Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes

• URL: http://arxiv.org/abs/2503.12286v1
• Date: Sat, 15 Mar 2025 22:57:31 GMT
• Title: Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes
• Authors: Da Wu, Zhanliang Wang, Quan Nguyen, Kai Wang,
• Abstract summary: We introduce RAG-driven CoT and CoT-driven RAG, two methods that combine Chain-of-Thought (CoT) and Retrieval Augmented Generation (RAG) to analyze clinical notes.<n>We evaluated these approaches on rare disease datasets, including 5,980 Phenopacket-derived notes, 255 literature-based narratives, and 220 in-house clinical notes from Childrens Hospital of Philadelphia.
• Score: 7.772766729052347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Background: Several studies show that large language models (LLMs) struggle with phenotype-driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models like GPT and LLaMA to predict candidate genes. However, in real-world settings, foundation models are not optimized for domain-specific tasks like clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major challenge. Methods: We introduce RAG-driven CoT and CoT-driven RAG, two methods that combine Chain-of-Thought (CoT) and Retrieval Augmented Generation (RAG) to analyze clinical notes. A five-question CoT protocol mimics expert reasoning, while RAG retrieves data from sources like HPO and OMIM (Online Mendelian Inheritance in Man). We evaluated these approaches on rare disease datasets, including 5,980 Phenopacket-derived notes, 255 literature-based narratives, and 220 in-house clinical notes from Childrens Hospital of Philadelphia. Results: We found that recent foundations models, including Llama 3.3-70B-Instruct and DeepSeek-R1-Distill-Llama-70B, outperformed earlier versions such as Llama 2 and GPT-3.5. We also showed that RAG-driven CoT and CoT-driven RAG both outperform foundation models in candidate gene prioritization from clinical notes; in particular, both methods with DeepSeek backbone resulted in a top-10 gene accuracy of over 40% on Phenopacket-derived clinical notes. RAG-driven CoT works better for high-quality notes, where early retrieval can anchor the subsequent reasoning steps in domain-specific evidence, while CoT-driven RAG has advantage when processing lengthy and noisy notes.

Related papers

• Survey and Improvement Strategies for Gene Prioritization with Large Language Models [61.24568051916653]
  Large language models (LLMs) have performed well in medical exams, but their effectiveness in diagnosing rare genetic diseases has not been assessed.<n>We used multi-agent and Human Phenotype Ontology (HPO) classification to categorized patients based on phenotypes and solvability levels.<n>At baseline, GPT-4 outperformed other LLMs, achieving near 30% accuracy in ranking causal genes correctly.
  arXiv  Detail & Related papers  (2025-01-30T23:03:03Z)
• MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models [49.765466293296186]
  Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for interactive diagnostic tools.<n>Med-LVLMs often suffer from factual hallucination, which can lead to incorrect diagnoses.<n>We propose a versatile multimodal RAG system, MMed-RAG, designed to enhance the factuality of Med-LVLMs.
  arXiv  Detail & Related papers  (2024-10-16T23:03:27Z)
• MLC-GCN: Multi-Level Generated Connectome Based GCN for AD Analysis [14.541273450756128]
  Alzheimers Disease (AD) is a currently incurable neurodegeneartive disease. Alzheimer's Disease (AD) is a currently incurable neurodegeneartive disease.
  arXiv  Detail & Related papers  (2024-08-06T14:18:36Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Large Language Models with Retrieval-Augmented Generation for Zero-Shot Disease Phenotyping [1.8630636381951384]
  Large language models (LLMs) offer promise in text understanding but may not efficiently handle real-world clinical documentation. We propose a zero-shot LLM-based method enriched by retrieval-augmented generation and MapReduce. We show that this method as applied to pulmonary hypertension (PH), a rare disease characterized by elevated arterial pressures in the lungs, significantly outperforms physician logic rules.
  arXiv  Detail & Related papers  (2023-12-11T15:45:27Z)
• Histopathologic Cancer Detection [0.0]
  This work uses the PatchCamelyon benchmark datasets and trains them in a multi-layer perceptron and convolution model to observe the model's performance in terms of precision Recall, F1 Score, Accuracy, and AUC Score. Also, this paper introduced ResNet50 and InceptionNet models with data augmentation, where ResNet50 is able to beat the state-of-the-art model.
  arXiv  Detail & Related papers  (2023-11-13T19:51:46Z)
• An evaluation of GPT models for phenotype concept recognition [0.4715973318447338]
  We examine the performance of the latest Generative Pre-trained Transformer (GPT) models for clinical phenotyping and phenotype annotation. Our results show that, with an appropriate setup, these models can achieve state of the art performance.
  arXiv  Detail & Related papers  (2023-09-29T12:06:55Z)
• Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology [57.25098075813054]
  We propose a new framework for gene discovery entitled Un Phenotype Ensembles. It builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations.
  arXiv  Detail & Related papers  (2023-01-07T18:36:44Z)
• Ontology-Driven and Weakly Supervised Rare Disease Identification from Clinical Notes [13.096008602034086]
  Rare diseases are challenging to be identified due to few cases available for machine learning and the need for data annotation from domain experts. We propose a method using brain and weak supervision, with recent pre-trained contextual representations from Bi-directional Transformers (e.g. BERT) The weakly supervised approach is proposed to learn a confirmation phenotype model to improve Text-to-UMLS linking, without annotated data from domain experts.
  arXiv  Detail & Related papers  (2022-05-11T17:38:24Z)
• Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis [50.15205065710629]
  Clinical diagnosis, which aims to assign diagnosis codes for a patient based on the clinical note, plays an essential role in clinical decision-making. We propose a novel framework to combine the inheritance-guided hierarchical assignment and co-occurrence graph propagation for clinical automatic diagnosis.
  arXiv  Detail & Related papers  (2021-01-27T13:16:51Z)
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction [55.94378672172967]
  We focus on few-shot disease subtype prediction problem, identifying subgroups of similar patients. We introduce meta learning techniques to develop a new model, which can extract the common experience or knowledge from interrelated clinical tasks. Our new model is built upon a carefully designed meta-learner, called Prototypical Network, that is a simple yet effective meta learning machine for few-shot image classification.
  arXiv  Detail & Related papers  (2020-09-02T02:50:30Z)

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.