JMIR Medical Informatics

View query in Help articles search

Field

e.g. mhealth

Operator

Field

Criteria

e.g. mhealth

Search Results (1 to 10 of 92 Results)

Download search results: CSV END BibTex RIS

Sort by:

Demonstrating Tactical Combat Casualty Care in Simulated Environments to Enable Passive, Autonomous Documentation: Protocol for a Prospective Simulation-Based Study

The long-term benefit is the ability to provide a basis for evaluating quality of care and benchmarking key metrics for quality improvement efforts and to leverage machine learning (ML) and artificial intelligence (AI) to enhance future care delivery in the tactical environment, as well as to inform clinical decision support systems and algorithms deployed in these settings [5].

Jeanette R Little, Triana Rivera-Nichols, Holly H Pavliscsak, Omar Badawi, James C Gaudaen, Chevas R Yeoman, Todd S Hall, Ethan T Quist, Ericka L Stoor-Burning

JMIR Res Protoc 2025;14:e67673

Download Citation: END BibTex RIS

Download PDF Download XML

Generative AI Models in Time-Varying Biomedical Data: Scoping Review

We have organized the paper as follows: (1) overview of the algorithms and techniques introduced in the review; (2) structured data; (3) unstructured data; (4) medical imaging; (5) physiological waveforms; (6) genetics and multi-omics data; and (7) ethical considerations, challenges, and future directions. Health care data sources in different modalities for generative artificial intelligence (AI) application. ECG: electrocardiogram; EEG: electroencephalogram.

Rosemary He, Varuni Sarwal, Xinru Qiu, Yongwen Zhuang, Le Zhang, Yue Liu, Jeffrey Chiang

J Med Internet Res 2025;27:e59792

Download Citation: END BibTex RIS

Download PDF Download XML

Trends and Gaps in Digital Precision Hypertension Management: Scoping Review

Digital tools used included mobile phones (2/4, 50%), web platform (1/4, 25%), electronic health record (EHR; 1/4, 25%), machine learning (ML) algorithms (1/4, 25%), BP monitor (1/4, 25%), and genomic databases (1/4, 25%). Summary of the studies on digital phenotyping for HTNa. a HTN: hypertension. b BP: blood pressure. c EHR: electronic health record. d ML: machine learning. e SBP: systolic blood pressure. Of the 4 studies, 2 (50%) used secondary data analysis to apply phenotyping.

Namuun Clifford, Rachel Tunis, Adetimilehin Ariyo, Haoxiang Yu, Hyekyun Rhee, Kavita Radhakrishnan

J Med Internet Res 2025;27:e59841

Download Citation: END BibTex RIS

Download PDF Download XML

Identification of Intracranial Germ Cell Tumors Based on Facial Photos: Exploratory Study on the Use of Deep Learning for Software Development

Since i GCTs patients exhibit facial feature changes compared with normal children, we hypothesize that facial recognition algorithms can be developed to alert clinicians at the initial consultation, providing personalized diagnostic approaches [9,10]. The application of facial recognition algorithms is extensive, especially those based on machine learning algorithms, which have been profoundly studied in the medical field.

Yanong Li, Yixuan He, Yawei Liu, Bingchen Wang, Bo Li, Xiaoguang Qiu

J Med Internet Res 2025;27:e58760

Download Citation: END BibTex RIS

Download PDF Download XML

Combining a Risk Factor Score Designed From Electronic Health Records With a Digital Cytology Image Scoring System to Improve Bladder Cancer Detection: Proof-of-Concept Study

Increasing interest in deep learning algorithms has also led to the emergence of new diagnostic strategies based on image processing (see [12,13] for reviews). Although most of them have been developed from cystoscopy images, some aim to propose noninvasive techniques and have exploited images obtained from urine cytology [14-16].

Sandie Cabon, Sarra Brihi, Riadh Fezzani, Morgane Pierre-Jean, Marc Cuggia, Guillaume Bouzillé

J Med Internet Res 2025;27:e56946

Download Citation: END BibTex RIS

Download PDF Download XML

Bias Mitigation in Primary Health Care Artificial Intelligence Models: Scoping Review

This branch of AI focuses on understanding, generating, and reasoning based on data without explicit human instructions [2,3] Such ML algorithms use datasets known as “training datasets” to capture the patterns required for clustering tasks or predictive modeling [3,4]. These models are now used in multiple contexts and industries to predict the likelihood of an event or to support human decision-making [4].

Maxime Sasseville, Steven Ouellet, Caroline Rhéaume, Malek Sahlia, Vincent Couture, Philippe Després, Jean-Sébastien Paquette, David Darmon, Frédéric Bergeron, Marie-Pierre Gagnon

J Med Internet Res 2025;27:e60269

Download Citation: END BibTex RIS

Download PDF Download XML

Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Health Analytics

Algorithms and mathematical expressions for the quantities involved are reported. For conciseness, we present mathematical formulas for estimation procedures of CIs only. Expressions involved for hypothesis testing are similar and can be deduced following the close connection between CIs and hypothesis tests in GLMs (eg, see Agresti [5]). The mathematical description of the GLM setting considered for this analysis is described in the following section along with the mathematical notations to be used.

Félix Camirand Lemyre, Simon Lévesque, Marie-Pier Domingue, Klaus Herrmann, Jean-François Ethier

JMIR Med Inform 2024;12:e53622

Download Citation: END BibTex RIS

Download PDF Download XML

Case Identification of Depression in Inpatient Electronic Medical Records: Scoping Review

A quarter of the identified studies (5/20, 25%) used machine learning to develop phenotyping algorithms. Machine learning models included logistic regression, random forest, and propositional rule learners. Table 2 contains details about the algorithms defined in each study.

Allison Grothman, William J Ma, Kendra G Tickner, Elliot A Martin, Danielle A Southern, Hude Quan

JMIR Med Inform 2024;12:e49781

Download Citation: END BibTex RIS

Download PDF Download XML