RAG4Outcome: A Retrieval-Augmented Multimodal Framework for Prognostic Prediction in Chronic Osteomyelitis

• URL: http://arxiv.org/abs/2605.22833v1
• Date: Fri, 24 Apr 2026 19:33:54 GMT
• Title: RAG4Outcome: A Retrieval-Augmented Multimodal Framework for Prognostic Prediction in Chronic Osteomyelitis
• Abstract summary: RAG4Outcome is a retrieval-augmented generation (RAG) framework for prognostic prediction in chronic osteomyelitis.<n>Our method integrates multimodal clinical data, including PET-CT imaging reports, structured surgical and diagnostic records, and unstructured follow-up notes, into a unified prediction pipeline.<n>Preliminary results on real-world cases demonstrate promising effectiveness and clinical alignment.
• Score: 8.12645396241252
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Traditional assessment often relies on manual scoring systems, which limit scalability, efficiency, and consistency in clinical practice. Furthermore, the heterogeneous nature of clinical data poses challenges for current multimodal learning approaches that require aligned inputs and large annotated datasets. In this work, we propose RAG4Outcome, a retrieval-augmented generation (RAG) framework for prognostic prediction in chronic osteomyelitis. Our method integrates multimodal clinical data, including PET-CT imaging reports, structured surgical and diagnostic records, and unstructured follow-up notes, into a unified prediction pipeline. By combining a domain-specific retrieval corpus with expert-guided prompting, the framework enables more interpretable, evidence-grounded, and clinically reliable prognosis. Preliminary results on real-world cases demonstrate promising effectiveness and clinical alignment, highlighting the potential of RAG4Outcome for AI-assisted infection management and postoperative decision support.

Related papers

• Sparse Multi-Stage Expert-Agent Routing for Complex Clinical Reasoning [8.604005197463147]
  We propose Sparse Multi-Stage Expert-Agent, a language-based clinical reasoning framework that models diagnosis as a stage-wise routing process.<n>Given progressively available clinical evidence, the framework maintains an evolving case state and adaptively activates a sparse set of medical expert agents.<n>On reconstructed multi-stage cases from MAC and AgentClinic-NEJM, our framework reduces the average number of activated experts from 17.0 to 3.0 whilst maintaining strong fact-level diagnostic quality.
  arXiv  Detail & Related papers  (2026-08-22T13:23:30Z)
• Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patients [7.355504522142393]
  We propose a multimodal prompt-learning framework for robust clinical prediction under diverse missing-modality scenarios.<n>Generative prompts construct surrogate latent representations for unavailable modalities, while missing-signal prompts distinguish observed representations from generated ones.<n>Our method outperforms existing approaches across evaluation metrics on two missingness settings.
  arXiv  Detail & Related papers  (2026-08-22T12:49:01Z)
• Dysphagia Risk Stratification in Head and Neck Cancer via Two-Stage PRO-Clinical Stacking [13.262516787411487]
  Dysphagia is a debilitating late effect of head and neck cancer (HNC) treatment, yet timely identification of at-risk patients remains challenging.<n>Definitive assessment relies on videofluoroscopic imaging, which requires specialized equipment, trained personnel, and significant patient burden.<n>Patient-reported outcomes (PROs) are low-cost, scalable, and easily collected at any clinical encounter.
  arXiv  Detail & Related papers  (2026-07-24T17:34:26Z)
• OGA-AID: Clinician-in-the-loop AI Report Drafting Assistant for Multimodal Observational Gait Analysis in Post-Stroke Rehabilitation [14.477021243053322]
  We present OGA-AID, a clinician-in-the-loop multi-agent large language model system for multimodal report drafting.<n>The system coordinates 3 specialized agents to synthesize patient movement recordings, kinematic trajectories, and clinical profiles into structured assessments.
  arXiv  Detail & Related papers  (2026-04-07T02:57:29Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC [1.3160173536707265]
  Major pathological response (pR) following neoadjuvant therapy is a clinically meaningful endpoint in non-small cell lung cancer.<n>We propose a multimodal deep learning framework designed to address these constraints by integrating foundation model-based CT feature extraction with a missing-aware architecture for clinical variables.<n>A weighted fusion mechanism is employed to leverage the complementary contributions of imaging and clinical modalities, yielding a multimodal model that consistently outperforms both unimodal imaging and clinical baselines.
  arXiv  Detail & Related papers  (2026-03-16T10:51:52Z)
• MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus [24.19892707167392]
  Existing AI approaches for clinical diagnosis often lack transparency, structured reasoning, and deployability.<n>We propose MedCoRAG, an end-to-end framework that generates diagnostic hypotheses from standardized abnormal findings.<n>It then constructs a patient-specific evidence package by jointly retrieving and pruning UMLS knowledge graph paths and clinical guidelines.
  arXiv  Detail & Related papers  (2026-03-05T12:58:45Z)
• RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis [11.973474883672282]
  We propose RE-MCDF, a relation-enhanced multi-expert clinical diagnosis framework.<n>We show that RE-MCDF consistently outperforms state-of-the-art baselines in complex diagnostic scenarios.
  arXiv  Detail & Related papers  (2026-02-01T15:53:27Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• Multimodal Doctor-in-the-Loop: A Clinically-Guided Explainable Framework for Predicting Pathological Response in Non-Small Cell Lung Cancer [0.7003240413492382]
  This study proposes a novel approach combining Multimodal Deep Learning with intrinsic eXplainable Artificial Intelligence techniques to predict pathological response in non-small cell lung cancer patients undergoing neoadjuvant therapy.<n>Due to the limitations of existing radiomics and unimodal deep learning approaches, we introduce an intermediate fusion strategy that integrates imaging and clinical data, enabling efficient interaction between data modalities.<n>Results demonstrate improved predictive accuracy and explainability, providing insights into optimal data integration strategies for clinical applications.
  arXiv  Detail & Related papers  (2025-05-02T16:57:37Z)
• Automatic diagnosis of knee osteoarthritis severity using Swin transformer [55.01037422579516]
  Knee osteoarthritis (KOA) is a widespread condition that can cause chronic pain and stiffness in the knee joint. We propose an automated approach that employs the Swin Transformer to predict the severity of KOA.
  arXiv  Detail & Related papers  (2023-07-10T09:49:30Z)
• 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)
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response [58.0291320452122]
  This paper aims at a unified deep learning approach to predict patient prognosis and therapy response. We formalize the prognosis modeling as a multi-modal asynchronous time series classification task. Our predictive model could further stratify low-risk and high-risk patients in terms of long-term survival.
  arXiv  Detail & Related papers  (2020-10-08T15:30:17Z)

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.