Search Articles

View query in Help articles search

Search Results (1 to 10 of 2307 Results)

Download search results: CSV END BibTex RIS


Use of Large Language Models to Classify Epidemiological Characteristics in Synthetic and Real-World Social Media Posts About Conjunctivitis Outbreaks: Infodemiology Study

Use of Large Language Models to Classify Epidemiological Characteristics in Synthetic and Real-World Social Media Posts About Conjunctivitis Outbreaks: Infodemiology Study

Cell colors indicate values ranging from 0.0 (red) to 0.5 (yellow) to 1.0 (green). Columns 2 and 3 present the results of LLM validation against the gold standard. With known preclassified values of epidemiological characteristics (severity, etc) in synthetic posts, the LLMs’ abilities to classify these characteristics from these posts’ content were assessed. Columns 4 and 5 present the results of comparative intermodel validations.

Michael S Deiner, Russell Y Deiner, Cherie Fathy, Natalie A Deiner, Vagelis Hristidis, Stephen D McLeod, Thomas J Bukowski, Thuy Doan, Gerami D Seitzman, Thomas M Lietman, Travis C Porco

J Med Internet Res 2025;27:e65226

Enhancing Magnetic Resonance Imaging (MRI) Report Comprehension in Spinal Trauma: Readability Analysis of AI-Generated Explanations for Thoracolumbar Fractures

Enhancing Magnetic Resonance Imaging (MRI) Report Comprehension in Spinal Trauma: Readability Analysis of AI-Generated Explanations for Thoracolumbar Fractures

The MRI report completed by the radiologist can be seen on the left in green, while a GPT-4o–generated, simplified version of the MRI report can be seen on the right in blue. Readability scores (Flesch Readability Ease Score) and reading grade levels (Flesch-Kincaid Grade Level) were determined for each version of the MRI report. AI: artificial intelligence.

David C Sing, Kishan S Shah, Michael Pompliano, Paul H Yi, Calogero Velluto, Ali Bagheri, Robert K Eastlack, Stephen R Stephan, Gregory M Mundis Jr

JMIR AI 2025;4:e69654

Research Dissemination Strategies in Pediatric Emergency Care Using a Professional Twitter (X) Account: A Mixed Methods Developmental Study of a Logic Model Framework

Research Dissemination Strategies in Pediatric Emergency Care Using a Professional Twitter (X) Account: A Mixed Methods Developmental Study of a Logic Model Framework

development (R) Acquisition of external graphics designer (G) Selection of software and metrics (J) Learning to work with existing technologies for scheduling and publishing (AF) Sudden unexpected team member change (U) Outputs Extracting key teaching points from top PECARN articles into tweet (X) Tweet frequency established at the same time each week (3 times per week) (AH) Tweet visual structure: Intentional or strategic polls, emojis, bullet points, and multimedia such as images and videos (AA, AB, AC, C,

Gwendolyn C Hooley, Julia N Magana, Jason M Woods, Shyam Sivasankar, Lauren VonHoltz, Anita R Schmidt, Todd P Chang, Michelle Lin

JMIR Form Res 2025;9:e59481

The Rapid Online Cognitive Assessment for the Detection of Neurocognitive Disorder: Open-Label Study

The Rapid Online Cognitive Assessment for the Detection of Neurocognitive Disorder: Open-Label Study

We first evaluated how Ro CA evaluated patient drawings (Figure 3 A-C). Ro CA classified 97% (44/46) of the cubes correctly, 91% (42/46) of the infinities correctly, and 98% (45/46) of the clocks correctly. We next calculated the accuracy of Ro CA for each drawing individually (Figure 3 D). We compared the accuracy of each drawing to its statistical baseline by bootstrapping, resampling the accuracy, and counting the number of times it fell below the random classifier.

Calvin Howard, Amy Johnson, Joseph Peedicail, Marcus C Ng

J Med Internet Res 2025;27:e66735