JMIR mHealth and uHealth

In contrast, Chat GPT-4’s text length and degree of dispersion were closer to those of the medical experts, highlighting its relative strength in generating explanation texts. Text length distribution of the explanations from experts, Chat GPT-4, Chat GPT-3.5, i FLYTEK Spark (Spark), and Ernie Bot (Wenxin). Statistical analysis results for text length.

Dongmei Tan, Yi Huang, Ming Liu, Ziyu Li, Xiaoqian Wu, Cheng Huang

J Med Internet Res 2025;27:e70733

Download Citation: END BibTex RIS

Download PDF Download XML

Developing the MyCancerGene Digital Health Portal to Improve Patients’ Understanding of Germline Cancer Genetic Test Results: Development, User, and Usability Testing Study

Phillip Trieu, Dominique Fetzer, Briana McLeod, Kathryn Schweickert, Lauren Gutstein, Brian Egleston, Susan Domchek, Linda Fleisher, Lynne Wagner, Kuang-Yi Wen, Cara Cacioppo, Jessica E Ebrahimzadeh, Dana Falcone, Claire Langer, Elisabeth Wood, Kelsey Karpink, Shelby Posen, Enida Selmani, Angela R Bradbury

JMIR Form Res 2025;9:e56282

Download Citation: END BibTex RIS

Download PDF Download XML

Stigma Attitudes Toward HIV/AIDS From 2011 Through 2023 in Japan: Retrospective Study in Japan

Yi Piao, Nao Taguchi, Keisuke Harada, Kunihiro Hirahara, Yosuke Takaku, John Austin, KuanYeh Lee, Yui Shiozawa, Yunfei Cheng, Yoji Inoue

J Med Internet Res 2025;27:e69696

Download Citation: END BibTex RIS

Download PDF Download XML

Effects of Digital Sleep Interventions on Sleep Among College Students and Young Adults: Systematic Review and Meta-Analysis

Reference 6: Søvn ogsundhed(https://nfa.elsevierpure.com/en/publications/s%C3%B8vn-og-sundhed)

Yi-An Lu, Hui-Chen Lin, Pei-Shan Tsai

J Med Internet Res 2025;27:e69657

Download Citation: END BibTex RIS

Download PDF Download XML

Large Language Models and Artificial Neural Networks for Assessing 1-Year Mortality in Patients With Myocardial Infarction: Analysis From the Medical Information Mart for Intensive Care IV (MIMIC-IV) Database

While Llama-3’s accuracy might seem impressive, its poor sensitivity and discriminative power (C-index) make it clinically inadequate for mortality prediction. In imbalanced settings, metrics such as C-index, AUROC, and sensitivity are more informative, as they prioritize identifying true positives (deaths) over inflating accuracy through true negatives (survivors).

Boqun Shi, Liangguo Chen, Shuo Pang, Yue Wang, Shen Wang, Fadong Li, Wenxin Zhao, Pengrong Guo, Leli Zhang, Chu Fan, Yi Zou, Xiaofan Wu