Search Articles

View query in Help articles search

Search Results (1 to 10 of 187 Results)

Download search results: CSV END BibTex RIS


A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation

A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation

Acute kidney injury (AKI) represents a critical challenge in postoperative care, significantly affecting patient outcomes and health care systems. It is a common complication that affects up to 5% to 7.5% of all hospitalized patients, with a markedly higher prevalence of 20% in intensive care units [1]. Among all AKI in hospitalized patients, 40% occur in postoperative patients [1].

Ji Won Min, Jae-Hong Min, Se-Hyun Chang, Byung Ha Chung, Eun Sil Koh, Young Soo Kim, Hyung Wook Kim, Tae Hyun Ban, Seok Joon Shin, In Young Choi, Hye Eun Yoon

J Med Internet Res 2025;27:e62853

Developing a Machine Learning Model for Predicting 30-Day Major Adverse Cardiac and Cerebrovascular Events in Patients Undergoing Noncardiac Surgery: Retrospective Study

Developing a Machine Learning Model for Predicting 30-Day Major Adverse Cardiac and Cerebrovascular Events in Patients Undergoing Noncardiac Surgery: Retrospective Study

These factors may modestly impact its effectiveness in predicting clinical outcomes following noncardiac surgeries in practical clinical environments [10]. Subsequent predictive tools, such as the American College of Surgeons, National Surgical Quality Improvement Project (NSQIP), and NSQIP Myocardial Infarction or Cardiac Arrest, developed after RCRI, also show strong performance in predicting postoperative MACE.

Ju-Seung Kwun, Houng-Beom Ahn, Si-Hyuck Kang, Sooyoung Yoo, Seok Kim, Wongeun Song, Junho Hyun, Ji Seon Oh, Gakyoung Baek, Jung-Won Suh

J Med Internet Res 2025;27:e66366

Analysis of Metabolic and Quality-of-Life Factors in Patients With Cancer for a New Approach to Classifying Walking Habits: Secondary Analysis of a Randomized Controlled Trial

Analysis of Metabolic and Quality-of-Life Factors in Patients With Cancer for a New Approach to Classifying Walking Habits: Secondary Analysis of a Randomized Controlled Trial

At the same time, commercial smartphone apps have many limitations in research, especially in collecting physical activity data over a sufficient period [16]. Consequently, the practical application of the research results to patients with cancer in the real world is limited, although e Health tools can provide a potent resource to facilitate personalized and accessible care in daily life [11,12].

Yae Won Tak, Junetae Kim, Haekwon Chung, Sae Byul Lee, In Ja Park, Sei Won Lee, Min-Woo Jo, Jong Won Lee, Seunghee Baek, Yura Lee

J Med Internet Res 2025;27:e52694

Evaluating the Effectiveness of a Mobile App for Breast Cancer Self-Management on Self-Efficacy: Nonrandomized Intervention Trial

Evaluating the Effectiveness of a Mobile App for Breast Cancer Self-Management on Self-Efficacy: Nonrandomized Intervention Trial

In this study, we chose self-efficacy as the primary outcome based on the self-efficacy theory by Bandura [32], which posits that individuals with higher self-efficacy are more likely to engage in self-management behaviors, leading to better health outcomes [33]. This theory is particularly relevant in chronic disease management, where patient engagement in treatment and self-care practices is crucial for long-term treatment success.

Sun Mi Kim, Da Seul Kim, Yoonsung Jang, Min Kyoon Kim, Eun-Seung Yu, Doug Hyun Han, Hee Jun Kim

JMIR Mhealth Uhealth 2025;13:e63989

Machine Learning–Based Explainable Automated Nonlinear Computation Scoring System for Health Score and an Application for Prediction of Perioperative Stroke: Retrospective Study

Machine Learning–Based Explainable Automated Nonlinear Computation Scoring System for Health Score and an Application for Prediction of Perioperative Stroke: Retrospective Study

Despite their exceptional predictive performance, the lack of interpretability has limited their adoption in real-world medical practice [14]. Recent efforts in ML have addressed the “black box” issue of existing models by presenting data in a more understandable fashion [15]. For instance, an ML-based automated scoring model was developed by integrating the Random Forest (RF) algorithm and logistic regression methods [16].

Mi-Young Oh, Hee-Soo Kim, Young Mi Jung, Hyung-Chul Lee, Seung-Bo Lee, Seung Mi Lee

J Med Internet Res 2025;27:e58021

Comparative Effectiveness of Wearable Devices and Built-In Step Counters in Reducing Metabolic Syndrome Risk in South Korea: Population-Based Cohort Study

Comparative Effectiveness of Wearable Devices and Built-In Step Counters in Reducing Metabolic Syndrome Risk in South Korea: Population-Based Cohort Study

The practice of “regular walking” was defined based on a survey as engaging in walking for at least 10 minutes consecutively for 5 or more days in the past week. If individuals who did not practice “regular walking” before participating in the program started practicing it afterward, it was considered an improvement in “regular walking.”

Kyung-In Joung, Sook Hee An, Joon Seok Bang, Kwang Joon Kim

JMIR Mhealth Uhealth 2025;13:e64527

Harnessing Social Media Data to Understand Information Needs About Kidney Diseases and Emotional Experiences With Disease Management: Topic and Sentiment Analysis

Harnessing Social Media Data to Understand Information Needs About Kidney Diseases and Emotional Experiences With Disease Management: Topic and Sentiment Analysis

Kidney diseases primarily manifest in 2 main forms: chronic kidney disease (CKD) and acute kidney injury (AKI), which are 2 significant kidney conditions [1,2]. CKD is characterized by a progressive decline in kidney function lasting >3 months, whereas AKI refers to a sudden decrease in kidney function that occurs over a period of hours to days [1,2].

Hee Jeong Hwang, Nara Kim, Jeong Yun You, Hye Ri Ryu, Seo-Young Kim, Jung Han Yoon Park, Ki Won Lee

J Med Internet Res 2025;27:e64838

Machine Learning–Based Prediction of Substance Use in Adolescents in Three Independent Worldwide Cohorts: Algorithm Development and Validation Study

Machine Learning–Based Prediction of Substance Use in Adolescents in Three Independent Worldwide Cohorts: Algorithm Development and Validation Study

Ungdata is offered to all local and county councils in Norway, who administer the questionnaire in collaboration with NOVA and regional centers for substance use rehabilitation. The dataset can be accessed via the official Ungdata website. During the data processing phase, individual missing values in the KYRBS and YRBS datasets were imputed using a random forest regression–based imputation method [14].

Soeun Kim, Hyejun Kim, Seokjun Kim, Hojae Lee, Ahmed Hammoodi, Yujin Choi, Hyeon Jin Kim, Lee Smith, Min Seo Kim, Guillaume Fond, Laurent Boyer, Sung Wook Baik, Hayeon Lee, Jaeyu Park, Rosie Kwon, Selin Woo, Dong Keon Yon

J Med Internet Res 2025;27:e62805

Designing Patient-Centered Interventions for Emergency Care: Participatory Design Study

Designing Patient-Centered Interventions for Emergency Care: Participatory Design Study

Artificial intelligence (AI)–based software [3] has also been developed to provide practical guidance to novice nurses or scan operators in the ED who have limited experience in echocardiography. In addition, AI-based systems [4,5] have been used to support documentation for the nursing team, indirectly promoting the efficiency of the care process.

Woosuk Seo, Shruti Jain, Vivian Le, Jiaqi Li, Zhan Zhang, Hardeep Singh, Kalyan Pasupathy, Prashant Mahajan, Sun Young Park

JMIR Form Res 2025;9:e63610

Performance Assessment of Large Language Models in Medical Consultation: Comparative Study

Performance Assessment of Large Language Models in Medical Consultation: Comparative Study

Even before the pandemic, depression was recognized as a societal issue and a mental health concern with substantial economic implications in many countries [17-22]. Generative AI has recently been employed as an interactive consultant, sparking interest in evaluating its applicability in medical discussions and consultations, particularly in the context of depression.

Sujeong Seo, Kyuli Kim, Heyoung Yang

JMIR Med Inform 2025;13:e64318