Search Articles

View query in Help articles search

Search Results (1 to 10 of 161 Results)

Download search results: CSV END BibTex RIS

CSV download: Download all 161 search results (up to 5,000 articles maximum)

Maturity Framework for Operationalizing Machine Learning Applications in Health Care: Scoping Review

Maturity Framework for Operationalizing Machine Learning Applications in Health Care: Scoping Review

Currently, the standards for MLOps include variations of the following steps: data preparation (data extraction and data engineering); model development (model training and measuring model performance); and model operationalization (model validation and testing in production, model serving and deployment, CM and CL) [11,12,14,15]. The first stage involves defining the use case and outcomes to inform the data collection and handling process.

Yutong Li, Julie Tian, Ariana Xu, Russell Greiner, Jake Hayward, Andrew James Greenshaw, Bo Cao

J Med Internet Res 2025;27:e66559


Development of a Data-Based Method for Predicting Nursing Workload in an Acute Care Hospital: Methodological Study

Development of a Data-Based Method for Predicting Nursing Workload in an Acute Care Hospital: Methodological Study

In addition to workload data, we also received data relating to patient medication and planned operations. In this study, nursing workload is defined as the time spent on direct patient nursing activities in the presence of the patient, family, or both, and indirect nursing activities performed on behalf of the patient, with LEP as the documentation tool and data source.

Mark McMahon, Sylvie Plate, Tobias Herz, Gabi Brenner, Michael Kleinknecht-Dolf, Michael Krauthammer

J Med Internet Res 2025;27:e66667


Toward Data-Informed Care in Long-Term Care: Qualitative Analysis

Toward Data-Informed Care in Long-Term Care: Qualitative Analysis

Despite the potential of data, integrating data into daily care practice is challenging due to uncertainties about interoperability regarding different data sources (ie, EHRs) and how to use this data for clinical decision-making [12-14]. In addition, health care professionals are often ambivalent about data and the use of information technology [15,16].

Suleyman Bouchmal, Katya YJ Sion, Jan PH Hamers, Sil Aarts

JMIR Aging 2025;8:e69423


Analysis of Social Media Perceptions During the COVID-19 Pandemic in the United Kingdom: Social Listening Study (2019-2022)

Analysis of Social Media Perceptions During the COVID-19 Pandemic in the United Kingdom: Social Listening Study (2019-2022)

To investigate discussions surrounding COVID-19 treatment on social media, we collected data from various social media platforms using a comprehensive search query (Table S1 in Multimedia Appendix 1). Data collection spanned from September 2019 to September 2022 and focused on capturing data from the United Kingdom, specifically English language content. Below, we outline our data sources and search strategy.

Marzieh Araghi, Arron Sahota, Maciej Czachorowski, Kevin Naicker, Natalie Bohm, Katie Phillipps, James Gaddum, Erica Jane Cook

JMIR Form Res 2025;9:e63997


Public Perception of the Brain-Computer Interface Based on a Decade of Data on X: Mixed Methods Study

Public Perception of the Brain-Computer Interface Based on a Decade of Data on X: Mixed Methods Study

We excluded posts before January 2010 due to limited data availability and after December 2021 to maintain the temporal consistency of the dataset, as our data cover only a few months of 2022 (Figure S1 in Multimedia Appendix 1). Detailed individual post data included the text, date and time of posts, the number of reposts, replies, likes, and quote count. Additional data included whether the post included links, media, tagging, or any hashtags.

Mohammed A Almanna, Lior M Elkaim, Mohammed A Alvi, Jordan J Levett, Ben Li, Muhammad Mamdani, Mohammed Al‑Omran, Naif M Alotaibi

JMIR Form Res 2025;9:e60859


Pursuit of Digital Innovation in Psychiatric Data Handling Practices in Ireland: Comprehensive Case Study

Pursuit of Digital Innovation in Psychiatric Data Handling Practices in Ireland: Comprehensive Case Study

With the growing reliance on digital health records, the risk of data-related threats continues to increase. In 2023 alone, European Union countries reported 309 major cybersecurity incidents in the health care sector, the highest among all critical sectors [5]. We have also listed some relevant incidents of data violations in Table 2. List of relevant data violation incidents.

Rana Zeeshan, John Bogue, Amna Gill, Mamoona Naveed Asghar

JMIR Hum Factors 2025;12:e64919


Alert Reduction and Telemonitoring Process Optimization for Improving Efficiency in Remote Patient Monitoring Programs: Framework Development Study

Alert Reduction and Telemonitoring Process Optimization for Improving Efficiency in Remote Patient Monitoring Programs: Framework Development Study

In 21st-century telemonitoring, patients measure relevant health data like vital signs at home according to a predefined measurement schedule [3]. These data are transmitted through a smartphone or tablet application, can be reviewed remotely by health care providers, and can trigger alerts based on pre-defined threshold values. Alerts are reviewed by e-nurses in remote patient monitoring centers and discussed with health care providers if required.

Job van Steenkiste, Niki Lupgens, Martijn Kool, Daan Dohmen, Iris Verberk-Jonkers

JMIR Med Inform 2025;13:e66066


Comparison of Deep Learning Approaches Using Chest Radiographs for Predicting Clinical Deterioration: Retrospective Observational Study

Comparison of Deep Learning Approaches Using Chest Radiographs for Predicting Clinical Deterioration: Retrospective Observational Study

Current EWS rely on structured data, such as vital signs and laboratory values, to predict clinical deterioration and ignore other data modalities that could potentially enhance prediction accuracy [7]. This results in lower detection and higher false-positive rates for these scores that could be mitigated by incorporating additional modalities [8].

Mahmudur Rahman, Jifan Gao, Kyle A Carey, Dana P Edelson, Askar Afshar, John W Garrett, Guanhua Chen, Majid Afshar, Matthew M Churpek

JMIR AI 2025;4:e67144


The AI Reviewer: Evaluating AI’s Role in Citation Screening for Streamlined Systematic Reviews

The AI Reviewer: Evaluating AI’s Role in Citation Screening for Streamlined Systematic Reviews

No personal or patient-level data were used, and no identifiers were included. Formal research ethics board approval was therefore not required. Among the 121 total citations, the LLMs’ sensitivity (correctly identifying included citations) ranged from 57% to 100%, and specificity (correctly excluding noneligible citations) ranged from 18% to 79%. Chat GPT 3.5 achieved the highest sensitivity (100%) and the highest specificity (79%). Full results are shown in Table 1.

Jamie Ghossein, Brett N Hryciw, Tim Ramsay, Kwadwo Kyeremanteng

JMIR Form Res 2025;9:e58366


Associations Among Online Health Information Seeking Behavior, Online Health Information Perception, and Health Service Utilization: Cross-Sectional Study

Associations Among Online Health Information Seeking Behavior, Online Health Information Perception, and Health Service Utilization: Cross-Sectional Study

An empirical analysis based on data from the United States Health Information Trends Survey revealed that OHIS has a positive, relatively large, and statistically significant effect on individual health care demand [21].

Hongmin Li, Dongxu Li, Min Zhai, Li Lin, ZhiHeng Cao

J Med Internet Res 2025;27:e66683