Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 6, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

A Proposed Participatory Framework for Explainable AI in mHealth: Mixed Methods Study Integrating User and

Farzana Islam¹, Ashraful Islam¹, M Ashraful Amin¹

¹Center for Computational & Data Sciences, Independent University, Bangladesh, Plot 16, Block B, Aftab Uddin Ahmed Road, Bashundhara R/A, Dhaka, Dhaka Division, 1245, Bangladesh, 880 9612-939393.

Journal of Medical Internet Research

|May 4, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

CattleNet-XAI: An explainable CNN framework for efficient cattle weight estimation.

PloS one·2025

Same author

A Mobile Application-Based Relational Agent as a Health Professional for COVID-19 Patients: Design, Approach, and Implications.

International journal of environmental research and public health·2022

Same author

Design Validation of a Relational Agent by COVID-19 Patients: Mixed Methods Study.

JMIR human factors·2022

Same author

Correction: Toward Designs of Workplace Stress Management Mobile Apps for Frontline Health Workers During the COVID-19 Pandemic and Beyond: Mixed Methods Qualitative Study.

JMIR formative research·2022

Same author

Toward Designs of Workplace Stress Management Mobile Apps for Frontline Health Workers During the COVID-19 Pandemic and Beyond: Mixed Methods Qualitative Study.

JMIR formative research·2021

Developing explainable AI (XAI) for mobile health (mHealth) in South Asia requires context-specific frameworks. This study identified key explainability needs for trust and adoption among diverse stakeholders in Bangladesh.

Area of Science:

Digital Health
Artificial Intelligence
Human-Computer Interaction

Background:

Mobile health (mHealth) apps integrating artificial intelligence (AI) offer potential in low-resource settings.
Opaque AI recommendations in mHealth hinder trust and adoption, particularly in South Asia due to cultural and linguistic barriers.
Existing explainable AI (XAI) frameworks are not designed for the unique needs of South Asian populations, creating implementation challenges.

Purpose of the Study:

To investigate stakeholder perceptions of trust and explainability in AI-driven mHealth in Bangladesh.
To identify demographic predictors influencing trust in AI-driven mHealth.
To develop a context-adapted XAI framework for resource-constrained settings.

Main Methods:

A sequential mixed-methods design combining quantitative surveys (n=137) and qualitative interviews/focus groups (n=20) with developers, XAI experts, and clinicians.

Keywords:

AI transparency Global South artificial intelligence clinical decision support digital health explainable AI human-centered design mHealth participatory design responsible AI trust in AI

Related Experiment Videos

Last Updated: May 6, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Statistical analysis was used to examine demographic predictors of trust.

Thematic analysis identified stakeholder-specific explainability needs.

Main Results:

Higher education levels correlated with lower trust in AI, suggesting critical evaluation skills develop with advanced education.
Users stressed the need for human validation and understanding AI logic, while developers noted limited explainability in current apps.
Key requirements identified include human-AI collaboration, transparent logic, personalization, cultural relevance, and ethical safeguards.

Conclusions:

A novel, context-adapted XAI framework was developed to address stakeholder misalignments in resource-constrained environments.
The framework emphasizes equity, inclusion, and user empowerment by integrating explainability within South Asia's sociocultural context.
This research advances XAI beyond technical transparency toward practical application and user trust in digital health.