Training and Evaluation of Guideline-Based Medical Reasoning in LLMs

• URL: http://arxiv.org/abs/2512.03838v1
• Date: Wed, 03 Dec 2025 14:39:02 GMT
• Title: Training and Evaluation of Guideline-Based Medical Reasoning in LLMs
• Authors: Michael Staniek, Artem Sokolov, Stefan Riezler,
• Abstract summary: Machine learning for early prediction in medicine has recently shown breakthrough performance.<n>The goal of this paper is to teach LLMs to follow medical consensus guidelines step-by-step in their reasoning and prediction process.
• Score: 7.814266948607376
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Machine learning for early prediction in medicine has recently shown breakthrough performance, however, the focus on improving prediction accuracy has led to a neglect of faithful explanations that are required to gain the trust of medical practitioners. The goal of this paper is to teach LLMs to follow medical consensus guidelines step-by-step in their reasoning and prediction process. Since consensus guidelines are ubiquitous in medicine, instantiations of verbalized medical inference rules to electronic health records provide data for fine-tuning LLMs to learn consensus rules and possible exceptions thereof for many medical areas. Consensus rules also enable an automatic evaluation of the model's inference process regarding its derivation correctness (evaluating correct and faithful deduction of a conclusion from given premises) and value correctness (comparing predicted values against real-world measurements). We exemplify our work using the complex Sepsis-3 consensus definition. Our experiments show that small fine-tuned models outperform one-shot learning of considerably larger LLMs that are prompted with the explicit definition and models that are trained on medical texts including consensus definitions. Since fine-tuning on verbalized rule instantiations of a specific medical area yields nearly perfect derivation correctness for rules (and exceptions) on unseen patient data in that area, the bottleneck for early prediction is not out-of-distribution generalization, but the orthogonal problem of generalization into the future by forecasting sparsely and irregularly sampled clinical variables. We show that the latter results can be improved by integrating the output representations of a time series forecasting model with the LLM in a multimodal setup.

Related papers

• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• Will Large Language Models Transform Clinical Prediction? [6.239284099493876]
  Large language models (LLMs) are attracting increasing interest in healthcare.<n>This commentary evaluates the potential of LLMs to improve clinical prediction models (CPMs) for diagnostic and prognostic tasks.
  arXiv  Detail & Related papers  (2025-05-23T17:02:04Z)
• Evaluating Machine Learning Models against Clinical Protocols for Enhanced Interpretability and Continuity of Care [39.58317527488534]
  In clinical practice, decision-making relies heavily on established protocols, often formalised as rules. Despite the growing number of Machine Learning applications, their adoption into clinical practice remains limited. We propose metrics to assess the accuracy of ML models with respect to the established protocol.
  arXiv  Detail & Related papers  (2024-11-05T13:50:09Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning.<n>Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• An Interpretable Deep-Learning Framework for Predicting Hospital Readmissions From Electronic Health Records [1.9185059111021852]
  We propose a novel and interpretable deep learning framework for predicting unplanned hospital readmissions.<n>We validate the framework on two predictive tasks for hospital readmission within 30 and 180 days, using real-world data.<n>Our solution outperforms traditional machine learning models in prediction accuracy while simultaneously providing more interpretable results.
  arXiv  Detail & Related papers  (2023-10-16T08:48:52Z)
• Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study [60.56194508762205]
  We reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. We present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models.
  arXiv  Detail & Related papers  (2023-04-21T11:54:44Z)
• Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes? [53.45585591262433]
  We present an explainable Read, Attend, and Code (xRAC) framework and assess two approaches, attention score-based xRAC-ATTN and model-agnostic knowledge-distillation-based xRAC-KD. We find that the supporting evidence text highlighted by xRAC-ATTN is of higher quality than xRAC-KD whereas xRAC-KD has potential advantages in production deployment scenarios.
  arXiv  Detail & Related papers  (2022-10-28T04:06:07Z)
• Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Sets [0.7734726150561088]
  A lack of statistically rigorous uncertainty quantification is a significant factor undermining trust in AI results. Recent developments in distribution-free uncertainty quantification present practical solutions for these issues. We demonstrate a technique for forming ordinal prediction sets that are guaranteed to contain the correct stenosis severity.
  arXiv  Detail & Related papers  (2022-07-05T18:01:20Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.