Search Articles

View query in Help articles search

Search Results (1 to 10 of 8328 Results)

Download search results: CSV END BibTex RIS


To Implement or Not to Implement? A Commentary on the Pitfalls of Judging the Value and Risks of Personalized Prognostic Statistical Models

To Implement or Not to Implement? A Commentary on the Pitfalls of Judging the Value and Risks of Personalized Prognostic Statistical Models

If the patient would have participated in the treatment but did not do so due to a personalized outcome prediction of increasing pain, this could be beneficial to them if they would not benefit from the treatment. However, it could also be harmful if the patient would have benefited and does not experience pain relief due to their decision to not participate in the treatment because of a false-negative personalized outcome prediction (node E7).

Linda Baumbach, Walter Hötzendorfer, Jan Baumbach

J Med Internet Res 2025;27:e69341


Benchmarking the Confidence of Large Language Models in Answering Clinical Questions: Cross-Sectional Evaluation Study

Benchmarking the Confidence of Large Language Models in Answering Clinical Questions: Cross-Sectional Evaluation Study

The prompts were carefully designed to modify only the writing style, without altering any clinical details, such as medical terms, laboratory values, or answer choices [25]. This approach aimed to preserve all clinical details, ensuring that rephrased questions stayed faithful to the original intent and information. To confirm this, 2 board-certified physicians separately reviewed a 20% random sample of questions from each specialty.

Mahmud Omar, Reem Agbareia, Benjamin S Glicksberg, Girish N Nadkarni, Eyal Klang

JMIR Med Inform 2025;13:e66917


Online Group–Based Dual-Task Training to Improve Cognitive Function of Community-Dwelling Older Adults: Randomized Controlled Feasibility Study

Online Group–Based Dual-Task Training to Improve Cognitive Function of Community-Dwelling Older Adults: Randomized Controlled Feasibility Study

Dual-task training has been widely applied among populations with clinical conditions, such as stroke, Parkinson disease, and cognitive impairment. A systematic review of 13 randomized controlled trials (RCTs) on stroke survivors reported that dual-task training could improve walking and balance function [8]. A recent meta-analysis of 14 RCTs estimated a small-to-moderate effect in improving cognitive function among stroke survivors [9].

Pui Hing Chau, Denise Shuk Ting Cheung, Jojo Yan Yan Kwok, Wai Chi Chan, Doris Sau Fung Yu

JMIR Aging 2025;8:e67267


Patient Triage and Guidance in Emergency Departments Using Large Language Models: Multimetric Study

Patient Triage and Guidance in Emergency Departments Using Large Language Models: Multimetric Study

In recent years, research on LLM applications has expanded significantly, ranging from basic sentence prediction to aiding human decision-making. The potential of LLMs is being increasingly realized with the continuing advancement of artificial intelligence (AI). First released to the public in November 2022 by Open AI, Chat GPT represents a significant milestone in making LLMs accessible to the general public.

Chenxu Wang, Fei Wang, Shuhan Li, Qing-wen Ren, Xiaomei Tan, Yaoyu Fu, Di Liu, Guangwu Qian, Yu Cao, Rong Yin, Kang Li

J Med Internet Res 2025;27:e71613


Parents’ Motivations for Calling an Out-of-Hours Helpline: Qualitative Study

Parents’ Motivations for Calling an Out-of-Hours Helpline: Qualitative Study

Nighttime triggered anxiety as parents felt ill-equipped to assess a tired child and, consequently, could not rule out severe illness. Mothers and fathers did not differ meaningfully in what made them worry, but a few fathers highlighted that it was typically the mother who took charge when the child went ill. Q5: I know that 1000 different things can cause fever. Luckily, 950 of them are harmless. But when I am uncertain about the doctor’s advice, I know that no one has been wrong so far. I want control.

Liv Borch-Johnsen, Fredrik Folke, Marianne Sjølin Frederiksen, Morten Schrøder, Gorm Greisen, Stine Lund, Vibeke Zoffmann, Caroline Gren, Tine Tjørnhøj-Thomsen, Dina Cortes

J Med Internet Res 2025;27:e66780


Identification of Target Body Composition Parameters by Dual-Energy X-Ray Absorptiometry, Bioelectrical Impedance, and Ultrasonography to Detect Older Adults With Frailty and Prefrailty Status Using a Mobile App in Primary Care Services: Descriptive Cross-Sectional Study

Identification of Target Body Composition Parameters by Dual-Energy X-Ray Absorptiometry, Bioelectrical Impedance, and Ultrasonography to Detect Older Adults With Frailty and Prefrailty Status Using a Mobile App in Primary Care Services: Descriptive Cross-Sectional Study

The whole-body phase angle (WBPh A), obtained through BIA, serves as an indicator of cellular health and nutritional status, with lower values associated with increased frailty and poorer clinical outcomes [11,12]. Similarly, muscle US offers a noninvasive way to assess muscle thickness and quality, aiding in the detection of sarcopenia and frailty [13].

Beatriz Ortiz-Navarro, José Losa-Reyna, Veronica Mihaiescu-Ion, Jerónimo Garcia-Romero, Margarita Carrillo de Albornoz-Gil, Alejandro Galán-Mercant

JMIR Aging 2025;8:e67982


Extracting Multifaceted Characteristics of Patients With Chronic Disease Comorbidity: Framework Development Using Large Language Models

Extracting Multifaceted Characteristics of Patients With Chronic Disease Comorbidity: Framework Development Using Large Language Models

Major research directions include exploring multimorbidity patterns [2,3], investigating multimorbidity development and prediction [4,5], and examining the mutual interplay between multimorbidity and patient characteristics [6]. Amid ongoing research on frequently occurring diseases, extracting patient characteristics holds paramount importance.

Junyan Zhang, Junchen Zhou, Liqin Zhou, Zhichao Ba

JMIR Med Inform 2025;13:e70096


AI-Assisted Hypothesis Generation to Address Challenges in Cardiotoxicity Research: Simulation Study Using ChatGPT With GPT-4o

AI-Assisted Hypothesis Generation to Address Challenges in Cardiotoxicity Research: Simulation Study Using ChatGPT With GPT-4o

Unlike mathematical or purely theoretical investigations, biomedical hypothesis testing requires experimental validation, which introduces additional challenges such as feasibility, clinical relevance, and ethical considerations. Accordingly, this study investigates whether Chat GPT with GPT-4o can generate hypotheses to address challenges in cardiotoxicity research and whether the hypotheses are novel and potentially able to impact research and clinical applications in heart disease treatment.

Yilan Li, Tianshu Gu, Chengyuan Yang, Minghui Li, Congyi Wang, Lan Yao, Weikuan Gu, DianJun Sun

J Med Internet Res 2025;27:e66161


Jaw Bone Density in Chronic Areca Nut Chewers and Nonchewers Using Digital Panoramic Radiography Indices as a Screening Tool for Osteoporosis: Protocol for a Comparative Evaluation

Jaw Bone Density in Chronic Areca Nut Chewers and Nonchewers Using Digital Panoramic Radiography Indices as a Screening Tool for Osteoporosis: Protocol for a Comparative Evaluation

Digital panoramic radiography (OPG) is a widely used imaging modality for primary screening in clinical practice. It has several significant advantages including feasibilty, ease of acquisition, being cost effective, a low radiation dose, and ability to depict the dentition as well as jaw bones together. Several indices studied on OPG are helpful for evaluating jaw bone density. The measurements are easy to perform and understand.

Aakanksha Tiwari, Suwarna Dangore-khasbage

JMIR Res Protoc 2025;14:e72041


Deep Learning–Based Chronic Obstructive Pulmonary Disease Exacerbation Prediction Using Flow-Volume and Volume-Time Curve Imaging: Retrospective Cohort Study

Deep Learning–Based Chronic Obstructive Pulmonary Disease Exacerbation Prediction Using Flow-Volume and Volume-Time Curve Imaging: Retrospective Cohort Study

Previous studies on AE-COPD prediction have primarily relied on traditional statistical models such as logistic regression or the Cox proportional hazards model [8]. The CODEX index and BODE index, which incorporate clinical and spirometric variables, are representative tools [18,19]. However, their predictive accuracy is limited when applied to heterogeneous COPD populations.

Eun-Tae Jeon, Heemoon Park, Jung-Kyu Lee, Eun Young Heo, Chang Hoon Lee, Deog Kyeom Kim, Dong Hyun Kim, Hyun Woo Lee

J Med Internet Res 2025;27:e69785