Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Journal of Software Engineering, Information and Communication Technology The Indonesian Journal of Computer Science
Kabarungi, Moreen
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : The Indonesian Journal of Computer Science

 1 
Developing a Campus Blended Learning Framework to Improve Adoption in Higher Educational Institutions in Southwestern Uganda Kabarungi, Moreen; Ntwari Richard; Annabella Habinka Ejiri; Kawuma Simon
The Indonesian Journal of Computer Science Vol. 14 No. 5 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i5.5026

Abstract

Despite the potential benefits of blended learning in higher education, adoption rates in Ugandan universities remain critically low at 29.1%, with significant barriers including inadequate infrastructure, limited institutional support, and mental health challenges affecting both educators and students. This study aimed to develop a Campus Blended Learning Framework (CBLF) to improve blended learning adoption in higher educational institutions in southwestern Uganda. A Design Science Research methodology was employed, incorporating both quantitative and qualitative approaches. Data were collected from three universities: Mbarara University of Science and Technology (MUST), Bishop Stuart University (BSU), and Kabale University (KAB). A total of 1,495 participants (1,051 students and 444 staff members) were surveyed using structured questionnaires based on the Complex Adaptive Blended Learning Framework (CABLF). Ten experts participated in qualitative interviews to evaluate the framework's usability and acceptability. The study identified six critical components for effective blended learning adoption: pedagogy, infrastructure, content, assessment, support, and mental health. Mental health emerged as a significant factor influencing all other components. The proposed CBLF integrates these elements while addressing the unique contextual challenges of developing countries. The Campus Blended Learning Framework provides a comprehensive approach to addressing low adoption rates of blended learning in southwestern Uganda's higher educational institutions. The framework's emphasis on mental health support and contextual adaptation makes it particularly suitable for developing country contexts.
Design and Implementation of mHealth-Based Early Warning Systems for Heart Disease: A Scoping Review Ntwari, Richard; Wesonga, Bob; Vallence Ngabo Maniragaba; Engwau, Tonny; Kabarungi, Moreen
The Indonesian Journal of Computer Science Vol. 14 No. 6 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i6.5051

Abstract

Cardiovascular diseases (CVDs) remain the leading cause of mortality globally, with sub-Saharan Africa including Uganda experiencing a growing burden due to limited access to early detection and specialist care. In response, mobile health (mHealth) technologies have emerged as promising tools to support early cardiac risk detection and intervention, especially in low-resource settings. Following Arksey and O’Malley’s scoping review framework with enhancements a systematic search was conducted across five databases from January 2000 to April 2025. Studies were screened and selected based on predefined inclusion criteria, and data were charted across design elements, outcomes, and implementation contexts. Thematic analysis was applied to synthesize findings.Twenty-seven studies met the inclusion criteria. mHealth-based EWS frequently incorporate wearable sensors, mobile apps, and AI-driven analytics for real-time monitoring and risk prediction. While user-centered design enhances acceptability, clinical efficacy evidence is mixed and scalability remains under-explored. AI/ML integration shows promise in improving prediction and personalization, but challenges persist around interoperability and health system integration.mHealth-based early warning systems hold significant potential to address cardiovascular care gaps in resource-limited settings. To maximize impact, future interventions should prioritize clinical validation, adaptive AI integration, and sustainable scale-up models tailored to local infrastructure and user needs. These insights are critical for guiding policymakers, developers, and researchers toward more effective digital health strategies for CVD prevention.
Co-Authors Annabella Habinka Ejiri Engwau, Tonny Kalungi, Dickson Kawuma Simon Kawuma, Simon Mabberi, Enock Nabaasa, Evarist Ntwari Richard Ntwari, Richard Sabiiti, David Vallence Ngabo Maniragaba Wesonga, Bob