e.g. mhealth
Search Results (1 to 10 of 74 Results)
Download search results: CSV END BibTex RIS
CSV download: Download all 74 search results
(up to 5,000 articles maximum)
- 20 Journal of Medical Internet Research
- 8 JMIR Medical Informatics
- 7 JMIR AI
- 7 JMIR Formative Research
- 7 JMIR Public Health and Surveillance
- 5 JMIR Research Protocols
- 4 JMIR Aging
- 3 JMIR Cardio
- 2 Interactive Journal of Medical Research
- 2 JMIR Bioinformatics and Biotechnology
- 2 JMIR Mental Health
- 2 JMIR Perioperative Medicine
- 2 Online Journal of Public Health Informatics
- 1 JMIR Cancer
- 1 JMIR Diabetes
- 1 JMIR Human Factors
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR mHealth and uHealth
- 0 JMIR Serious Games
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Medical Education
- 0 JMIR Challenges
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 0 Journal of Participatory Medicine
- 0 JMIR Dermatology
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 JMIR XR and Spatial Computing (JMXR)
Althammer et al [8] conducted a study on image analysis to predict the response to durvalumab therapy targeting the programmed cell death-1/programmed cell death ligand-1 (PD1/PD-L1) pathway in patients with non–small cell lung cancer.
JMIR Med Inform 2025;13:e75022
Download Citation: END BibTex RIS
To develop and evaluate prediction models capable of predicting the number of short-term discharges (ie, in the next 1 to 4 hours) in near real time, we must first decide the granularity level we want to predict. The literature has considered 2 main types of models: patient-level models [7-11] and hospital-level models [12,13]. Hospital-level models typically use a time series approach to directly predict the number of discharges in an entire hospital or a hospital unit such as the ED [12,13].
J Med Internet Res 2025;27:e63765
Download Citation: END BibTex RIS
Predictive Modeling of Hypertension-Related Postpartum Readmission: Retrospective Cohort Analysis
We used a cost-sensitive random forest method to predict which patient would experience a hypertension-related postpartum readmission [14]. Since the data set was imbalanced (only 170 readmissions out of 32,645 participants), the use of class weights that penalize false negatives significantly higher than false positives was necessary to avoid ML models that predict every sample as the negative class.
JMIR AI 2024;3:e48588
Download Citation: END BibTex RIS
First, prediction modeling validation studies using machine learning methods, statistical models, and biomarkers to predict postoperative infections were identified. Second, a separate search was performed to identify studies on automated surveillance for postoperative and other hospital-acquired infections (Figure 1). Surveillance studies focusing on surgical populations often only investigate SSIs.
JMIR Med Inform 2024;12:e57195
Download Citation: END BibTex RIS
The second review investigates studies integrating machine learning with RPM to predict AECOPD. This comprehensive approach enables us to provide a novel understanding of digitally enabled AECOPD interventions. We review the evidence and concepts behind RPM and machine learning; discuss the strengths, limitations, and clinical applications of available systems; and generate recommendations to enhance patient and health care system outcomes.
J Med Internet Res 2024;26:e52143
Download Citation: END BibTex RIS
In this study of Cook County, IL, we sought to enable a neighborhood-focused prevention approach by creating a semiautomated method to precisely describe where SUID occurred in the recent past (2015‐2019) and to predict where SUID would occur in the near future (2021‐2025) while pointing to social vulnerability indicators as explanatory variables.
JMIR Public Health Surveill 2024;10:e48825
Download Citation: END BibTex RIS
Predicting Long COVID in the National COVID Cohort Collaborative Using Super Learner: Cohort Study
Given this heterogeneity, multisite evaluations including large sample sizes and high-dimensional covariate information can provide opportunities to build models that can accurately predict PASC risk.
Due to the broad range of factors associated with PASC, the high dimensionality of the large EHR databases, and the unknown determinants of PASC, modeling methods for predicting PASC must be highly flexible.
JMIR Public Health Surveill 2024;10:e53322
Download Citation: END BibTex RIS
Understanding the patterns of and changes in social vulnerability that predict an individual’s capability to comply with the WHO advice in these countries will provide beneficial information to guide COVID-19 prevention, especially among vulnerable populations.
JMIR Public Health Surveill 2024;10:e54383
Download Citation: END BibTex RIS
The study’s outcomes were considered promising, as the developed model demonstrated the ability to predict severe AEs induced by antineoplastic drugs in patients with cancer. The researchers concluded that the use of automated triggers and ML is a promising approach to identifying risk factors for severe events, in contrast to the manual and retrospective method which aims to track events that have already occurred.
JMIR Res Protoc 2024;13:e55466
Download Citation: END BibTex RIS
We develop an explainable, machine-learning model to predict pediatric patients with T1 D who are at risk of DKA hospitalization postdiagnosis using a time-series of routinely collected, EHR data. We evaluate the predictive performance of our gradient-boosted decision tree model (XGBoost) on one of the largest cohorts of pediatric patients with T1 D.
JMIR Diabetes 2024;9:e53338
Download Citation: END BibTex RIS