DALL-M: Context-Aware Clinical Data Augmentation with LLMs

2024-07-11

arXiv.org

AI Summary

X-ray diagnosis is often hindered by the absence of structured clinical context. To address this, we propose the first three-stage context-aware synthetic data augmentation framework—comprising *clinical knowledge grounding*, *expert-level query generation*, and *LLM-driven feature synthesis*—which integrates authoritative medical knowledge (e.g., Radiopaedia) to intelligently expand patient vital signs, imaging findings, and demographic attributes. Our method supports both enhancement of existing features and generation of novel, clinically relevant features, ensuring fidelity and interpretability. Evaluated on MIMIC-IV (799 cases), it extends the original 9-dimensional clinical feature space to 91 dimensions, yielding a 16.5% improvement in F1-score and 25% gains in both precision and recall. Integration with downstream models—including TabNET—demonstrates consistent and significant performance gains in diagnostic classification tasks.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

X-ray images are vital in medical diagnostics, but their effectiveness is limited without clinical context. Radiologists often find chest X-rays insufficient for diagnosing underlying diseases, necessitating the integration of structured clinical features with radiology reports. To address this, we introduce DALL-M, a novel framework that enhances clinical datasets by generating contextual synthetic data. DALL-M augments structured patient data, including vital signs (e.g., heart rate, oxygen saturation), radiology findings (e.g., lesion presence), and demographic factors. It integrates this tabular data with contextual knowledge extracted from radiology reports and domain-specific resources (e.g., Radiopaedia, Wikipedia), ensuring clinical consistency and reliability. DALL-M follows a three-phase process: (i) clinical context storage, (ii) expert query generation, and (iii) context-aware feature augmentation. Using large language models (LLMs), it generates both contextual synthetic values for existing clinical features and entirely new, clinically relevant features. Applied to 799 cases from the MIMIC-IV dataset, DALL-M expanded the original 9 clinical features to 91. Empirical validation with machine learning models (including Decision Trees, Random Forests, XGBoost, and TabNET) demonstrated a 16.5% improvement in F1 score and a 25% increase in Precision and Recall. DALL-M bridges an important gap in clinical data augmentation by preserving data integrity while enhancing predictive modeling in healthcare. Our results show that integrating LLM-generated synthetic features significantly improves model performance, making DALL-M a scalable and practical approach for AI-driven medical diagnostics.

Problem

• Enhances clinical datasets with contextual synthetic data
• Integrates structured patient data with radiology reports
• Improves predictive modeling in healthcare diagnostics

Innovation

• DALL-M integrates LLMs for clinical data augmentation.
• Generates synthetic features from radiology reports and resources.
• Improves ML model performance in medical diagnostics.