Search Articles

View query in Help articles search
e.g. John Smith or 0000-0001-6479-5330

Search Results (1 to 10 of 1177 Results)

Download search results: CSV END BibTex RIS

Evaluation and Bias Analysis of Large Language Models in Generating Synthetic Electronic Health Records: Comparative Study

Evaluation and Bias Analysis of Large Language Models in Generating Synthetic Electronic Health Records: Comparative Study

Similarly, the Yi-6 B model had a relatively high MMLU score of 64.11 but an EPS of only 77.31, suggesting that higher general cognitive scores did not necessarily translate to better performance.

Ruochen Huang, Honghan Wu, Yuhan Yuan, Yifan Xu, Hao Qian, Changwei Zhang, Xin Wei, Shan Lu, Xin Zhang, Jingbao Kan, Cheng Wan, Yun Liu

J Med Internet Res 2025;27:e65317

Download Citation: END BibTex RIS

Download PDF Download XML

Diagnosis of Sarcopenia Using Convolutional Neural Network Models Based on Muscle Ultrasound Images: Prospective Multicenter Study

Diagnosis of Sarcopenia Using Convolutional Neural Network Models Based on Muscle Ultrasound Images: Prospective Multicenter Study

Yi et al [31] used three CNNs (VGG19, Res Net50, and Dense Net121) for predicting sarcopenia, achieving accuracies of 0.65-0.75 (based on grayscale ultrasound images) and 0.70-0.80 (based on shear-wave elastography images). Their study primarily focused on assessing the applicability of different CNNs for predicting sarcopenia based on ultrasound images. In this study, we compared three networks and selected the superior-performing Conv Ne Xt.

Zi-Tong Chen, Xiao-Long Li, Feng-Shan Jin, Yi-Lei Shi, Lei Zhang, Hao-Hao Yin, Yu-Li Zhu, Xin-Yi Tang, Xi-Yuan Lin, Bei-Lei Lu, Qun Wang, Li-Ping Sun, Xiao-Xiang Zhu, Li Qiu, Hui-Xiong Xu, Le-Hang Guo

J Med Internet Res 2025;27:e70545

Download Citation: END BibTex RIS

Download PDF Download XML