Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4

• URL: http://arxiv.org/abs/2402.10083v1
• Date: Thu, 15 Feb 2024 16:43:41 GMT
• Title: Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4
• Authors: Ting Fang Tan, Kabilan Elangovan, Liyuan Jin, Yao Jie, Li Yong, Joshua Lim, Stanley Poh, Wei Yan Ng, Daniel Lim, Yuhe Ke, Nan Liu, Daniel Shu Wei Ting
• Abstract summary: 400 ophthalmology questions and paired answers were created by ophthalmologists to represent commonly asked patient questions. We find-tuned 5 different LLMs, including LLAMA2-7b, LLAMA2-7b-Chat, LLAMA2-13b, and LLAMA2-13b-Chat. A customized clinical evaluation was used to guide GPT-4 evaluation, grounded on clinical accuracy, relevance, patient safety, and ease of understanding.
• Score: 2.3715885775680925
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Purpose: To assess the alignment of GPT-4-based evaluation to human clinician experts, for the evaluation of responses to ophthalmology-related patient queries generated by fine-tuned LLM chatbots. Methods: 400 ophthalmology questions and paired answers were created by ophthalmologists to represent commonly asked patient questions, divided into fine-tuning (368; 92%), and testing (40; 8%). We find-tuned 5 different LLMs, including LLAMA2-7b, LLAMA2-7b-Chat, LLAMA2-13b, and LLAMA2-13b-Chat. For the testing dataset, additional 8 glaucoma QnA pairs were included. 200 responses to the testing dataset were generated by 5 fine-tuned LLMs for evaluation. A customized clinical evaluation rubric was used to guide GPT-4 evaluation, grounded on clinical accuracy, relevance, patient safety, and ease of understanding. GPT-4 evaluation was then compared against ranking by 5 clinicians for clinical alignment. Results: Among all fine-tuned LLMs, GPT-3.5 scored the highest (87.1%), followed by LLAMA2-13b (80.9%), LLAMA2-13b-chat (75.5%), LLAMA2-7b-Chat (70%) and LLAMA2-7b (68.8%) based on the GPT-4 evaluation. GPT-4 evaluation demonstrated significant agreement with human clinician rankings, with Spearman and Kendall Tau correlation coefficients of 0.90 and 0.80 respectively; while correlation based on Cohen Kappa was more modest at 0.50. Notably, qualitative analysis and the glaucoma sub-analysis revealed clinical inaccuracies in the LLM-generated responses, which were appropriately identified by the GPT-4 evaluation. Conclusion: The notable clinical alignment of GPT-4 evaluation highlighted its potential to streamline the clinical evaluation of LLM chatbot responses to healthcare-related queries. By complementing the existing clinician-dependent manual grading, this efficient and automated evaluation could assist the validation of future developments in LLM applications for healthcare.

Related papers

• CLUE: A Clinical Language Understanding Evaluation for LLMs [2.3814275542331385]
  Large Language Models (LLMs) are expected to significantly contribute to patient care, diagnostics, and administrative processes. Assessing the models' suitability for this sensitive application area is of utmost importance. We present the Clinical Language Understanding Evaluation (CLUE), a benchmark tailored to evaluate LLMs on clinical tasks.
  arXiv  Detail & Related papers  (2024-04-05T12:51:37Z)
• EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries [9.031182965159976]
  Large Language Models (LLMs) show promise in efficiently analyzing vast and complex data. We introduce EHRNoteQA, a novel benchmark built on the MIMIC-IV EHR, comprising 962 different QA pairs each linked to distinct patients' discharge summaries. EHRNoteQA includes questions that require information across multiple discharge summaries and covers eight diverse topics, mirroring the complexity and diversity of real clinical inquiries.
  arXiv  Detail & Related papers  (2024-02-25T09:41:50Z)
• Quality of Answers of Generative Large Language Models vs Peer Patients for Interpreting Lab Test Results for Lay Patients: Evaluation Study [5.823006266363981]
  Large language models (LLMs) have opened a promising avenue for patients to get their questions answered. We generated responses to 53 questions from four LLMs including GPT-4, Meta LLaMA 2, MedAlpaca, and ORCA_mini. We find that GPT-4's responses are more accurate, helpful, relevant, and safer.
  arXiv  Detail & Related papers  (2024-01-23T22:03:51Z)
• Impact of Large Language Model Assistance on Patients Reading Clinical Notes: A Mixed-Methods Study [47.61555826813361]
  Complex medical concepts and jargon within clinical notes hinder patient comprehension and may lead to anxiety. We developed a patient-facing tool to simplify, extract information from, and add context to notes. Augmentations were evaluated for errors by clinicians, and we found misleading errors occur.
  arXiv  Detail & Related papers  (2024-01-17T23:14:52Z)
• Large Language Models in Medical Term Classification and Unexpected Misalignment Between Response and Reasoning [28.355000184014084]
  This study assesses the ability of state-of-the-art large language models (LLMs) to identify patients with mild cognitive impairment (MCI) from discharge summaries. The data was partitioned into training, validation, and testing sets in a 7:2:1 ratio for model fine-tuning and evaluation. Open-source models like Falcon and LLaMA 2 achieved high accuracy but lacked explanatory reasoning.
  arXiv  Detail & Related papers  (2023-12-19T17:36:48Z)
• A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis [87.25494411021066]
  GPT-4V's multimodal capability for medical image analysis is evaluated. It is found that GPT-4V excels in understanding medical images and generates high-quality radiology reports. It is found that its performance for medical visual grounding needs to be substantially improved.
  arXiv  Detail & Related papers  (2023-10-31T11:39:09Z)
• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models [66.12432440863816]
  We propose Prometheus, a fully open-source Large Language Model (LLM) that is on par with GPT-4's evaluation capabilities. Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics. Prometheus achieves the highest accuracy on two human preference benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:50:08Z)
• MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records [60.35217378132709]
  Large language models (LLMs) can follow natural language instructions with human-level fluency. evaluating LLMs on realistic text generation tasks for healthcare remains challenging. We introduce MedAlign, a benchmark dataset of 983 natural language instructions for EHR data.
  arXiv  Detail & Related papers  (2023-08-27T12:24:39Z)
• Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries [48.48630043740588]
  Large Language Models (LLMs) such as ChatGPT and Med-PaLM have excelled in various medical question-answering tasks. We develop a novel in-context learning framework to enhance their performance.
  arXiv  Detail & Related papers  (2023-05-17T12:31:26Z)
• Improving Patient Pre-screening for Clinical Trials: Assisting Physicians with Large Language Models [0.0]
  Large Language Models (LLMs) have shown to perform well for clinical information extraction and clinical reasoning. This paper investigates the use of InstructGPT to assist physicians in determining eligibility for clinical trials based on a patient's summarised medical profile.
  arXiv  Detail & Related papers  (2023-04-14T21:19:46Z)
• Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation [56.25869366777579]
  In recent years, machine learning models have rapidly become better at generating clinical consultation notes. We present an extensive human evaluation study where 5 clinicians listen to 57 mock consultations, write their own notes, post-edit a number of automatically generated notes, and extract all the errors. We find that a simple, character-based Levenshtein distance metric performs on par if not better than common model-based metrics like BertScore.
  arXiv  Detail & Related papers  (2022-04-01T14:04:16Z)

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.