Search Articles

View query in Help articles search

Search Results (1 to 6 of 6 Results)

Download search results: CSV END BibTex RIS


Target Product Profile for a Machine Learning–Automated Retinal Imaging Analysis Software for Use in English Diabetic Eye Screening: Protocol for a Mixed Methods Study

Target Product Profile for a Machine Learning–Automated Retinal Imaging Analysis Software for Use in English Diabetic Eye Screening: Protocol for a Mixed Methods Study

A recent qualitative systematic review on stakeholder perspectives of clinical AI implementation identified the following key stakeholder groups influencing implementation: patients, carers, and the public; health care professionals; health care managers and leaders; regulators and policy makers; and developers [44].

Trystan Macdonald, Jacqueline Dinnes, Gregory Maniatopoulos, Sian Taylor-Phillips, Bethany Shinkins, Jeffry Hogg, John Kevin Dunbar, Ameenat Lola Solebo, Hannah Sutton, John Attwood, Michael Pogose, Rosalind Given-Wilson, Felix Greaves, Carl Macrae, Russell Pearson, Daniel Bamford, Adnan Tufail, Xiaoxuan Liu, Alastair K Denniston

JMIR Res Protoc 2024;13:e50568

Leveraging Generative AI Tools to Support the Development of Digital Solutions in Health Care Research: Case Study

Leveraging Generative AI Tools to Support the Development of Digital Solutions in Health Care Research: Case Study

Stakeholders included: patients with prediabetes and their support network (eg, caregivers and partners), primary care providers, health technologists, programmers and computer scientists, behavioral change theorists and subject matter experts, the research administrative team, and d DPP product developers and coaches.

Danissa V Rodriguez, Katharine Lawrence, Javier Gonzalez, Beatrix Brandfield-Harvey, Lynn Xu, Sumaiya Tasneem, Defne L Levine, Devin Mann

JMIR Hum Factors 2024;11:e52885

Developer Perspectives on Potential Harms of Machine Learning Predictive Analytics in Health Care: Qualitative Analysis

Developer Perspectives on Potential Harms of Machine Learning Predictive Analytics in Health Care: Qualitative Analysis

Developers’ concerns regarding violation of privacy focused on the sharing of sensitive health information not germane to a developer’s task (participant P30). The primary harm to groups mentioned by developers was the possibility of systematic bias in an algorithm’s outcomes leading to medically unjustified differences in treatments among certain sociopolitical groups.

Ariadne A Nichol, Pamela L Sankar, Meghan C Halley, Carole A Federico, Mildred K Cho

J Med Internet Res 2023;25:e47609

Incorporating Consumers’ Needs in Nutrition Apps to Promote and Maintain Use: Mixed Methods Study

Incorporating Consumers’ Needs in Nutrition Apps to Promote and Maintain Use: Mixed Methods Study

Therefore, nutrition app developers should pay particular attention to a complete and trustworthy food database and the user-friendliness of the app. Finally, in our qualitative study, we found that nutrition apps can be specifically helpful for new users and that the learning curve is steepest in the beginning. A recent study by Samoggia et al [42] shows that a nutrition-information app is indeed mostly effective among consumers with limited knowledge.

Sandra van der Haar, Ireen Raaijmakers, Muriel C D Verain, Saskia Meijboom

JMIR Mhealth Uhealth 2023;11:e39515

Challenges With Developing Secure Mobile Health Applications: Systematic Review

Challenges With Developing Secure Mobile Health Applications: Systematic Review

Our review’s objective was to identify and codify the challenges that hinder m Health app developers from developing secure apps. This review’s findings would enable us to identify the potential gaps that need to be further investigated based on the developers’ perspectives.

Bakheet Aljedaani, M Ali Babar

JMIR Mhealth Uhealth 2021;9(6):e15654

The State of Open Source Electronic Health Record Projects: A Software Anthropology Study

The State of Open Source Electronic Health Record Projects: A Software Anthropology Study

The core success of the open source movement depends on developers who contribute their knowledge and effort for free to the community. Developers are either unpaid volunteers, hobbyists [20], or employees who are paid to write code. A study of mainstream F/OSS projects categorized developers’ contribution into eight different roles: project leader, core member, active developers, peripheral developer, bug fixer, bug reporter, reader, and passive user [4].

Mona Mohammed Alsaffar, Peter Yellowlees, Alberto Odor, Michael Hogarth

JMIR Med Inform 2017;5(1):e6