Dataset Information

Evaluating and Enhancing Large Language Models' Performance in Domain-Specific Medicine: Development and Usability Study With DocOA.

ABSTRACT:

Background

The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored.

Objective

This study focused on evaluating and enhancing the clinical capabilities and explainability of LLMs in specific domains, using OA management as a case study.

Methods

A domain-specific benchmark framework was developed to evaluate LLMs across a spectrum from domain-specific knowledge to clinical applications in real-world clinical scenarios. DocOA, a specialized LLM designed for OA management integrating retrieval-augmented generation and instructional prompts, was developed. It can identify the clinical evidence upon which its answers are based through retrieval-augmented generation, thereby demonstrating the explainability of those answers. The study compared the performance of GPT-3.5, GPT-4, and a specialized assistant, DocOA, using objective and human evaluations.

Results

Results showed that general LLMs such as GPT-3.5 and GPT-4 were less effective in the specialized domain of OA management, particularly in providing personalized treatment recommendations. However, DocOA showed significant improvements.

Conclusions

This study introduces a novel benchmark framework that assesses the domain-specific abilities of LLMs in multiple aspects, highlights the limitations of generalized LLMs in clinical contexts, and demonstrates the potential of tailored approaches for developing domain-specific medical LLMs.

SUBMITTER: Chen X

PROVIDER: S-EPMC11301122 | biostudies-literature | 2024 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluating and Enhancing Large Language Models' Performance in Domain-Specific Medicine: Development and Usability Study With DocOA.

Chen Xi X Wang Li L You MingKe M Liu WeiZhi W Fu Yu Y Xu Jie J Zhang Shaoting S Chen Gang G Li Kang K Li Jian J

Journal of medical Internet research 20240722

<h4>Background</h4>The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored.<h4>Objective</h4>This study focused on evaluating and enhancing the clinical capabilities and explainability of LLMs in specific domains, using OA management as a case study.<h4>Methods</h4>A domain-specific benchmark framework was developed to evaluate LLMs across a spectrum from domain-specific knowledge ...[more]

PMID: 38833165

Similar Datasets

Project description:BackgroundArtificial intelligence (AI) has the potential to dramatically alter healthcare by enhancing how we diagnosis and treat disease. One promising AI model is ChatGPT, a large general-purpose language model trained by OpenAI. The chat interface has shown robust, human-level performance on several professional and academic benchmarks. We sought to probe its performance and stability over time on surgical case questions.MethodsWe evaluated the performance of ChatGPT-4 on two surgical knowledge assessments: the Surgical Council on Resident Education (SCORE) and a second commonly used knowledge assessment, referred to as Data-B. Questions were entered in two formats: open-ended and multiple choice. ChatGPT output were assessed for accuracy and insights by surgeon evaluators. We categorized reasons for model errors and the stability of performance on repeat encounters.ResultsA total of 167 SCORE and 112 Data-B questions were presented to the ChatGPT interface. ChatGPT correctly answered 71% and 68% of multiple-choice SCORE and Data-B questions, respectively. For both open-ended and multiple-choice questions, approximately two-thirds of ChatGPT responses contained non-obvious insights. Common reasons for inaccurate responses included: inaccurate information in a complex question (n=16, 36.4%); inaccurate information in fact-based question (n=11, 25.0%); and accurate information with circumstantial discrepancy (n=6, 13.6%). Upon repeat query, the answer selected by ChatGPT varied for 36.4% of inaccurate questions; the response accuracy changed for 6/16 questions.ConclusionConsistent with prior findings, we demonstrate robust near or above human-level performance of ChatGPT within the surgical domain. Unique to this study, we demonstrate a substantial inconsistency in ChatGPT responses with repeat query. This finding warrants future consideration and presents an opportunity to further train these models to provide safe and consistent responses. Without mental and/or conceptual models, it is unclear whether language models such as ChatGPT would be able to safely assist clinicians in providing care.

Project description:Generative pre-trained transformers (GPT) have recently demonstrated excellent performance in various natural language tasks. The development of ChatGPT and the recently released GPT-4 model has shown competence in solving complex and higher-order reasoning tasks without further training or fine-tuning. However, the applicability and strength of these models in classifying legal texts in the context of argument mining are yet to be realized and have not been tested thoroughly. In this study, we investigate the effectiveness of GPT-like models, specifically GPT-3.5 and GPT-4, for argument mining via prompting. We closely study the model's performance considering diverse prompt formulation and example selection in the prompt via semantic search using state-of-the-art embedding models from OpenAI and sentence transformers. We primarily concentrate on the argument component classification task on the legal corpus from the European Court of Human Rights. To address these models' inherent non-deterministic nature and make our result statistically sound, we conducted 5-fold cross-validation on the test set. Our experiments demonstrate, quite surprisingly, that relatively small domain-specific models outperform GPT 3.5 and GPT-4 in the F1-score for premise and conclusion classes, with 1.9% and 12% improvements, respectively. We hypothesize that the performance drop indirectly reflects the complexity of the structure in the dataset, which we verify through prompt and data analysis. Nevertheless, our results demonstrate a noteworthy variation in the performance of GPT models based on prompt formulation. We observe comparable performance between the two embedding models, with a slight improvement in the local model's ability for prompt selection. This suggests that local models are as semantically rich as the embeddings from the OpenAI model. Our results indicate that the structure of prompts significantly impacts the performance of GPT models and should be considered when designing them.

Project description:BackgroundAdvances in genetics have underscored a strong association between genetic factors and health outcomes, leading to an increased demand for genetic counseling services. However, a shortage of qualified genetic counselors poses a significant challenge. Large language models (LLMs) have emerged as a potential solution for augmenting support in genetic counseling tasks. Despite the potential, Japanese genetic counseling LLMs (JGCLLMs) are underexplored. To advance a JGCLLM-based dialogue system for genetic counseling, effective domain adaptation methods require investigation.ObjectiveThis study aims to evaluate the current capabilities and identify challenges in developing a JGCLLM-based dialogue system for genetic counseling. The primary focus is to assess the effectiveness of prompt engineering, retrieval-augmented generation (RAG), and instruction tuning within the context of genetic counseling. Furthermore, we will establish an experts-evaluated dataset of responses generated by LLMs adapted to Japanese genetic counseling for the future development of JGCLLMs.MethodsTwo primary datasets were used in this study: (1) a question-answer (QA) dataset for LLM adaptation and (2) a genetic counseling question dataset for evaluation. The QA dataset included 899 QA pairs covering medical and genetic counseling topics, while the evaluation dataset contained 120 curated questions across 6 genetic counseling categories. Three enhancement techniques of LLMs-instruction tuning, RAG, and prompt engineering-were applied to a lightweight Japanese LLM to enhance its ability for genetic counseling. The performance of the adapted LLM was evaluated on the 120-question dataset by 2 certified genetic counselors and 1 ophthalmologist (SK, YU, and AY). Evaluation focused on four metrics: (1) inappropriateness of information, (2) sufficiency of information, (3) severity of harm, and (4) alignment with medical consensus.ResultsThe evaluation by certified genetic counselors and an ophthalmologist revealed varied outcomes across different methods. RAG showed potential, particularly in enhancing critical aspects of genetic counseling. In contrast, instruction tuning and prompt engineering produced less favorable outcomes. This evaluation process facilitated the creation an expert-evaluated dataset of responses generated by LLMs adapted with different combinations of these methods. Error analysis identified key ethical concerns, including inappropriate promotion of prenatal testing, criticism of relatives, and inaccurate probability statements.ConclusionsRAG demonstrated notable improvements across all evaluation metrics, suggesting potential for further enhancement through the expansion of RAG data. The expert-evaluated dataset developed in this study provides valuable insights for future optimization efforts. However, the ethical issues observed in JGCLLM responses underscore the critical need for ongoing refinement and thorough ethical evaluation before these systems can be implemented in health care settings.

Dataset Information

Evaluating and Enhancing Large Language Models' Performance in Domain-Specific Medicine: Development and Usability Study With DocOA.

Background

Objective

Methods

Results

Conclusions

Publications

Evaluating and Enhancing Large Language Models' Performance in Domain-Specific Medicine: Development and Usability Study With DocOA.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets