Background: ChatGPT, a popular new large language model (LLM) built by OpenAI, has shown impressive performance in a number of specialized applications. Despite the rising popularity and performance of AI, studies evaluating the use of LLMs for clinical decision support are lacking.

Purpose: To evaluate ChatGPT's capacity for clinical decision support in radiology via the identification of appropriate imaging services for two important clinical presentations: breast cancer screening and breast pain.

Materials And Methods: We compared ChatGPT's responses to the American College of Radiology (ACR) Appropriateness Criteria for breast pain and breast cancer screening. Our prompt formats included an open-ended (OE) format, where ChatGPT was asked to provide the single most appropriate imaging procedure, and a select all that apply (SATA) format, where ChatGPT was given a list of imaging modalities to assess. Scoring criteria evaluated whether proposed imaging modalities were in accordance with ACR guidelines.

Results: ChatGPT achieved an average OE score of 1.83 (out of 2) and a SATA average percentage correct of 88.9% for breast cancer screening prompts, and an average OE score of 1.125 (out of 2) and a SATA average percentage correct of 58.3% for breast pain prompts.

Conclusion: Our results demonstrate the feasibility of using ChatGPT for radiologic decision making, with the potential to improve clinical workflow and responsible use of radiology services.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9934725PMC
http://dx.doi.org/10.1101/2023.02.02.23285399DOI Listing

Publication Analysis

Top Keywords

breast cancer
12
cancer screening
12
clinical decision
8
decision support
8
appropriate imaging
8
breast pain
8
format chatgpt
8
imaging modalities
8
average score
8
sata average
8

Similar Publications

Management of nausea and vomiting induced by antibody-drug conjugates.

Breast Cancer

January 2025

Advanced Cancer Translational Research Institute, Showa University, 1-5-8 Hatanodai, Shinagawa-ku, Tokyo, 142-8555, Japan.

Antibody-drug conjugates (ADCs) are an emerging class of anticancer therapy that combines the specificity and long circulation half-life of monoclonal antibodies with the cytotoxic potency of the payload connected through a chemical linker. The optimal management of toxicities is crucial for improving quality of life in patients undergoing ADCs and for avoiding improper dose reductions or discontinuations. This article focuses on the characteristics and management of nausea and vomiting (NV) induced by three ADCs: trastuzumab deruxtecan (T-DXd), sacituzumab govitecan (SG), and datopotamab deruxtecan (Dato-DXd).

View Article and Find Full Text PDF

Purpose: Trophoblast cell-surface antigen 2 (Trop2) is overexpressed in various solid tumors and contributes to tumor progression, while its expression remains low in normal tissues. Trop2-targeting antibody-drug conjugate (ADC), sacituzumab govitecan-hziy (Trodelvy), has shown efficacy in targeting this antigen. Leveraging the enhanced specificity of ADCs, we conducted the first immunoPET imaging study of Trop2 expression in gastric cancer (GC) and triple-negative breast cancer (TNBC) models using Zr-labeled Trodelvy ([Zr]Zr-DFO-Trodelvy).

View Article and Find Full Text PDF

Background: Breast carcinoma stands out as the most widespread invasive cancer and the top contributor to cancer-related mortality in women. Nanoparticles have emerged as promising tools in cancer detection, diagnosis, and prevention. In this study, the antitumor and apoptotic capability of silver nanoparticles synthesized through Scrophularia striata extract (AgNPs-SSE) was investigated toward breast cancer cells.

View Article and Find Full Text PDF

SHP2 promotes the epithelial-mesenchymal transition in triple negative breast cancer cells by regulating β-catenin.

J Cancer Res Clin Oncol

January 2025

Key Laboratory of Laboratory Medicine, Ministry of Education of China, School of Laboratory Medicine and Life Sciences, Wenzhou Medical University, Wenzhou, 325035, Zhejiang, China.

Purpose: Growing evidence suggests that the tyrosine phosphatase SHP2 is pivotal for tumor progression. Triple-negative breast cancer (TNBC) is the most lethal subtype of breast cancer, characterized by its high recurrence rate, aggressive metastasis, and resistance to chemotherapy. Understanding the mechanisms of tumorigenesis and the underlying molecular pathways in TNBC could aid in identifying new therapeutic targets.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!