e.g. mhealth
Search Results (1 to 10 of 267 Results)
Download search results: CSV END BibTex RIS
CSV download: Download all 267 search results
(up to 5,000 articles maximum)
- 71 Journal of Medical Internet Research
- 50 JMIR Medical Informatics
- 35 JMIR Public Health and Surveillance
- 23 JMIR Formative Research
- 20 JMIRx Med
- 14 JMIR Research Protocols
- 7 JMIR AI
- 7 JMIR Aging
- 7 JMIR Bioinformatics and Biotechnology
- 5 JMIR mHealth and uHealth
- 4 JMIR Human Factors
- 4 JMIR Mental Health
- 3 Interactive Journal of Medical Research
- 3 Online Journal of Public Health Informatics
- 2 JMIR Cardio
- 2 JMIR Diabetes
- 2 JMIR Pediatrics and Parenting
- 1 JMIR Biomedical Engineering
- 1 JMIR Cancer
- 1 JMIR Dermatology
- 1 JMIR Medical Education
- 1 JMIR Neurotechnology
- 1 JMIR Perioperative Medicine
- 1 JMIR Rehabilitation and Assistive Technologies
- 1 JMIR Serious Games
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Preprints
- 0 JMIR Challenges
- 0 JMIR Data
- 0 Journal of Participatory Medicine
- 0 JMIR Nursing
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 Asian/Pacific Island Nursing Journal
- 0 JMIR XR and Spatial Computing (JMXR)
Since we found that the ensemble model of Ada Boost, Elastic Net, and SVR exhibited high test performance for predicting the PSI scores of children with ADHD, we visualized the prediction scores and actual PSI values on a graph (Figure 4). The x-axis presents the actual PSI scores, while the y-axis presents the scores predicted using the ensemble model of Ada Boost, Elastic Net, and SVR. The data points on the dashed line (y=x) indicate accurate prediction of the actual PSI values.
JMIR Serious Games 2025;13:e73408
Download Citation: END BibTex RIS
Achieving 96.5% accuracy for vital sign prediction demonstrates the effectiveness of the proposed model.
Response: We appreciate the reviewer’s recognition of our system’s performance. The 96.5% accuracy is detailed in section 5 (Results and Analysis), with comprehensive performance metrics shown in Table 1, demonstrating mean absolute error values of 1.82%, 2.14%, and 1.95% for heart rate, blood pressure, and respiratory rate, respectively.
JMIRx Med 2025;6:e83473
Download Citation: END BibTex RIS
.001)” I presume should be “(P
This paper presents an architecture to perform real-time monitoring of health signals using 5 G networks and deep-learning prediction of possible health problems using the aquired signals.
There are some equations with no defined parameters. In equation 16, what are Pij and xij? In equation 17, what is N? In equation 18, what are Bi, Cj, and M? In equation 19, what is Lu? They must be defined.
How are weights wu, wr, and wl calculated or estimated?
JMIRx Med 2025;6:e83424
Download Citation: END BibTex RIS
Achieving 96.5% accuracy for vital sign prediction demonstrates the effectiveness of the proposed model.
While tested on 1000 patients, analysis of its scalability to larger populations with diverse demographics would improve generalizability.
The use of attention mechanisms in the long short-term memory component improves the system’s ability to model dependencies in continuous vital sign monitoring.
JMIRx Med 2025;6:e83423
Download Citation: END BibTex RIS
Asaad et al [23] proposed a convolutional neural network (CNN)–long short-term memory (LSTM) hybrid architecture for real-time heart rate monitoring, achieving 94% prediction accuracy with a 5-second forecasting window. Their system processed real-time electrocardiogram signals but was limited by network latency issues. Kumar et al [3] developed a multiparameter vital sign prediction system using an attention-based LSTM network.
JMIRx Med 2025;6:e70906
Download Citation: END BibTex RIS
The increasing availability of real-world clinical data housed in electronic health records (EHR) is generating opportunities to investigate population-level health outcomes, develop classification and risk prediction models to augment clinical decision-making, and accelerate diagnostic and therapeutic discovery [13-15].
JMIR Diabetes 2025;10:e69142
Download Citation: END BibTex RIS
This capability has been successfully demonstrated in neurodegenerative diseases and tumor prognosis prediction by enhancing the feature representation of small-sample datasets. However, no study has systematically applied ML for prognostic prediction in NMDAR encephalitis.
JMIR Med Inform 2025;13:e75020
Download Citation: END BibTex RIS
However, most of these models focus on predicting the ultimate outcomes of MDR/RR-TB, with a notable gap in early efficacy prediction models specifically for MDR/RR-TB. Therefore, the use of predictive models to forecast early treatment efficacy in patients with MDR/RR-TB not only advances the development of this field but also aids in monitoring therapeutic outcomes.
J Med Internet Res 2025;27:e69998
Download Citation: END BibTex RIS
In this paper, we refer to a “prediction window,” by which we mean the time between the point at which the prediction is made and the shift for which the prediction is made. The prediction window is therefore 9 shifts (equivalent to 72 h or 3 d) into the future, from the time of prediction.
We derived a set of variables which were to be used during modeling (Table 2), using the full data range of available data sources to create the feature set.
J Med Internet Res 2025;27:e66667
Download Citation: END BibTex RIS
To address the knowledge gap, we developed and described the initial validation of SPRIGHT (Sickle Cell Predicting Outcomes of Hematopoietic Cell Transplantation), an individualized ML prediction model for outcomes of HCT for SCD, incorporating multiple relevant features to make predictions of key clinical outcomes.
JMIR AI 2025;4:e64519
Download Citation: END BibTex RIS