Search Articles

View query in Help articles search

Search Results (1 to 10 of 316 Results)

Download search results: CSV END BibTex RIS


Enhancing the Accuracy of Human Phenotype Ontology Identification: Comparative Evaluation of Multimodal Large Language Models

Enhancing the Accuracy of Human Phenotype Ontology Identification: Comparative Evaluation of Multimodal Large Language Models

For example, studies using Chat GPT-4o, the latest multimodal version of Chat GPT, have shown high diagnostic accuracy with text and image inputs, outperforming medical students on New England Journal of Medicine Image Challenge cases [32]. However, evaluations of Chat GPT on the Japanese National Medical Licensing Examination highlight ongoing challenges in achieving adequate diagnostic accuracy [33]. Overall, research on applying MLLMs to medical image analysis remains limited [18,33].

Wei Zhong, Mingyue Sun, Shun Yao, YiFan Liu, Dingchuan Peng, Yan Liu, Kai Yang, HuiMin Gao, HuiHui Yan, WenJing Hao, YouSheng Yan, ChengHong Yin

J Med Internet Res 2025;27:e73233

Chatbots’ Role in Generating Single Best Answer Questions for Undergraduate Medical Student Assessment: Comparative Analysis

Chatbots’ Role in Generating Single Best Answer Questions for Undergraduate Medical Student Assessment: Comparative Analysis

A newer, improved version of Chat GPT (Chat GPT Plus), which uses the GPT-4 Turbo language model, has been developed by Open AI and launched as a paid subscription version by the end of 2023 [6] In terms of assessment in medical education, Chat GPT has been the most extensively studied chatbot.

Enjy Abouzeid, Rita Wassef, Ayesha Jawwad, Patricia Harris

JMIR Med Educ 2025;11:e69521

Use of ChatGPT for Urinary Symptom Management Among People With Spinal Cord Injury or Disease: Qualitative Study

Use of ChatGPT for Urinary Symptom Management Among People With Spinal Cord Injury or Disease: Qualitative Study

Chat GPT, along with other large language models, has been increasingly integrated into health information seeking and chronic care contexts, offering decision-making support and patient engagement across a range of conditions [24-26]. Chat GPT has demonstrated potential utility in health care settings, including clinical decision support, patient education, and symptom interpretation [27,28].

Bat-Zion Hose, Amanda K Rounds, Ishaan Nandwani, Deanna-Nicole Busog, Traber Davis Giardina, Helen Haskell, Kelly M Smith, Kristen E Miller

JMIR Rehabil Assist Technol 2025;12:e70339

Exploring the Application Capability of ChatGPT as an Instructor in Skills Education for Dental Medical Students: Randomized Controlled Trial

Exploring the Application Capability of ChatGPT as an Instructor in Skills Education for Dental Medical Students: Randomized Controlled Trial

Research has shown that Chat GPT can assist students in reviewing key concepts, reinforcing theoretical knowledge [1,15], and simulating clinical scenarios to enhance clinical reasoning [16]. This raises the question whether Chat GPT could also serve as an instructor in skills training. We found that the potential of Chat GPT for dental kills education remains unknown.

Siyu Huang, Chang Wen, Xueying Bai, Sihong Li, Shuining Wang, Xiaoxuan Wang, Dong Yang

J Med Internet Res 2025;27:e68538

User Intent to Use DeepSeek for Health Care Purposes and Their Trust in the Large Language Model: Multinational Survey Study

User Intent to Use DeepSeek for Health Care Purposes and Their Trust in the Large Language Model: Multinational Survey Study

Specifically, while prior studies on Chat GPT and similar platforms have begun to shed light on user attitudes, few have examined the human factors by which trust is established—or eroded—when individuals face important decisions about their well-being. In this study, we add to the body of knowledge by focusing on Deep Seek, an open-source LLM that rapidly gained popularity after surpassing other competitors in App Store rankings.

Avishek Choudhury, Yeganeh Shahsavar, Hamid Shamszare

JMIR Hum Factors 2025;12:e72867

Evaluating an AI Chatbot “Prostate Cancer Info” for Providing Quality Prostate Cancer Screening Information: Cross-Sectional Study

Evaluating an AI Chatbot “Prostate Cancer Info” for Providing Quality Prostate Cancer Screening Information: Cross-Sectional Study

Generative artificial intelligence (AI) chatbots such as Chat GPT, Google Gemini, and Microsoft Copilot have become highly publicized for enhancing work efficiency and effectively responding to diverse queries. These sophisticated programs leverage large language models, machine learning, and natural language processing to understand and respond to a query with publicly available or third-party information [1].

Otis L Owens, Michael S Leonard

JMIR Cancer 2025;11:e72522

Comparison of ChatGPT and Internet Research for Clinical Research and Decision-Making in Occupational Medicine: Randomized Controlled Trial

Comparison of ChatGPT and Internet Research for Clinical Research and Decision-Making in Occupational Medicine: Randomized Controlled Trial

View of the Chat GPT group for solving case 2 before (A) and after (B) input. Chat GPT 4 was connected to the input window.. A web-based application with an integrated environment for answering questions, subsequent assignments to a group, and a case view was developed for the study. In addition, an integrated chat window was built into the case view for the Chat GPT cohort. This should look as similar as possible to the Chat GPT user interface. A screenshot can be seen in Figure 2.

Felix A Weuthen, Nelly Otte, Hanif Krabbe, Thomas Kraus, Julia Krabbe

JMIR Form Res 2025;9:e63857

Assessing ChatGPT’s Capability as a New Age Standardized Patient: Qualitative Study

Assessing ChatGPT’s Capability as a New Age Standardized Patient: Qualitative Study

Students were given access to Chat GPT version 4.0 accounts, the most recent available at the time of the study. Students were observed during a live role-play, in which a student inputted a predetermined prompt, provided by the study authors, into Chat GPT. The prompt directed the LLM to present as a patient with a neurological condition (Figure 1). The student, in the role of physician, then interviewed the Chat GPT and attempted to make a differential diagnosis (Figure 2). Prompt used in Chat GPT role-play.

Joseph Cross, Tarron Kayalackakom, Raymond E Robinson, Andrea Vaughans, Roopa Sebastian, Ricardo Hood, Courtney Lewis, Sumanth Devaraju, Prasanna Honnavar, Sheetal Naik, Jillwin Joseph, Nikhilesh Anand, Abdalla Mohammed, Asjah Johnson, Eliran Cohen, Teniola Adeniji, Aisling Nnenna Nnaji, Julia Elizabeth George

JMIR Med Educ 2025;11:e63353

Patient Triage and Guidance in Emergency Departments Using Large Language Models: Multimetric Study

Patient Triage and Guidance in Emergency Departments Using Large Language Models: Multimetric Study

First released to the public in November 2022 by Open AI, Chat GPT represents a significant milestone in making LLMs accessible to the general public. Due to its accuracy and ease of use, applications of Chat GPT in assisting humans have been advantageous.

Chenxu Wang, Fei Wang, Shuhan Li, Qing-wen Ren, Xiaomei Tan, Yaoyu Fu, Di Liu, Guangwu Qian, Yu Cao, Rong Yin, Kang Li

J Med Internet Res 2025;27:e71613

A Practical Guide and Assessment on Using ChatGPT to Conduct Grounded Theory: Tutorial

A Practical Guide and Assessment on Using ChatGPT to Conduct Grounded Theory: Tutorial

Despite these challenges, Chat GPT can frequently adapt to the iterative and reflexive nature of grounded theory coding, even without training datasets [8]. Furthermore, Chat GPT can help explore different perspectives, aiding in theoretical framework development [3]. Nevertheless, there is no recent paper systematically exploring the application and effectiveness of Chat GPT in grounded theory, especially within the Chinese context.

Yongjie Yue, Dong Liu, Yilin Lv, Junyi Hao, Peixuan Cui

J Med Internet Res 2025;27:e70122