Search Articles

View query in Help articles search

Search Results (1 to 10 of 153 Results)

Download search results: CSV END BibTex RIS


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

Assessing the Data Quality Dimensions of Partial and Complete Mastectomy Cohorts in the All of Us Research Program: Cross-Sectional Study

Assessing the Data Quality Dimensions of Partial and Complete Mastectomy Cohorts in the All of Us Research Program: Cross-Sectional Study

Accordingly, the primary objective of this study is to determine whether the All of Us data are fit for an analysis of women who had a mastectomy. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) is the data standard used by the All of Us Research Program. The OMOP CDM consists of standardized concepts and relationships, allowing for harmonizing data from different sources.

Matthew Spotnitz, John Giannini, Yechiam Ostchega, Stephanie L Goff, Lakshmi Priya Anandan, Emily Clark, Tamara R Litwin, Lew Berman

JMIR Cancer 2025;11:e59298

Assessing Digital Maturity of Hospitals: Viewpoint Comparing National Approaches in Five Countries

Assessing Digital Maturity of Hospitals: Viewpoint Comparing National Approaches in Five Countries

We assigned academic (KC, FJ, LW, TP, and EA) or policy (ML and SM) leads to each of the participating countries, who were responsible for collecting descriptive data. Using the nominal group technique with leads, we cocreated a data collection template table for each country, representing key features and learnings identified through discussions in group meetings.

Kathrin Cresswell, Franziska Jahn, Line Silsand, Leanna Woods, Tim Postema, Marion Logan, Sevala Malkic, Elske Ammenwerth

J Med Internet Res 2025;27:e57858

Empowering Health Care Actors to Contribute to the Implementation of Health Data Integration Platforms: Retrospective of the medEmotion Project

Empowering Health Care Actors to Contribute to the Implementation of Health Data Integration Platforms: Retrospective of the medEmotion Project

Accurate and well-formatted data are key to delivering high-quality health care and fueling medical research [1-3]. All health care actors acquire real-world data, defined as any health care-related information captured from the patient [4]. The volume, velocity, and variety of acquired data, however, raise challenges for data processing systems [5].

Marcel Parciak, Noëlla Pierlet, Liesbet M Peeters

J Med Internet Res 2025;27:e68083

Using Structured Codes and Free-Text Notes to Measure Information Complementarity in Electronic Health Records: Feasibility and Validation Study

Using Structured Codes and Free-Text Notes to Measure Information Complementarity in Electronic Health Records: Feasibility and Validation Study

EHR data are generally recorded in 2 forms: structured and unstructured data. Structured data includes clinical codes for documenting clinical events, such as diagnoses, medications, procedures, and measurements. Structured data is particularly suitable for observational research due to its consistent meaning, tabular format, and standardized vocabulary of codes.

Tom M Seinen, Jan A Kors, Erik M van Mulligen, Peter R Rijnbeek

J Med Internet Res 2025;27:e66910

Assessment of Digital Capabilities by 9 Countries in the Alliance for Healthy Cities Using AI: Cross-Sectional Analysis

Assessment of Digital Capabilities by 9 Countries in the Alliance for Healthy Cities Using AI: Cross-Sectional Analysis

The survey was conducted from August 1 to September 21, 2023, and the collected data were stored in a report. No human participants were involved, and thus institutional review board (IRB) approval was not obtained. Five healthy city experts performed a qualitative analysis on the collected data through a group deep discussion. The experts were recruited from October 1, 2023, to November 3, 2023.

Hocheol Lee

JMIR Form Res 2025;9:e62935

Identification of Gender Differences in Acute Myocardial Infarction Presentation and Management at Aga Khan University Hospital-Pakistan: Natural Language Processing Application in a Dataset of Patients With Cardiovascular Disease

Identification of Gender Differences in Acute Myocardial Infarction Presentation and Management at Aga Khan University Hospital-Pakistan: Natural Language Processing Application in a Dataset of Patients With Cardiovascular Disease

This paucity of data is particularly apparent in the evaluation of gender differences in the clinical presentation and medical management of IHD in LMICs [8,9]. A promising direction is the use of electronic health records (EHRs) to analyze patient data to better inform clinical decision-making and assess adherence to IHD treatment guidelines using a gender lens.

Christine Ngaruiya, Zainab Samad, Salma Tajuddin, Zarmeen Nasim, Rebecca Leff, Awais Farhad, Kyle Pires, Muhammad Alamgir Khan, Lauren Hartz, Basmah Safdar

JMIR Form Res 2024;8:e42774

The Challenges and Lessons Learned Building a New UK Infrastructure for Finding and Accessing Population-Wide COVID-19 Data for Research and Public Health Analysis: The CO-CONNECT Project

The Challenges and Lessons Learned Building a New UK Infrastructure for Finding and Accessing Population-Wide COVID-19 Data for Research and Public Health Analysis: The CO-CONNECT Project

The results from the queries run across all the data partners and are automatically collated and displayed within the Gateway for analysis by the user who initiated the query. To configure the federated platform, we worked across 22 different data partners to on-board their data. Data partners included academic groups collecting data from a consented research cohort and national Trusted Research Environments (TREs) collecting population-wide, routinely collected data.

Emily Jefferson, Gordon Milligan, Jenny Johnston, Shahzad Mumtaz, Christian Cole, Joseph Best, Thomas Charles Giles, Samuel Cox, Erum Masood, Scott Horban, Esmond Urwin, Jillian Beggs, Antony Chuter, Gerry Reilly, Andrew Morris, David Seymour, Susan Hopkins, Aziz Sheikh, Philip Quinlan

J Med Internet Res 2024;26:e50235

Attitudes of Health Professionals Toward Digital Health Data Security in Northwest Ethiopia: Cross-Sectional Study

Attitudes of Health Professionals Toward Digital Health Data Security in Northwest Ethiopia: Cross-Sectional Study

Numerous health care data security breaches have occurred owing to a lack of attitude by the user [8]. Most prominently, digital health data were the victim of phishing, ransomware, and malware [9]. As studies elucidated, the attitudes of health professionals toward digital health data security were prominent factors in determining the consequences of adopting digital technology to secure health care data [3].

Ayenew Sisay Gebeyew, Zegeye Regasa Wordofa, Ayana Alebachew Muluneh, Adamu Ambachew Shibabaw, Agmasie Damtew Walle, Sefefe Birhanu Tizie, Muluken Belachew Mengistie, Mitiku Kassaw Takillo, Bayou Tilahun Assaye, Adualem Fentahun Senishaw, Gizaw Hailye, Aynadis Worku Shimie, Fikadu Wake Butta

Online J Public Health Inform 2024;16:e57764