MedSumGraph: enhancing GraphRAG for medical QA with summarization and optimized prompts.

BACKGROUND Medical question answering (QA) is essential for various medical applications. While small-scale pre-training language models (PLMs) are widely adopted in open-domain QA tasks through fine-tuning with related datasets, applying this approach in the medical domain requires significant and rigorous integration of external knowledge. Knowledge-enhanced small-scale PLMs have been proposed to incorporate knowledge bases (KBs) to improve performance, as KBs contain vast amounts of factual knowledge. Large language models (LLMs) contain a vast amount of knowledge and have attracted significant research interest due to their outstanding natural language processing (NLP) capabilities. KBs and LLMs can provide external knowledge to enhance small-scale models in medical QA. OBJECTIVE KBs consist of structured factual knowledge that must be converted into sentences to align with the input format of PLMs. However, these converted sentences often lack semantic coherence, potentially causing them to deviate from the intrinsic knowledge of KBs. LLMs, on the other hand, can generate natural, semantically rich sentences, but they may also produce irrelevant or inaccurate statements. Retrieval-augmented generation (RAG) paradigm enhances LLMs by retrieving relevant information from an external database before responding. By integrating LLMs and KBs using the RAG paradigm, it is possible to generate statements that combine the factual knowledge of KBs with the semantic richness of LLMs, thereby enhancing the performance of small-scale models. In this paper, we explore a RAG fine-tuning method, RAG-mQA, that combines KBs and LLMs to improve small-scale models in medical QA. METHODS In the RAG fine-tuning scenario, we adopt medical KBs as an external database to augment the text generation of LLMs, producing statements that integrate medical domain knowledge with semantic knowledge. Specifically, KBs are used to extract medical concepts from the input text, while LLMs are tasked with generating statements based on these extracted concepts. In addition, we introduce two strategies for constructing knowledge: KB-based and LLM-based construction. In the KB-based scenario, we extract medical concepts from the input text using KBs and convert them into sentences by connecting the concepts sequentially. In the LLM-based scenario, we provide the input text to an LLM, which generates relevant statements to answer the question. For downstream QA tasks, the knowledge produced by these three strategies is inserted into the input text to fine-tune a small-scale PLM. F1 and exact match (EM) scores are employed as evaluation metrics for performance comparison. Fine-tuned PLMs without knowledge insertion serve as baselines. Experiments are conducted on two medical QA datasets: emrQA (English) and MedicalQA (Chinese). RESULTS RAG-mQA achieved the best results on both datasets. On the MedicalQA dataset, compared to the KB-based and LLM-based enhancement methods, RAG-mQA improved the F1 score by 0.59% and 2.36%, and the EM score by 2.96% and 11.18%, respectively. On the emrQA dataset, the EM score of RAG-mQA exceeded those of the KB-based and LLM-based methods by 4.65% and 7.01%, respectively. CONCLUSIONS Experimental results demonstrate that RAG fine-tuning method can improve the model performance in medical QA. RAG-mQA achieves greater improvements compared to other knowledge-enhanced methods. CLINICALTRIAL This study does not involve trial registration.

BackgroundPopularized by ChatGPT, large language models (LLMs) are poised to transform the scalability of clinical natural language processing (NLP) downstream tasks such as medical question answering (MQA) and automated data extraction from clinical narrative reports. However, the use of LLMs in the health care setting is limited by cost, computing power, and patient privacy concerns. Specifically, as interest in LLM-based clinical applications grows, regulatory safeguards must be established to avoid exposure of patient data through the public domain. The use of open-source LLMs deployed behind institutional firewalls may ensure the protection of private patient data. In this study, we evaluated the extraction performance of a locally deployed LLM for automated MQA from surgical pathology reports.ObjectiveWe compared the performance of human reviewers and a locally deployed LLM tasked with extracting key histologic and staging information from surgical pathology reports.MethodsA total of 84 thyroid cancer surgical pathology reports were assessed by two independent reviewers and the open-source FastChat-T5 3B-parameter LLM using institutional computing resources. Longer text reports were split into 1200-character-long segments, followed by conversion to embeddings. Three segments with the highest similarity scores were integrated to create the final context for the LLM. The context was then made part of the question it was directed to answer. Twelve medical questions for staging and thyroid cancer recurrence risk data extraction were formulated and answered for each report. The time to respond and concordance of answers were evaluated. The concordance rate for each pairwise comparison (human-LLM and human-human) was calculated as the total number of concordant answers divided by the total number of answers for each of the 12 questions. The average concordance rate and associated error of all questions were tabulated for each pairwise comparison and evaluated with two-sided t tests.ResultsOut of a total of 1008 questions answered, reviewers 1 and 2 had an average (SD) concordance rate of responses of 99% (1%; 999/1008 responses). The LLM was concordant with reviewers 1 and 2 at an overall average (SD) rate of 89% (7%; 896/1008 responses) and 89% (7.2%; 903/1008 responses). The overall time to review and answer questions for all reports was 170.7, 115, and 19.56 minutes for Reviewers 1, 2, and the LLM, respectively.ConclusionsThe locally deployed LLM can be used for MQA with considerable time-saving and acceptable accuracy in responses. Prompt engineering and fine-tuning may further augment automated data extraction from clinical narratives for the provision of real-time, essential clinical insights.

Objective:To enhance the accuracy and reliability of diverse medical question-answering (QA) tasks and investigate efficient approaches deploying the Large Language Models (LLM) technologies, We developed a novel ensemble learning pipeline by utilizing state-of-the-art LLMs, focusing on improving performance on diverse medical QA datasets.Materials and Methods:Our study employs three medical QA datasets: PubMedQA, MedQA-USMLE, and MedMCQA, each presenting unique challenges in biomedical question-answering. The proposed LLM-Synergy framework, focusing exclusively on zero-shot cases using LLMs, incorporates two primary ensemble methods. The first is a Boosting-based weighted majority vote ensemble, where decision-making is expedited and refined by assigning variable weights to different LLMs through a boosting algorithm. The second method is Cluster-based Dynamic Model Selection, which dynamically selects the most suitable LLM votes for each query, based on the characteristics of question contexts, using a clustering approach.Results:The Majority Weighted Vote and Dynamic Model Selection methods demonstrate superior performance compared to individual LLMs across three medical QA datasets. Specifically, the accuracies are 35.84%, 96.21%, and 37.26% for MedMCQA, PubMedQA, and MedQA-USMLE, respectively, with the Majority Weighted Vote. Correspondingly, the Dynamic Model Selection yields slightly higher accuracies of 38.01%, 96.36%, and 38.13%.Conclusion:The LLM-Synergy framework with two ensemble methods, represents a significant advancement in leveraging LLMs for medical QA tasks and provides an innovative way of efficiently utilizing the development with LLM Technologies, customing for both existing and potentially future challenge tasks in biomedical and health informatics research.

e13623 Background: Bone cancer is a complex and challenging disease to diagnose and treat in clinical practice. Recently, generative AI, especially large language models (LLMs), has demonstrated potential as a decision support tool for cancer. However, most implementations have overlooked the integration of available cancer guidelines, such as the NCCN Bone Cancer Guidelines, in fine-tuning the outputs of generative AI models. Incorporating these guidelines into LLMs presents an opportunity to harness the extensive clinical knowledge they contain and improve the decision-support capabilities of the model. Methods: In this study, the aim is to enhance the LLM with cancer clinical guidelines to enable accurate medical decisions and personalized treatment recommendations. Therefore, we introduce a novel method for incorporating the NCCN Bone Cancer Guidelines into LLMs using a Binary Decision Tree (BDT) approach. The approach involves constructing a BDT based on NCCN Bone Cancer Guidelines, where internal nodes represent decision points from the Guidelines, and leaf node signify final treatment suggestions. Then the LLM makes decision at each internal node, considering a given patient's characteristics, and guides toward a treatment recommendation in the leaf node. To assess the efficacy of Guideline-enhanced LLMs, an oncologist from our team created 11 hypothetical osteosarcoma patients’ medical progress notes. Each note contains their demographics, medical history, current illness, physical exams, diagnostic tests. We tested three LLMs in the implementation (GPT-4, GPT-3.5, and PaLM 2) and compared the LLM-generated treatment recommendations with the gold standard treatment across four runs with different random seeds (random seeds is a setting to control the LLM outputs). The results are reported as the average of four runs. The original LLMs are used as baseline methods for comparison. Results: The table below provides a comparison between the performance of original LLMs and those augmented with cancer guidelines for osteosarcoma treatment recommendations. We can observe that the PaLM 2 model demonstrated superior performance compared to its counterparts, underscoring the effectiveness of integrating cancer guidelines into LLMs for decision support. Conclusions: The clinical decision support capabilities of the LLMs are promising when enhanced by NCCN Bone Cancer Guidelines using our approach. To fully exhibit the potential of our proposed method as a clinical decision support tool, further investigation into other subtypes of bone cancer should be conducted in the future study. [Table: see text]

While holding great promise for improving and facilitating healthcare through applications of medical literature summarization, large language models (LLMs) struggle to produce up-to-date responses on evolving topics due to outdated knowledge or hallucination. Retrieval-augmented generation (RAG) is a pivotal innovation that improves the accuracy and relevance of LLM responses by integrating LLMs with a search engine and external sources of knowledge. However, the quality of RAG responses can be largely impacted by the rank and density of key information in the retrieval results, such as the “lost-in-the-middle” problem. In this work, we aim to improve the robustness and reliability of the RAG workflow in the medical domain. Specifically, we propose a map-reduce strategy, BriefContext, to combat the “lost-in-the-middle” issue without modifying the model weights. We demonstrated the advantage of the workflow with various LLM backbones and on multiple QA datasets. This method promises to improve the safety and reliability of LLMs deployed in healthcare domains by reducing the risk of misinformation, ensuring critical clinical content is retained in generated responses, and enabling more trustworthy use of LLMs in critical tasks such as medical question answering, clinical decision support, and patient-facing applications.

Large language models (LLMs) are increasingly adopted in medical question answering (QA) scenarios. However, LLMs have been proven to generate hallucinations and nonfactual information, undermining their trustworthiness in high-stakes medical tasks. Conformal Prediction (CP) is now recognized as a robust framework within the broader domain of machine learning, offering statistically rigorous guarantees of marginal (average) coverage for prediction sets. However, the applicability of CP in medical QA remains to be explored. To address this limitation, this study proposes an enhanced CP framework for medical multiple-choice question answering (MCQA) tasks. The enhanced CP framework associates the non-conformance score with the frequency score of the correct option. The framework generates multiple outputs for the same medical query by leveraging self-consistency theory. The proposed framework calculates the frequency score of each option to address the issue of limited access to the model’s internal information. Furthermore, a risk control framework is incorporated into the enhanced CP framework to manage task-specific metrics through a monotonically decreasing loss function. The enhanced CP framework is evaluated on three popular MCQA datasets using off-the-shelf LLMs. Empirical results demonstrate that the enhanced CP framework achieves user-specified average (or marginal) error rates on the test set. Moreover, the results show that the test set’s average prediction set size (APSS) decreases as the risk level increases. It is concluded that it is a promising evaluation metric for the uncertainty of LLMs.

Background Multidisciplinary tumor boards (MTBs) have been established in most countries to allow experts collaboratively determine the best treatment decisions for cancer patients. However, MTBs often face challenges such as case overload, which can compromise MTB decision quality. Clinical decision support systems (CDSSs) have been introduced to assist clinicians in this process. Despite their potential, CDSSs are still underutilized in routine practice. The emergence of large language models (LLMs), such as ChatGPT, offers new opportunities to improve the efficiency and usability of traditional CDSSs.Objectives OncoDoc2 is a guideline-based CDSS developed using a documentary approach and applied to breast cancer management. This study aims to evaluate the potential of LLMs, used as question-answering (QA) systems, to improve the usability of OncoDoc2 across different prompt engineering techniques (PETs).Methods Data extracted from breast cancer patient summaries (BCPSs), together with questions formulated by OncoDoc2, were used to create prompts for various LLMs, and several PETs were designed and tested. Using a sample of 200 randomized BCPSs, LLMs and PETs were initially compared with regard to their responses to OncoDoc2 questions using classic metrics (accuracy, precision, recall, and F1 score). Best performing LLMs and PETs were further assessed by comparing the therapeutic recommendations generated by OncoDoc2, based on LLM inputs, to those provided by MTB clinicians using OncoDoc2. Finally, the best performing method was validated using a new sample of 30 randomized BCPSs.Results The combination of Mistral and OpenChat models under the enhanced Zero-Shot PET showed the best performance as a question-answering system. This approach gets a precision of 60.16%, a recall of 54.18%, an F1 score of 56.59%, and an accuracy of 75.57% on the validation set of 30 BCPSs. However, this approach yielded poor results as a CDSS, with only 16.67% of the recommendations generated by OncoDoc2 based on LLM inputs matching the gold standard.Conclusion All the criteria in the OncoDoc2 decision tree are crucial for capturing the uniqueness of each patient. Any deviation from a criterion alters the recommendations generated. Despite achieving a good accuracy rate of 75.57%, LLMs still face challenges in reliably understanding complex medical contexts and be effective as CDSSs.

To investigate approaches of reasoning with large language models (LLMs) and to propose a new prompting approach, ensemble reasoning, to improve medical question answering performance with refined reasoning and reduced inconsistency. We used multiple choice questions from the USMLE Sample Exam question files on 2 closed-source commercial and 1 open-source clinical LLM to evaluate our proposed approach ensemble reasoning. On GPT-3.5 turbo and Med42-70B, our proposed ensemble reasoning approach outperformed zero-shot chain-of-thought with self-consistency on Steps 1, 2, and 3 questions (+3.44%, +4.00%, and +2.54%) and (2.3%, 5.00%, and 4.15%), respectively. With GPT-4 turbo, there were mixed results with ensemble reasoning again outperforming zero-shot chain-of-thought with self-consistency on Step 1 questions (+1.15%). In all cases, the results demonstrated improved consistency of responses with our approach. A qualitative analysis of the reasoning from the model demonstrated that the ensemble reasoning approach produces correct and helpful reasoning. The proposed iterative ensemble reasoning has the potential to improve the performance of LLMs in medical question answering tasks, particularly with the less powerful LLMs like GPT-3.5 turbo and Med42-70B, which may suggest that this is a promising approach for LLMs with lower capabilities. Additionally, the findings show that our approach helps to refine the reasoning generated by the LLM and thereby improve consistency even with the more powerful GPT-4 turbo. We also identify the potential and need for human-artificial intelligence teaming to improve the reasoning beyond the limits of the model.

Large Language Models (LLMs) have the potential of facilitating the development of Artificial Intelligence technology to assist medical experts for interactive decision support. This potential has been illustrated by the state-of-the-art performance obtained by LLMs in Medical Question Answering, with striking results such as passing marks in licensing medical exams. However, while impressive, the required quality bar for medical applications remains far from being achieved. Currently, LLMs remain challenged by outdated knowledge and by their tendency to generate hallucinated content. Furthermore, most benchmarks to assess medical knowledge lack reference gold explanations which means that it is not possible to evaluate the reasoning of LLMs predictions. Finally, the situation is particularly grim if we consider benchmarking LLMs for languages other than English which remains, as far as we know, a totally neglected topic. In order to address these shortcomings, in this paper we present MedExpQA, the first multilingual benchmark based on medical exams to evaluate LLMs in Medical Question Answering. To the best of our knowledge, MedExpQA includes for the first time reference gold explanations, written by medical doctors, of the correct and incorrect options in the exams. Comprehensive multilingual experimentation using both the gold reference explanations and Retrieval Augmented Generation (RAG) approaches show that performance of LLMs, with best results around 75 accuracy for English, still has large room for improvement, especially for languages other than English, for which accuracy drops 10 points. Therefore, despite using state-of-the-art RAG methods, our results also demonstrate the difficulty of obtaining and integrating readily available medical knowledge that may positively impact results on downstream evaluations for Medical Question Answering. Data, code, and fine-tuned models will be made publicly available.11https://huggingface.co/datasets/HiTZ/MedExpQA.

Large Language Models (LLMs) have garnered increasing attention in neurosurgery and possess significant potential to improve the field. However, the breadth and performance of LLMs across diverse neurosurgical tasks have not been systematically examined, and LLMs come with their own challenges and unique terminology. We seek to identify key models, establish reporting guidelines for replicability, and highlight progress in key application areas of LLM use in the neurosurgical literature. We searched PubMed and Google Scholar using terms related to LLMs and neurosurgery ("large language model" OR "LLM" OR "ChatGPT" OR "GPT-3" OR "GPT3" OR "GPT-3.5" OR "GPT3.5" OR "GPT-4" OR "GPT4" OR "LLAMA" OR "MISTRAL" OR "BARD") AND "neurosurgery". The final set of articles was reviewed for publication year, application area, specific LLM(s) used, control/comparison groups used to evaluate LLM performance, whether the article reported specific LLM prompts, prompting strategy types used, whether the LLM query could be reproduced in its entirety (including both the prompt used and any adjoining data), measures of hallucination, and reported performance measures. Fifty-one articles met inclusion criteria, and were categorized into six application areas, with the most common being Generation of Text for Direct Clinical Use (n = 14, 27.5%), Answering Standardized Exam Questions (n = 12, 23.5%), and Clinical Judgement and Decision-Making Support (n = 11, 21.6%). The most frequently used LLMs were GPT-3.5 (n = 30, 58.8%), GPT-4 (n = 20, 39.2%), Bard (n = 9, 17.6%), and Bing (n = 6, 11.8%). Most studies (n = 43, 84.3%) used LLMs directly out-of-the-box, while 8 studies (15.7%) conducted advanced pre-training or fine-tuning. Large language models show advanced capabilities in complex tasks and hold potential to transform neurosurgery. However, research typically addresses basic applications and overlooks enhancing LLM performance, facing reproducibility issues. Standardizing detailed reporting, considering LLM stochasticity, and using advanced methods beyond basic validation are essential for progress.

Background/Objectives: Large language models (LLMs) have shown significant potential to transform various aspects of healthcare. This review aims to explore the current applications, challenges, and future prospects of LLMs in medical education, clinical decision support, and healthcare administration. Methods: A comprehensive literature review was conducted, examining the applications of LLMs across the three key domains. The analysis included their performance, challenges, and advancements, with a focus on techniques like retrieval-augmented generation (RAG). Results: In medical education, LLMs show promise as virtual patients, personalized tutors, and tools for generating study materials. Some models have outperformed junior trainees in specific medical knowledge assessments. Concerning clinical decision support, LLMs exhibit potential in diagnostic assistance, treatment recommendations, and medical knowledge retrieval, though performance varies across specialties and tasks. In healthcare administration, LLMs effectively automate tasks like clinical note summarization, data extraction, and report generation, potentially reducing administrative burdens on healthcare professionals. Despite their promise, challenges persist, including hallucination mitigation, addressing biases, and ensuring patient privacy and data security. Conclusions: LLMs have transformative potential in medicine but require careful integration into healthcare settings. Ethical considerations, regulatory challenges, and interdisciplinary collaboration between AI developers and healthcare professionals are essential. Future advancements in LLM performance and reliability through techniques such as RAG, fine-tuning, and reinforcement learning will be critical to ensuring patient safety and improving healthcare delivery.

ChatENT: Augmented Large Language Model for Expert Knowledge Retrieval in Otolaryngology-Head and Neck Surgery.

The rapid growth of biomedical literature poses challenges for manual knowledge curation and synthesis. Biomedical Natural Language Processing (BioNLP) automates the process. While Large Language Models (LLMs) have shown promise in general domains, their effectiveness in BioNLP tasks remains unclear due to limited benchmarks and practical guidelines. We perform a systematic evaluation of four LLMs—GPT and LLaMA representatives—on 12 BioNLP benchmarks across six applications. We compare their zero-shot, few-shot, and fine-tuning performance with the traditional fine-tuning of BERT or BART models. We examine inconsistencies, missing information, hallucinations, and perform cost analysis. Here, we show that traditional fine-tuning outperforms zero- or few-shot LLMs in most tasks. However, closed-source LLMs like GPT-4 excel in reasoning-related tasks such as medical question answering. Open-source LLMs still require fine-tuning to close performance gaps. We find issues like missing information and hallucinations in LLM outputs. These results offer practical insights for applying LLMs in BioNLP.

The integration of large language models (LLMs) into medical diagnostics has garnered substantial attention due to their potential to enhance diagnostic accuracy, streamline clinical workflows, and address health care disparities. However, the rapid evolution of LLM research necessitates a comprehensive synthesis of their applications, challenges, and future directions. This scoping review aimed to provide an overview of the current state of research regarding the use of LLMs in medical diagnostics. The study sought to answer four primary subquestions, as follows: (1) Which LLMs are commonly used? (2) How are LLMs assessed in diagnosis? (3) What is the current performance of LLMs in diagnosing diseases? (4) Which medical domains are investigating the application of LLMs? This scoping review was conducted according to the Joanna Briggs Institute Manual for Evidence Synthesis and adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). Relevant literature was searched from the Web of Science, PubMed, Embase, IEEE Xplore, and ACM Digital Library databases from 2022 to 2025. Articles were screened and selected based on predefined inclusion and exclusion criteria. Bibliometric analysis was performed using VOSviewer to identify major research clusters and trends. Data extraction included details on LLM types, application domains, and performance metrics. The field is rapidly expanding, with a surge in publications after 2023. GPT-4 and its variants dominated research (70/95, 74% of studies), followed by GPT-3.5 (34/95, 36%). Key applications included disease classification (text or image-based), medical question answering, and diagnostic content generation. LLMs demonstrated high accuracy in specialties like radiology, psychiatry, and neurology but exhibited biases in race, gender, and cost predictions. Ethical concerns, including privacy risks and model hallucination, alongside regulatory fragmentation, were critical barriers to clinical adoption. LLMs hold transformative potential for medical diagnostics but require rigorous validation, bias mitigation, and multimodal integration to address real-world complexities. Future research should prioritize explainable artificial intelligence frameworks, specialty-specific optimization, and international regulatory harmonization to ensure equitable and safe clinical deployment.

BACKGROUND The integration of large language models (LLMs) into medical diagnostics has garnered substantial attention due to their potential to enhance diagnostic accuracy, streamline clinical workflows, and address health care disparities. However, the rapid evolution of LLM research necessitates a comprehensive synthesis of their applications, challenges, and future directions. OBJECTIVE This scoping review aimed to provide an overview of the current state of research regarding the use of LLMs in medical diagnostics. The study sought to answer four primary subquestions, as follows: (1) Which LLMs are commonly used? (2) How are LLMs assessed in diagnosis? (3) What is the current performance of LLMs in diagnosing diseases? (4) Which medical domains are investigating the application of LLMs? METHODS This scoping review was conducted according to the Joanna Briggs Institute Manual for Evidence Synthesis and adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). Relevant literature was searched from the Web of Science, PubMed, Embase, IEEE Xplore, and ACM Digital Library databases from 2022 to 2025. Articles were screened and selected based on predefined inclusion and exclusion criteria. Bibliometric analysis was performed using VOSviewer to identify major research clusters and trends. Data extraction included details on LLM types, application domains, and performance metrics. RESULTS The field is rapidly expanding, with a surge in publications after 2023. GPT-4 and its variants dominated research (70/95, 74% of studies), followed by GPT-3.5 (34/95, 36%). Key applications included disease classification (text or image-based), medical question answering, and diagnostic content generation. LLMs demonstrated high accuracy in specialties like radiology, psychiatry, and neurology but exhibited biases in race, gender, and cost predictions. Ethical concerns, including privacy risks and model hallucination, alongside regulatory fragmentation, were critical barriers to clinical adoption. CONCLUSIONS LLMs hold transformative potential for medical diagnostics but require rigorous validation, bias mitigation, and multimodal integration to address real-world complexities. Future research should prioritize explainable artificial intelligence frameworks, specialty-specific optimization, and international regulatory harmonization to ensure equitable and safe clinical deployment.