Abstract
Structured AbstractImportanceLarge language models (LLMs) have proven useful for extracting data from publicly available sources, but their uses in clinical settings and with clinical data are unknown.ObjectiveTo determine the accuracy of data extraction using “Versa Chat,” a chat implementation of the general-purpose OpenAI gpt-35-turbo LLM model, versus manual chart review for hepatocellular carcinoma (HCC) imaging reports.DesignWe engineered a prompt for the data extraction task of six distinct data elements and input 182 abdominal imaging reports that were also manually tagged. We evaluated performance by calculating accuracy, precision, recall, and F1 scores.Setting/ParticipantsCross-sectional abdominal imaging reports of patients diagnosed with hepatocellular carcinoma enrolled in the Functional Assessment in Liver Transplantation (FrAILT) study.
Publisher
Cold Spring Harbor Laboratory
Reference12 articles.
1. Artificial intelligence-based text generators in hepatology: ChatGPT is just the beginning
2. Large language models encode clinical knowledge
3. Liver Imaging Reporting and Data System (LI-RADS) Version 2018: Imaging of Hepatocellular Carcinoma in At-Risk Patients
4. Azure OpenAI Service – Large Language Models for Generative AI. https://azure.microsoft.com/en-us/products/ai-services/openai-service-b. Accessed August 25, 2023.
5. Azure OpenAI Service models - Azure OpenAI | Microsoft Learn. https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models. Accessed August 26, 2023.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献