October 1, 2024

Testing the Ability and Limitations of ChatGPT to Generate Differential Diagnoses from Transcribed Radiologic Findings

Key Points

Key points are not available for this paper at this time.

Abstract

ChatGPT (GPT-3.5 and GPT-4; OpenAI) produced accurate diagnoses from transcribed radiologic findings for a majority of cases; however, hallucinations and repeatability issues were present.

AI에게 질문

Bookmark

Cite This Study

Sun et al. (Tue,) studied this question.

synapsesocial.com/papers/6a0b41984a081dac3aacabd6 https://doi.org/https://doi.org/10.1148/radiol.232346

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Top 3 Differentials in Nuclear Medicine2019 · 1 citations
2Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge2023 · 427 citations
3Top 3 Differentials in Gastrointestinal Imaging2019 · 1 citations
4Evaluation of Large Language Model Performance and Reliability for Citations and References in Scholarly Writing: Cross-Disciplinary Study2024 · 54 citations
5Artificial Intelligence-Based Differential Diagnosis: Development and Validation of a Probabilistic Model to Address Lack of Large-Scale Clinical Datasets2020 · 35 citations

AI에게 질문

Bookmark