Search Articles

View query in Help articles search

Search Results (1 to 10 of 2054 Results)

Download search results: CSV END BibTex RIS


Evaluating the Characteristics and Outcomes of Acute Pharmaceutical Exposure in Children: 5-Year Retrospective Study

Evaluating the Characteristics and Outcomes of Acute Pharmaceutical Exposure in Children: 5-Year Retrospective Study

Li et al [14] showed that most poisoning incidents among children are accidental, with 70.4% occurring at home. Accidental poisonings are more common in young children, particularly in those aged 1‐3 years, whereas intentional poisonings are more common among adolescents [15,16]. Furthermore, the clinical manifestations of acute poisoning in children are diverse, and some severe cases presenting consciousness disturbances and circulatory failure can be life-threatening.

Zhu Yan Duan, Yan Ning Qu, Rui Tang, Jun Ting Liu, Hui Wang, Meng Yi Sheng, Liang Liang Wang, Shuang Liu, Jiao Li, Lin Ying Guo, Si Zheng

JMIR Pediatr Parent 2025;8:e66951

Imaging-Based AI for Predicting Lymphovascular Space Invasion in Cervical Cancer: Systematic Review and Meta-Analysis

Imaging-Based AI for Predicting Lymphovascular Space Invasion in Cervical Cancer: Systematic Review and Meta-Analysis

In contrast, other studies, such as Li et al [19] and Wang et al [20], observed considerably lower performance, with AUC values of 0.72 and 0.73, respectively. These discrepancies can be attributed to factors such as data quality, sample size, and model architecture. Low-quality datasets, such as retrospective studies or single-center studies, may introduce selection bias and limit the generalizability of models, thereby affecting the reliability of radiomics approaches in clinical practice [21].

Lizhen She, Yunfeng Li, Hongyong Wang, Jun Zhang, Yuechen Zhao, Jie Cui, Ling Qiu

J Med Internet Res 2025;27:e71091

Predictive Performance of Machine Learning for Suicide in Adolescents: Systematic Review and Meta-Analysis

Predictive Performance of Machine Learning for Suicide in Adolescents: Systematic Review and Meta-Analysis

Research by Chiu et al [7] suggested that suicidal ideation often precedes suicidal plans, and these plans serve as precursors to suicide attempts, which may ultimately result in fatal outcomes. These forms of suicide-related behaviors not only lead to individual tragedies but also pose substantial threats to the social and psychological well-being and stability of communities [8].

Lingjiang Liu, Zhiyuan Li, Yaxin Hu, Chunyou Li, Shuhan He, Shibei Zhang, Jie Gao, Huaiyi Zhu, Guoping Huang

J Med Internet Res 2025;27:e73052

Mental Health Issues and 24-Hour Movement Guidelines–Based Intervention Strategies for University Students With High-Risk Social Network Addiction: Cross-Sectional Study Using a Machine Learning Approach

Mental Health Issues and 24-Hour Movement Guidelines–Based Intervention Strategies for University Students With High-Risk Social Network Addiction: Cross-Sectional Study Using a Machine Learning Approach

A study by Li et al [52] further supports this view, finding that adherence to the 24-HMG guidelines was significantly associated with reduced depression risk, particularly in terms of PA and sleep. In addition, Brown et al [53] noted that comprehensive interventions targeting ST, sleep, and PA within the 24-HMG framework had significant effects on improving mental health. These results indicate that a healthy lifestyle not only helps reduce SNA risk but also significantly enhances mental health.

Lin Luo, Junfeng Yuan, Chen Xu, Huilin Xu, Haojie Tan, Yinhao Shi, Haiping Zhang, Haijun Xi

J Med Internet Res 2025;27:e72260

The Machine Learning Models in Major Cardiovascular Adverse Events Prediction Based on Coronary Computed Tomography Angiography: Systematic Review

The Machine Learning Models in Major Cardiovascular Adverse Events Prediction Based on Coronary Computed Tomography Angiography: Systematic Review

In the 2 studies that analyzed data at the nonpatient level, Li et al [12] in 2021 integrated 14 radiomic features and compared the RF model with a conventional LR model, achieving a sensitivity of 89.02%, a specificity of 64.91%, and an AUROC of 0.82 at the plaque level in the training set, with no statistically significant difference observed between the training set and the validation set (P=.58).

Yuchen Ma, Mohan Li, Huiqun Wu

J Med Internet Res 2025;27:e68872