{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["8(1)"],"submitter":["Yan Y"],"pubmed_abstract":["This retrospective study evaluated the efficacy of large language models (LLMs) in improving the accuracy of Chinese ultrasound reports. Data from three hospitals (January-April 2024) including 400 reports with 243 errors across six categories were analyzed. Three GPT versions and Claude 3.5 Sonnet were tested in zero-shot settings, with the top two models further assessed in few-shot scenarios. Six radiologists of varying experience levels performed error detection on a randomly selected test set. In zero-shot setting, Claude 3.5 Sonnet and GPT-4o achieved the highest error detection rates (52.3% and 41.2%, respectively). In few-shot, Claude 3.5 Sonnet outperformed senior and resident radiologists, while GPT-4o excelled in spelling error detection. LLMs processed reports faster than the q"],"journal":["NPJ digital medicine"],"pagination":["66"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11775253"],"repository":["biostudies-literature"],"pubmed_title":["The use of large language models in detecting Chinese ultrasound report errors."],"pmcid":["PMC11775253"],"pubmed_authors":["Zhou L","Wang VY","Yao J","Zheng Y","Yang J","Xu D","Du Y","Jiang T","Yan Y","Feng B","Zhou Y","Chen C","Jin Z","Wang K","Sui L","Chen X","Pan Q","Liang P"],"additional_accession":[]},"is_claimable":false,"name":"The use of large language models in detecting Chinese ultrasound report errors.","description":"This retrospective study evaluated the efficacy of large language models (LLMs) in improving the accuracy of Chinese ultrasound reports. Data from three hospitals (January-April 2024) including 400 reports with 243 errors across six categories were analyzed. Three GPT versions and Claude 3.5 Sonnet were tested in zero-shot settings, with the top two models further assessed in few-shot scenarios. Six radiologists of varying experience levels performed error detection on a randomly selected test set. In zero-shot setting, Claude 3.5 Sonnet and GPT-4o achieved the highest error detection rates (52.3% and 41.2%, respectively). In few-shot, Claude 3.5 Sonnet outperformed senior and resident radiologists, while GPT-4o excelled in spelling error detection. LLMs processed reports faster than the q","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Jan","modification":"2025-04-03T23:26:40.764Z","creation":"2025-04-03T23:26:40.764Z"},"accession":"S-EPMC11775253","cross_references":{"pubmed":["39875800"],"doi":["10.1038/s41746-025-01468-7"]}}