e.g. mhealth
Search Results (1 to 10 of 263 Results)
Download search results: CSV END BibTex RIS
CSV download: Download all 263 search results
(up to 5,000 articles maximum)
- 84 JMIR Medical Informatics
- 57 Journal of Medical Internet Research
- 34 JMIR Formative Research
- 13 JMIR Research Protocols
- 12 JMIR Human Factors
- 10 JMIR Public Health and Surveillance
- 8 JMIRx Med
- 7 JMIR Aging
- 6 JMIR Cancer
- 5 JMIR AI
- 4 Interactive Journal of Medical Research
- 3 JMIR Cardio
- 3 JMIR Medical Education
- 3 JMIR mHealth and uHealth
- 2 JMIR Diabetes
- 2 JMIR Mental Health
- 2 JMIR Nursing
- 2 JMIR Pediatrics and Parenting
- 2 Online Journal of Public Health Informatics
- 1 JMIR Bioinformatics and Biotechnology
- 1 JMIR Dermatology
- 1 JMIR Perioperative Medicine
- 1 Journal of Participatory Medicine
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Serious Games
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Challenges
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 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)
The benefits of EHR for medical documentation include legibility, accuracy of record-keeping, enhanced ability to access laboratory data, placement of physician orders, interactive alerts, clinical pathways, plus timeliness and interoperability between health care institutions. Since the EHR is designed to be comprehensive, there are considerable and growing demands on clinicians for documentation of the myriad aspects of patient encounters.
JMIR Med Inform 2025;13:e77901
Download Citation: END BibTex RIS
Electronic health records (EHR) data are widely used in clinical research. While they contain dense, often granular information on a patient’s health status, they also pose challenges for clinical studies since they lack explicit documentation for the reason for the health care encounter (eg, admission due to infection). In principle, the problem list, which provides a historical listing of previous health problems, can be used to identify chronic conditions, though it is often unreliable [1,2].
JMIR Med Inform 2025;13:e72068
Download Citation: END BibTex RIS
However, their predictive performance remains suboptimal in real-world applications, with area under the receiver operating characteristic curve (AUROC) of 0.6 when using electronic health record (EHR) data [4].
Medical codes such as International Classification of Diseases (ICD) codes, procedure codes, and medication identifiers vary in structure and granularity, introducing complexity and high dimensionality into the data.
JMIR Med Inform 2025;13:e73020
Download Citation: END BibTex RIS
Creation and Implementation of an Electronic Sexual Assault Record at the Geneva University Hospital
ehr
JMIR Med Inform 2025;13:e66764
Download Citation: END BibTex RIS
Given the limitations of existing surveillance systems, there is an increasing interest in using electronic health record (EHR) data to estimate prevalence at these granular levels. It is posited that EHR systems may capture more cases with distinguishing characteristics relative to a population-based survey as data are obtained from all individuals interacting with health care services [14].
JMIR Public Health Surveill 2025;11:e79653
Download Citation: END BibTex RIS
For instance, Berman et al [14] used comprehensive EHR data sourced from 2 prominent academic medical centers to identify variables predictive of 30-day readmission among patients with liver disease. Similarly, Hu and colleagues [15] conducted an analysis of 30-day and 90-day readmission rates for patients with end-stage liver disease, leveraging EHR data in conjunction with models such as logistic regression, support vector machines, and random forests.
JMIR Med Inform 2025;13:e63581
Download Citation: END BibTex RIS
Our NLP algorithm outperforms ICD codes in identifying NID patients and achieves competitive performance compared to the Llama 3.2 autoregressive model (an LLM with 3 B parameters) in zero-shot learning tasks, making it a valuable tool for large-scale EHR-based research to investigate the relationship between NID exposure and short- and long-term neurological outcomes.
JMIR Med Inform 2025;13:e63157
Download Citation: END BibTex RIS
Understanding the importance of broadband access, financial incentives such as the Centers for Medicare and Medicaid Services EHR (electronic health record) Incentive Program, also known as Meaningful Use Program, were created to support widespread implementation of internet-driven resources throughout health systems [1,5-7].
J Med Internet Res 2025;27:e69606
Download Citation: END BibTex RIS
EHR data consist of structured data, which are data in standardized format, and unstructured data, which are free-text data. Primary care (PC) EHR data provide extensive and longitudinal data from a patient’s health trajectory and changes over time. AI might prove to be a valuable method to extract clinically useful and actionable insight from this vast and complex source of patient data [13].
JMIR Med Inform 2025;13:e62862
Download Citation: END BibTex RIS
In this viewpoint paper, we highlight challenges in the quality and linkage of electronic health record (EHR) infrastructures in NHS England, including inconsistencies in data documentation, interoperability issues, and limitations in data linkage between primary and secondary care. Additionally, we discuss variations in findings due to differences in population characteristics, service settings, and outcome measures.
Online J Public Health Inform 2025;17:e66672
Download Citation: END BibTex RIS