Studies and assessments have shown that large language models (LLMs) like ChatGPT are being evaluated for their capabilities in various medical fields, including radiology and clinical trials. Research indicates that LLMs can provide valuable information and perform tasks such as answering questions and writing medical documents. In particular, ChatGPT-4 has been identified as a top-performing model in clinical text summarization tasks, surpassing the performance of medical experts in certain scenarios.
Sources
Radiology: Artificial IntelligenceProspective exploratory study on ChatGPT’s ability to answer questions from Brazilian Radiology Board exams https://t.co/XO44w79mYH @FelipeKitamura @eduardomjfarina @unifesp #radiology #LargeLanguageModel #AI https://t.co/D57L567bsv
Dennis LalAdapted large language models can outperform medical experts in clinical text summarization https://t.co/9VPnlH1e6C https://t.co/5ai0hxvvgM
- Radiology: Artificial Intelligence
"The #LLM Will See You Now": Performance of #ChatGPT on the Brazilian Radiology and Diagnostic Imaging and Mammography Board Examinations https://t.co/VoWger1zQC @haritrivedimd @judywawira @emoryradiology #AI #ML #MachineLearning https://t.co/Y1h30aiHpo
Additional media
