Search Articles

View query in Help articles search

Search Results (1 to 10 of 33 Results)

Download search results: CSV END BibTex RIS


Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis

Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis

However, challenges remain when these models are tested with image-based questions, highlighting a persisting gap between current AI capabilities and the complex demands of radiological diagnostics [26]. While integrating LLMs into medical education and assessments promises transformative changes in how content is delivered and evaluated, there is a risk of excessive reliance on AI.

Boxiong Wei

JMIR Med Educ 2025;11:e64284

Elevated Ambient Temperature Associated With Reduced Infectious Disease Test Positivity Rates: Retrospective Observational Analysis of Statewide COVID-19 Testing and Weather Across California Counties

Elevated Ambient Temperature Associated With Reduced Infectious Disease Test Positivity Rates: Retrospective Observational Analysis of Statewide COVID-19 Testing and Weather Across California Counties

To assess model stability, several diagnostics and post hoc analyses were performed. First, variance inflation factors were computed to assess collinearity between the study variables. Next, a series of model diagnostics were calculated including residual versus predictor plots, a quantile-quantile plot of residuals, an outlier test plot, and a nonparametric dispersion test plot using the standard deviation of fitted and simulated residuals.

Nicholas Wing-Ping Kwok, Joshua Pevnick, Keith Feldman

JMIR Public Health Surveill 2024;10:e57495

Virtual Reality in Clinical Teaching and Diagnostics for Liver Surgery: Prospective Cohort Study

Virtual Reality in Clinical Teaching and Diagnostics for Liver Surgery: Prospective Cohort Study

Especially in areas of surgery and radiology, but also for any medical specialty, an extraordinary level of knowledge of human anatomy, as well as the transfer of what has been learned to the respective patient, is indispensable for the success of diagnostics and therapy [2-4].

Joshua Preibisch, Navid Tabriz, Maximilian Kaluschke, Dirk Weyhe, Verena Uslar

JMIR XR Spatial Comput 2024;1:e60383

Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies Using AI (QUADAS-AI): Protocol for a Qualitative Study

Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies Using AI (QUADAS-AI): Protocol for a Qualitative Study

Indeed, the majority of health care–related AI systems that have reached regulatory approval belong to the field of medical diagnostics [3]. As seminal primary research studies arise on the theme of AI diagnostics [4,5], there has been a concomitant rise in secondary research studies that amalgamate the findings of comparable studies.

Ahmad Guni, Viknesh Sounderajah, Penny Whiting, Patrick Bossuyt, Ara Darzi, Hutan Ashrafian

JMIR Res Protoc 2024;13:e58202

Feasibility of Multimodal Artificial Intelligence Using GPT-4 Vision for the Classification of Middle Ear Disease: Qualitative Study and Validation

Feasibility of Multimodal Artificial Intelligence Using GPT-4 Vision for the Classification of Middle Ear Disease: Qualitative Study and Validation

There have also been advancements in its application, such as implementing smartphone-based point-of-care diagnostics [8]. However, these models rely on trained image data, require large image data sets, and do not consider patient information or clinical context. Consequently, the universality of these models is limited, and their optimal application in clinical practice remains unclear. Recently, large-scale language-processing models have become available for general use.

Masao Noda, Hidekane Yoshimura, Takuya Okubo, Ryota Koshu, Yuki Uchiyama, Akihiro Nomura, Makoto Ito, Yutaka Takumi

JMIR AI 2024;3:e58342