Search Articles

View query in Help articles search

Search Results (1 to 10 of 6704 Results)

Download search results: CSV END BibTex RIS


Using Large Language Models to Automate Data Extraction From Surgical Pathology Reports: Retrospective Cohort Study

Using Large Language Models to Automate Data Extraction From Surgical Pathology Reports: Retrospective Cohort Study

Large language models (LLMs) power a new generation of natural language processing (NLP) whereby deep neural networks are trained on a massive corpus of human text that are then deconstructed into vectorized embeddings that depict linguistic relationships in a numerical format appropriate for easy analysis [9].

Denise Lee, Akhil Vaid, Kartikeya M Menon, Robert Freeman, David S Matteson, Michael L Marin, Girish N Nadkarni

JMIR Form Res 2025;9:e64544

Identifying Unmet Needs of Informal Dementia Caregivers in Clinical Practice: User-Centered Development of a Digital Assessment Tool

Identifying Unmet Needs of Informal Dementia Caregivers in Clinical Practice: User-Centered Development of a Digital Assessment Tool

In phase 2, the chosen assessment version covering most unmet needs was tested in a memory clinic. A tablet computer was deemed most appropriate to serve as digital device due to its size, weight, flexibility, and ease of handling. Based on a previous study on the use of a tablet-based digital expert system [26,28,30], we had taken several decisions on the hardware basis of our system before the participatory part of our study started.

Olga A Biernetzky, Jochen René Thyrian, Melanie Boekholt, Matthias Berndt, Wolfgang Hoffmann, Stefan J Teipel, Ingo Kilimann

JMIR Aging 2025;8:e59942

Anticipated Acceptability of Blended Learning Among Lay Health Care Workers in Malawi: Qualitative Analysis Guided by the Technology Acceptance Model

Anticipated Acceptability of Blended Learning Among Lay Health Care Workers in Malawi: Qualitative Analysis Guided by the Technology Acceptance Model

Perceived usefulness refers to the belief that a certain technology would increase an individual’s job performance. Perceived ease of use is a belief that the use of the new technology would be effortless [27]. TAM proposes that a populations’ perceptions of usefulness and ease of use of a technology impact the population’s intention to use the technology, which in turn influences the population’s actual usage of the technology.

Tiwonge E Mbeya-Munkhondya, Caroline J Meek, Mtisunge Mphande, Tapiwa A Tembo, Mike J Chitani, Milenka Jean-Baptiste, Caroline Kumbuyo, Dhrutika Vansia, Katherine R Simon, Sarah E Rutstein, Victor Mwapasa, Vivian Go, Maria H Kim, Nora E Rosenberg

JMIR Form Res 2025;9:e62741

A Culturally Tailored Artificial Intelligence Chatbot (K-Bot) to Promote Human Papillomavirus Vaccination Among Korean Americans: Development and Usability Study

A Culturally Tailored Artificial Intelligence Chatbot (K-Bot) to Promote Human Papillomavirus Vaccination Among Korean Americans: Development and Usability Study

Korean Americans are at a relatively high risk for HPV-related cancers, yet they exhibit significant disparities in HPV vaccination rates [6,7]. Notably, Korean American women demonstrate a particularly low intention to receive the HPV vaccine, with only 34.6% expressing a willingness to get the vaccine in prior studies [8].

Minjin Kim, Ellie Kim, Hyeongsuk Lee, Meihua Piao, Brittany Rosen, Jeroan J Allison, Adrian H Zai, Hoa L Nguyen, Dong-Soo Shin, Jessica A Kahn

Asian Pac Isl Nurs J 2025;9:e71865

Electrophysiological Insights in Exergaming—Electroencephalography Data Recording and Movement Artifact Detection: Systematic Review

Electrophysiological Insights in Exergaming—Electroencephalography Data Recording and Movement Artifact Detection: Systematic Review

A “good” rating was assigned when none or just 1 answer was “NO,” indicating minimal risk of bias. A “fair” rating was given when 2 or 3 answers were “NO,” suggesting some potential for bias. Conversely, a “poor” rating was assigned when there was a “NO” answer in 1 of the most important questions, or at least 4 “NO” answers in the less important questions, indicating a significant risk of bias. The final rating for each study was determined by tallying the number of “NO” answers across all questions.

Carolina Rico-Olarte, Diego M Lopez, Bjoern M Eskofier, Linda Becker

JMIR Serious Games 2025;13:e50992

Correction: Stress Reduction in Perioperative Care: Feasibility Randomized Controlled Trial

Correction: Stress Reduction in Perioperative Care: Feasibility Randomized Controlled Trial

In “A Stress Reduction in Perioperative Care: Feasibility Randomized Controlled Trial” (J Med Internet Res 2025;27:e54049) the authors noted one error. Affiliation 2 has been revised from: Adhera Therapeutics (United States), Wake Forest, CA, United States to: Adhera Health Inc, Santa Cruz, CA, United States Additionally, the Conflicts of Interest section has been updated from: IACG, HA, SH-F, and PLG-S are employees of Adhera Therapeutics, which owns the Adhera CARINAE DH Program.

Haridimos Kondylakis, Irene Alice Chicchi Giglioli, Dimitrios Katehakis, Hatice Aldemir, Paul Zikas, George Papagiannakis, Santiago Hors-Fraile, Pedro L González-Sanz, Konstantinos Apostolakis, Constantine Stephanidis, Francisco J Núñez-Benjumea, Rosa M Baños-Rivera, Luis Fernandez-Luque, Angelina Kouroubali

J Med Internet Res 2025;27:e73608

Evaluation of Large Language Models in Tailoring Educational Content for Cancer Survivors and Their Caregivers: Quality Analysis

Evaluation of Large Language Models in Tailoring Educational Content for Cancer Survivors and Their Caregivers: Quality Analysis

The FKG level is a readability test designed to indicate how difficult a text is to understand. It calculates the grade level required for someone to comprehend the text. The FKG is based on word length and sentence length, providing a numerical score that corresponds to US grade levels [42]. The National Institutes of Health (NIH) and the American Medical Association (AMA) suggest that patient education materials should be written at a reading level no higher than the sixth grade [43].

Darren Liu, Xiao Hu, Canhua Xiao, Jinbing Bai, Zahra A Barandouzi, Stephanie Lee, Caitlin Webster, La-Urshalar Brock, Lindsay Lee, Delgersuren Bold, Yufen Lin

JMIR Cancer 2025;11:e67914

Racial Disparities in Parkinson Disease Clinical Phenotype, Management, and Genetics: Protocol for a Prospective Observational Study

Racial Disparities in Parkinson Disease Clinical Phenotype, Management, and Genetics: Protocol for a Prospective Observational Study

Study participants will have a single visit with the site investigator and coordinator after obtaining consent or a hybrid combination of in-person and virtual visits. Recommendations of the NINDS PD CDE Working Group informed the choice of measures, scales, and questionnaires. Data will be collected and entered into a REDCap (Research Electronic Data Capture) system that uses electronic data entry forms.

Deborah A Hall, Josh M Shulman, Andrew Singleton, Sara Bandres Ciga, Michelle Hyczy S Tosin, Bichun Ouyang, Lisa Shulman

JMIR Res Protoc 2025;14:e60587

Health Care Professionals' Engagement With Digital Mental Health Interventions in the United Kingdom and China: Mixed Methods Study on Engagement Factors and Design Implications

Health Care Professionals' Engagement With Digital Mental Health Interventions in the United Kingdom and China: Mixed Methods Study on Engagement Factors and Design Implications

Many recent reviews have shown that low engagement is a ubiquitous problem among DMHIs [17-19]. Plus, user engagement is considerably lower in naturalistic settings than in empirical studies [19-21]. To illustrate this, a review of 59 off-the-shelf mental health apps reported a median uptake rate of 4.0% and a 15-day retention rate of only 3.9% [22].

Zheyuan Zhang, Sijin Sun, Laura Moradbakhti, Andrew Hall, Celine Mougenot, Juan Chen, Rafael A Calvo

JMIR Ment Health 2025;12:e67190

Patient and Clinician Perspectives on Alert-Based Remote Monitoring–First Care for Cardiovascular Implantable Electronic Devices: Semistructured Interview Study Within the Veterans Health Administration

Patient and Clinician Perspectives on Alert-Based Remote Monitoring–First Care for Cardiovascular Implantable Electronic Devices: Semistructured Interview Study Within the Veterans Health Administration

RM involves sending CIED data from a patient’s residence via a transmitter or smartphone app. Routine transmissions are usually sent every 90 days and can also be patient- or alert-initiated. RM is a Class 1, Level of Evidence A, professional society recommendation because of its many clinical outcome benefits [1,2]. These include reduced mortality [3-5], fewer hospitalizations [3,6], fewer inappropriate ICD shocks [7], as well as high patient satisfaction [8].

Allison Kratka, Thomas L Rotering, Scott Munson, Merritt H Raitt, Mary A Whooley, Sanket S Dhruva

JMIR Cardio 2025;9:e66215