotation-free framework that uses a Large Language Model (LLM) to generate clinical guidance from raw medical records, which is then used by a physician to predict diagnoses. MedGellan uses a Bayesian-inspired prompting strategy that respects the temporal order of clinical data. Preliminary experiments show that the guidance generated by the LLM with MedGellan improves diagnostic performance, particularly in recall and F₁ score.

Citations

• Explainable ICD Coding via Entity Linking
• MedCodER: A Generative AI Assistant for Medical Coding
• Guiding IoT-Based Healthcare Alert Systems with Large Language Models
• The Llama 3 Herd of Models
• Gemma 2: Improving Open Language Models at a Practical Size
• Qwen2 Technical Report
• MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
• Exploring LLM Multi-Agents for ICD Coding
• Learning To Guide Human Decision Makers With Vision-Language Models
• Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data
• MedDM:LLM-executable clinical guidance tree for clinical decision-making
• Automated clinical coding using off-the-shelf large language models
• DRG-LLaMA : Tuning LLaMA Model to Predict Diagnosis-related Group for Hospitalized Patients
• ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models
• Designing Closed Human-in-the-loop Deferral Pipelines
• Calibrated Learning to Defer with One-vs-All Classifiers
• Incorporating Uncertainty in Learning to Defer Algorithms for Safe Computer-Aided Diagnosis
• Consistent Estimators for Learning to Defer to an Expert
• Learning to Complement Humans
• Predict Responsibly: Improving Fairness and Accuracy by Learning to\n Defer
• ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge

Related

• Retrieval-Augmented Framework for LLM-Based Clinical Decision Support
• Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review
• A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoning
• Med-R²: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine
• Learning To Guide Human Decision Makers With Vision-Language Models