Search Articles

View query in Help articles search

Search Results (1 to 10 of 10430 Results)

Download search results: CSV END BibTex RIS


Autoencoder-Based Representation Learning for Similar Patients Retrieval From Electronic Health Records: Comparative Study

Autoencoder-Based Representation Learning for Similar Patients Retrieval From Electronic Health Records: Comparative Study

The Mahalanobis distance can be viewed as a Euclidean distance after applying a linear transformation to the feature space, defined by L: In this study, we used 3 different algorithms to estimate the Mahalanobis distance on the latent representations: large margin nearest neighbor (LMNN) [37], Neighborhood Components Analysis (NCA) [38], and Metric Learning for Kernel Regression (MLKR) [39].

Deyi Li, Aditi Shukla, Sravani Chandaka, Bradley Taylor, Jie Xu, Mei Liu

JMIR Med Inform 2025;13:e68830

Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study

Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study

Cox regression analysis was conducted to examine the association between serum chloride levels and in-hospital mortality (Text S3 in Multimedia Appendix 1), which quantified the relationship in patients who were critically ill to provide a statistical basis for developing prognostic models and individualized treatment strategies.

Jing Wang, Qixiu Li, Can Xie, Xiaofei Li, Huikao Wang, Wei Xu, Ruyan Lv, Xiaobing Zhai, Ping Xu, Kefeng Li, Xi-Cheng Song

J Med Internet Res 2025;27:e70118

Evaluating Tailored Learning Experiences in Emergency Residency Training Through a Comparative Analysis of Mobile-Based Programs Versus Paper- and Web-Based Approaches: Feasibility Cross-Sectional Questionnaire Study

Evaluating Tailored Learning Experiences in Emergency Residency Training Through a Comparative Analysis of Mobile-Based Programs Versus Paper- and Web-Based Approaches: Feasibility Cross-Sectional Questionnaire Study

A linear regression model with repeated measurements at the hospital level was applied to evaluate the ability to individualize training programs based on performance results, adjusting for potential confounders, including the number of trainers and trainees. The chi-squared test was used to analyze differences in assessment platform performance, with statistical significance set at P This pilot study received ethical approval from the Taipei City Hospital institutional review board (TCHIRB-11110007-E).

Hsin-Ling Chen, Chen-Wei Lee, Chia-Wen Chang, Yi-Ching Chiu, Tzu-Yao Hung

JMIR Med Educ 2025;11:e57216

Predicting Social Frailty in Older Adults Using Fitbit-Derived Circadian and Heart Rate Biomarkers: Cross-Sectional Study

Predicting Social Frailty in Older Adults Using Fitbit-Derived Circadian and Heart Rate Biomarkers: Cross-Sectional Study

To determine the appropriate sample size for the logistic regression analysis, we used G*Power (version 3.1.9.6) with the likelihood-ratio test as the test statistic. The estimation indicated that a minimum of 82 participants would be required to detect a clinically significant effect based on the following parameters: 3 groups, a significance level (α) of .05, a statistical power of 80%, and an odds ratio (OR) of 2.0 [21].

Hiroki Maekawa, Yu Kume

JMIR Form Res 2025;9:e71393

Parent-Child Mutual Influences on Sugar-Sweetened Beverage Consumption Behaviors: Actor-Partner Analysis

Parent-Child Mutual Influences on Sugar-Sweetened Beverage Consumption Behaviors: Actor-Partner Analysis

This categorization captures key educational transitions in Singapore and was used as a covariate in regression analyses to account for developmental differences in autonomy, social influence, and decision-making relevant to dietary behaviors. Data analyses were conducted using SPSS Statistics (version 29; IBM Corporation) along with the MEDYAD tool developed by Coutts et al [33]. Descriptive statistics were computed to summarize participant demographics.

May O Lwin, Allison Seet, Seraphina Leo, Peter J Schulz

JMIR Pediatr Parent 2025;8:e76943

Digital Interventions for Cognitive Dysfunction in Patients With Stroke: Systematic Review and Meta-Analysis

Digital Interventions for Cognitive Dysfunction in Patients With Stroke: Systematic Review and Meta-Analysis

Subgroup analyses and meta-regression further explored sources of heterogeneity (eg, intervention programs and population characteristics). The evidence quality for each outcome was systematically evaluated using the Evidence quality was assessed using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) framework.

Chen Wang, Min Liu

J Med Internet Res 2025;27:e73687

Factors Influencing Physicians' Referral Decision-Making for Rehabilitation Outpatient Services in the Health Care Landscape of China: Cross-Sectional Study

Factors Influencing Physicians' Referral Decision-Making for Rehabilitation Outpatient Services in the Health Care Landscape of China: Cross-Sectional Study

In this study, physicians used the Longshi Scale to classify patients into one of these three groups, which served as a proxy for functional impairment severity in the regression analysis. All statistical analyses were conducted using SPSS (version 26.0; IBM Corp). Descriptive statistics were used to summarize physician and patient characteristics.

Yawei Li, Ruixue Ye, Linlin Shan, Kun Wang, Kaiwen Xue, Zeyu Zhang, Yingzi Hao, Yucong Zou, Xiaoxuan Li, Yulong Wang

Interact J Med Res 2025;14:e64464

Health Care Professionals’ Perspectives on Technology Use in Urinary Care: Cross-Sectional Survey-Based Study

Health Care Professionals’ Perspectives on Technology Use in Urinary Care: Cross-Sectional Survey-Based Study

Despite this deviation from normality, we used parametric tests, specifically Pearson correlation and multiple linear regression, based on central limit theorem (CLT), which supports the use of parametric methods when sample sizes are sufficiently large, typically over 200 participants (N=256). We also assessed regression assumptions, including linearity and multicollinearity. All variance inflation factor (VIF) values were below 2.0, indicating no significant multicollinearity between predictors.

Nicole Zhang, Ni Zhang, Yun Wang, Rachel Wong, Kaylin Ma

JMIR Form Res 2025;9:e73453

Sodium Oxybate as a Potential New Treatment for Catatonia in Patients With Depression, Bipolar Disorder, or a Psychotic Disorder: Protocol for a Randomized Controlled Trial

Sodium Oxybate as a Potential New Treatment for Catatonia in Patients With Depression, Bipolar Disorder, or a Psychotic Disorder: Protocol for a Randomized Controlled Trial

For the secondary outcome measures, we will first determine the remission after 4 days and subsequently after 10 days of treatment using logistic regression. Remission is defined as no longer meeting the DSM-5 criteria of catatonia. We will also describe the percentage of side effects observed in participants assigned to high-dose lorazepam or sodium oxybate.

Lilian Bot, Josine G van Mill, Laetitia J C A Smarius, Adriaan W Hoogendoorn, Bram W C Storosum, Christiaan H Vinkers, Gabriel E Jacobs, Gert Jan Lammers, Hanna M Heller, Jantine C A Colen-de Koning, Joris J B van der Vlugt, Marloes S Oudijn, Martijn S van Noorden, Pierre M Bet, Rolf Fronczek, Heleen S van der Heijden, Sjors M M Lange, Ysbrand D van der Werf, Eric R van Exel

JMIR Res Protoc 2025;14:e68356

Online Peer Support for Long-Term Conditions: Protocol for a Feasibility Randomized Controlled Trial

Online Peer Support for Long-Term Conditions: Protocol for a Feasibility Randomized Controlled Trial

As the clinical outcomes have been selected for their relevance for informing potential effect sizes for a future confirmatory trial, regression models will be used to estimate the effect of treatment allocation on outcomes measured at the postintervention time point (T6). The analysis of clinical outcomes will follow a modified intention-to-treat principle.

Grace Lavelle, Hannah Grace Jones, Ewan Carr, Elly Aylwin-Foster, Vanessa Lawrence, Alan Simpson, Matthew Hotopf

JMIR Res Protoc 2025;14:e71513