Search Articles

View query in Help articles search

Search Results (1 to 10 of 125 Results)

Download search results: CSV END BibTex RIS


Supervised Natural Language Processing Classification of Violent Death Narratives: Development and Assessment of a Compact Large Language Model

Supervised Natural Language Processing Classification of Violent Death Narratives: Development and Assessment of a Compact Large Language Model

Police and coroner report narratives were combined into a single field in order to use the information available in both narratives (with the exception of the LE narrative–only simulation). Next, the analysis turned to creating simulated data. First, a test set on which the model outputs were to be evaluated was randomly selected. The test set consisted of a random sample of 30% of each outcome’s records, which was then held out from any selection into the training data.

Susan T Parker

JMIR AI 2025;4:e68212

Development of a Serious Game to Simulate Neonatal Intensive Care Unit Experiences: Collaborative Quasi-Experimental Study

Development of a Serious Game to Simulate Neonatal Intensive Care Unit Experiences: Collaborative Quasi-Experimental Study

Overview of the neonatal intensive care unit simulation game stages. (A) High school scene: the protagonist, a high school student, expresses their interest in the neonatal intensive care unit to classmates and prepares a previsit report, setting the foundation for their upcoming hospital experience.

Yukihide Miyosawa, Koichi Hirabayashi, Kodai Yamada, Fumiya Kobayashi, Nanami Ogihara, Noa Takeda, Eri Okamura, Shogo Matsumura

JMIR Form Res 2025;9:e73009

Virtual Simulated Placements in Health Care Education: Scoping Review

Virtual Simulated Placements in Health Care Education: Scoping Review

Simulation-based placements present an alternative to traditional practice placements. In traditional placements, students enter a workplace and learn through observation and participation in actual clinical events. In contrast, health care simulation is a technique that produces a scenario designed to represent a real-life practice situation for experiential learning [5,6].

Juliana Samson, Marc Gilbey, Natasha Taylor, Rosie Kneafsey

JMIR Med Educ 2025;11:e58794

Knowledge Gain and the Impact of Stress in a Fully Immersive Virtual Reality–Based Medical Emergencies Training With Automated Feedback: Randomized Controlled Trial

Knowledge Gain and the Impact of Stress in a Fully Immersive Virtual Reality–Based Medical Emergencies Training With Automated Feedback: Randomized Controlled Trial

Both physiological stress markers can be recorded by wearable sensors (eg, wristbands), causing minimal or no disruption to the simulation [24,25]. To evaluate objectively the learning outcomes of self-moderated VR-based emergency training with automated feedback and simultaneously to gain insight into the impact of different stress dimensions on the learning process, we aimed to answer the following questions.

Marco Lindner, Tobias Leutritz, Joy Backhaus, Sarah König, Tobias Mühling

J Med Internet Res 2025;27:e67412

Mono-Professional Simulation-Based Obstetric Training in a Low-Resource Setting: Stepped-Wedge Cluster Randomized Trial

Mono-Professional Simulation-Based Obstetric Training in a Low-Resource Setting: Stepped-Wedge Cluster Randomized Trial

Additional challenges, such as resource constraints, difficulties in sustaining training programs, staff shortages, and high turnover rates, further hinder the implementation and long-term impact of simulation-based training in sub-Saharan Africa. To overcome these challenges, high-quality research is essential to determine the most effective methodologies for emergency obstetric simulation-based training in sub-Saharan Africa.

Anne A C van Tetering, Ella L de Vries, Peter Ntuyo, E R van den Heuvel, Annemarie F Fransen, M Beatrijs van der Hout-van der Jagt, Imelda Namagembe, Josaphat Byamugisha, S Guid Oei

JMIR Med Educ 2025;11:e54911

Immersive Virtual Reality and AI (Generative Pretrained Transformer) to Enhance Student Preparedness for Objective Structured Clinical Examinations: Mixed Methods Study

Immersive Virtual Reality and AI (Generative Pretrained Transformer) to Enhance Student Preparedness for Objective Structured Clinical Examinations: Mixed Methods Study

This investigation used an improved VR simulation featuring the use of AI, which allowed the virtual patient to provide dynamic responses to student questions. This investigation also included qualitative components—semistructured interviews and focus groups were used to obtain student perspectives regarding their experiences with their first-year coursework and the VR simulation.

Shaniff Esmail, Brendan Concannon

JMIR Serious Games 2025;13:e69428

Impact of a 3-Month Recall Using High-Fidelity Simulation or Screen-Based Simulation on Learning Retention During Neonatal Resuscitation Training for Residents in Anesthesia and Intensive Care: Randomized Controlled Trial

Impact of a 3-Month Recall Using High-Fidelity Simulation or Screen-Based Simulation on Learning Retention During Neonatal Resuscitation Training for Residents in Anesthesia and Intensive Care: Randomized Controlled Trial

The objective of our study is to analyze the retention of knowledge and skills at 6 months after an initial training in neonatal resuscitation for anesthesia and intensive care residents, with or without a 3-month recall training session using either screen-based simulation or high-fidelity (HF) simulation. This randomized controlled simulation study was conducted from February 2021 to November 2021 at the University Hospital of Reims, France.

Anne-Claire Louvel, Cécile Dopff, Gauthier Loron, Daphne Michelet

JMIR Serious Games 2025;13:e57057

Demonstrating Tactical Combat Casualty Care in Simulated Environments to Enable Passive, Autonomous Documentation: Protocol for a Prospective Simulation-Based Study

Demonstrating Tactical Combat Casualty Care in Simulated Environments to Enable Passive, Autonomous Documentation: Protocol for a Prospective Simulation-Based Study

From the beginning of the scenario brief to after action reporting, each participant will be engaged in the study for a maximum of 2.5 hours, where 50 minutes is the maximum amount of time a participant can participate in a simulation run. Autonomous documentation flow diagram from simulation data collection to algorithm development. TATRC: Telemedicine & Advanced Technology Research Center.

Jeanette R Little, Triana Rivera-Nichols, Holly H Pavliscsak, Omar Badawi, James C Gaudaen, Chevas R Yeoman, Todd S Hall, Ethan T Quist, Ericka L Stoor-Burning

JMIR Res Protoc 2025;14:e67673