Search Articles

View query in Help articles search

Search Results (1 to 10 of 48 Results)

Download search results: CSV END BibTex RIS


Comparative Analysis of Diagnostic Performance: Differential Diagnosis Lists by LLaMA3 Versus LLaMA2 for Case Reports

Comparative Analysis of Diagnostic Performance: Differential Diagnosis Lists by LLaMA3 Versus LLaMA2 for Case Reports

Two expert physicians, T Shiraishi and T Suzuki, independently evaluated the differentials. We adopted a binary approach to evaluate whether the final diagnosis was included in the differential diagnosis lists. When the lists included the final diagnosis, their rankings were also evaluated. To ensure consistency and objectivity in evaluations, any discrepancies between the initial assessments by T Shiraishi and T Suzuki were resolved through a consensus meeting involving a third expert physician, KT.

Takanobu Hirosawa, Yukinori Harada, Kazuki Tokumasu, Tatsuya Shiraishi, Tomoharu Suzuki, Taro Shimizu

JMIR Form Res 2024;8:e64844

Comparative Study to Evaluate the Accuracy of Differential Diagnosis Lists Generated by Gemini Advanced, Gemini, and Bard for a Case Report Series Analysis: Cross-Sectional Study

Comparative Study to Evaluate the Accuracy of Differential Diagnosis Lists Generated by Gemini Advanced, Gemini, and Bard for a Case Report Series Analysis: Cross-Sectional Study

A total of 2 expert researchers (TI and T Suzuki) independently evaluated the differential diagnosis lists from GAI systems. A score of “1” was assigned if the differential accurately and specifically identified the final diagnosis or was sufficiently close to the final diagnosis. Conversely, a score of “0” was assigned if it diverged significantly from the final diagnosis [25]. When a GAI system could not output the differential diagnosis list, a score of “0” was labeled.

Takanobu Hirosawa, Yukinori Harada, Kazuki Tokumasu, Takahiro Ito, Tomoharu Suzuki, Taro Shimizu

JMIR Med Inform 2024;12:e63010