Search Articles

View query in Help articles search

Search Results (1 to 10 of 522 Results)

Download search results: CSV END BibTex RIS


Daily Automated Prediction of Delirium Risk in Hospitalized Patients: Model Development and Validation

Daily Automated Prediction of Delirium Risk in Hospitalized Patients: Model Development and Validation

Reference 30: From local explanations to global understanding with explainable AI for trees chasm from model performance to clinical impact: the need to improve implementation and evaluation of AIai

Kendrick Matthew Shaw, Yu-Ping Shao, Manohar Ghanta, Valdery Moura Junior, Eyal Y Kimchi, Timothy T Houle, Oluwaseun Akeju, Michael Brandon Westover

JMIR Med Inform 2025;13:e60442

Effect of Uncertainty-Aware AI Models on Pharmacists’ Reaction Time and Decision-Making in a Web-Based Mock Medication Verification Task: Randomized Controlled Trial

Effect of Uncertainty-Aware AI Models on Pharmacists’ Reaction Time and Decision-Making in a Web-Based Mock Medication Verification Task: Randomized Controlled Trial

Each AI condition consisted of 100 trials with 76 trials containing correctly filled medications and 24 trials containing misfilled medications. For the correctly filled medications, the AI accurately recommended accepting (AI Accept) in 60 trials and erroneously recommended rejecting (AI Reject) in 16 trials. For the 24 trials containing misfilled medications, the AI accurately recommended AI Reject for 22 trials and erroneously recommended AI Accept for 2 trials.

Corey Lester, Brigid Rowell, Yifan Zheng, Zoe Co, Vincent Marshall, Jin Yong Kim, Qiyuan Chen, Raed Kontar, X Jessie Yang

JMIR Med Inform 2025;13:e64902

Development of a GPT-4–Powered Virtual Simulated Patient and Communication Training Platform for Medical Students to Practice Discussing Abnormal Mammogram Results With Patients: Multiphase Study

Development of a GPT-4–Powered Virtual Simulated Patient and Communication Training Platform for Medical Students to Practice Discussing Abnormal Mammogram Results With Patients: Multiphase Study

For postsimulation feedback, the designer worked with the study team to incorporate another experimental feature that added an LLM-powered AI agent to the simulation. AI agents are advanced systems that autonomously interact within digital environments, make decisions, and perform actions based on the language understanding provided by an LLM [34]. Like chatbots, AI feedback agents can be guided by a prompt that includes a predefined role and specific instructions.

Dan Weisman, Alanna Sugarman, Yue Ming Huang, Lillian Gelberg, Patricia A Ganz, Warren Scott Comulada

JMIR Form Res 2025;9:e65670

Application of an Innovative Methodology to Build Infrastructure for Digital Transformation of Health Systems: Developmental Program Evaluation

Application of an Innovative Methodology to Build Infrastructure for Digital Transformation of Health Systems: Developmental Program Evaluation

More importantly, such platforms, particularly with the incorporation of artificial intelligence (AI) and machine learning, can enable precision prediction of health outcomes [23,24] as well as rapid responses to help monitor, mitigate, and manage existing and emerging health crises [6,25].

M Claire Buchan, Tarun Reddy Katapally, Jasmin Bhawra

JMIR Form Res 2025;9:e53339

Effectiveness of The Umbrella Collaboration Versus Traditional Umbrella Reviews for Evidence Synthesis in Health Care: Protocol for a Validation Study

Effectiveness of The Umbrella Collaboration Versus Traditional Umbrella Reviews for Evidence Synthesis in Health Care: Protocol for a Validation Study

Despite these developments in secondary synthesis, the application of AI and software engineering in tertiary synthesis is still in its early stages, with no dedicated software currently available. TU is at the forefront of this field, pioneering the integration of AI and software engineering with human oversight to ensure accuracy and minimize technology-induced errors.

Beltran Carrillo, Marta Rubinos-Cuadrado, Jazmin Parellada-Martin, Alejandra Palacios-López, Beltran Carrillo-Rubinos, Fernando Canillas-Del Rey, Juan Jose Baztán-Cortes, Javier Gómez-Pavon

JMIR Res Protoc 2025;14:e67248