Shafiqur Rahman Jabin

Background: Young people in low- and middle-income countries face social and structural stressors that increase vulnerability to mental health difficulties, while access to formal mental health services remains limited. Digital mental health interventions may expand access to support, but their design requires understanding young people’ lived experiences, coping strategies, and help-seeking behaviors. Objective: This study explored young people's experiences of mental health challenges, coping strategies, and help-seeking behaviors in Kenyan communities to inform the design of youth-centered digital mental health interventions. Methods: We conducted an exploratory qualitative study using 12 focus group discussions with 72 young people aged 18–24 years in urban (Kibra), peri-urban (Kikuyu Town), and rural (Nachu) Kenya. Participants were purposively sampled by gender, education, and geography. Discussions explored mental health experiences, coping, support-seeking, barriers to care, and perspectives on digital mental health tools. Audio-recorded discussions were transcribed verbatim and analyzed using thematic analysis. Reporting followed COREQ guidelines. Results: Six themes emerged: (1) causes of mental distress, including academic pressure, financial hardship, and uncertainty about the future; (2) emotional distress, including sadness, anxiety, loneliness, and overwhelm; (3) stigma and barriers to professional help-seeking; (4) reliance on informal support from friends, family, teachers, and religious leaders; (5) coping strategies, including sports, music, social interaction, and spiritual practices; and (6) openness to digital mental health support. Participants valued digital platforms that offered anonymity, trustworthy information, and culturally relevant content. Conclusions: Young people in Kenyan communities face multiple stressors and barriers to formal mental health care. Youth-centered digital mental health platforms may offer accessible and acceptable support when designed to be confidential, culturally relevant, and linked to existing community support systems.

Background: Digital health interventions have considerable potential to improve healthcare access, quality, and efficiency. Despite increasing adoption, many interventions fail to achieve sustainable implementation or progress beyond pilot phases because they are insufficiently integrated with user needs, organizational workflows, and health system contexts. Although human-centered design (HCD) has improved the usability and acceptability of digital health technologies, its application frequently remains confined to early design activities and is rarely integrated with implementation science throughout the implementation lifecycle. Objective: This study aimed to develop a multi-level, human-centered design framework informed by a cross-project methodological synthesis integrating participatory design and implementation science to support the design, implementation, evaluation, and scale-up of digital health interventions. Methods: A cross-project methodological synthesis was conducted using complementary digital health implementation studies undertaken in Kenya. The empirical corpus included studies spanning adolescent mental health, neonatal clinical decision support, digital health infrastructure, generative artificial intelligence, and frugal digital health innovation. Framework development followed an iterative analytical process combining thematic synthesis, constant comparative analysis, and abductive reasoning. The synthesis organized recurring methodological themes into an integrated framework spanning user, workflow, and system perspectives across the digital health implementation lifecycle. Results: The synthesis identified recurring methodological processes that consistently contributed to successful digital health implementation, including contextual understanding, participatory stakeholder engagement, iterative refinement, workflow integration, organizational readiness, governance, and sustainability. These findings informed the development of a multi-level framework structured around six iterative implementation phases: Understand, Co-design, Prototype, Evaluate, Implement, and Scale, and three interconnected analytical levels: user (micro), workflow (meso), and system (macro). The framework conceptualizes digital health implementation as a continuous sociotechnical process in which sustained adoption and scale-up depend upon coordinated alignment among these three levels throughout the implementation lifecycle. Conclusions: This study advances human-centered design by integrating it with implementation science through an empirically derived, lifecycle-oriented methodological framework for digital health implementation. The proposed framework may provide researchers, developers, practitioners, and policymakers with a structured approach for designing, implementing, evaluating, and scaling digital health interventions while supporting sustainable, context-responsive, and equitable digital health transformation.

Background: Human papillomavirus (HPV) is the most common sexually transmitted infection in women and the primary cause of cervical cancer (CC). HPV vaccination and screening programs have significantly reduced CC incidence and mortality worldwide, preventing up to 70% of HPV-related CC and 90% of genital warts. Developing effective vaccination strategies is therefore essential. Objectives: This study systematically synthesizes the attitudes and health beliefs of Middle Eastern (ME) parents regarding HPV vaccination, examines parental vaccine uptake, and assesses uptake among their children. Methods: This systematic review followed PRISMA guidelines. PubMed/MEDLINE, Web of Science, CINAHL, and Google Scholar were searched for studies published between January 2006 and May 2025. Thirty-three studies were included. A theory-informed narrative synthesis of predominantly quantitative evidence was conducted, with deductive mapping of findings to the health belief model (HBM) constructs. The review protocol was registered in PROSPERO (CRD42025645551). Results: The review included 32 quantitative cross-sectional studies and one qualitative study, involving 18,170 participants. Findings were organized according to HBM constructs, including perceived susceptibility, severity, barriers, benefits, self-efficacy, and cues to action. Parents generally demonstrated limited knowledge of HPV and vaccination. Major barriers included safety concerns, cost, limited access, lack of healthcare provider recommendations, and insufficient information. Cultural and systemic factors were also associated with vaccine uptake. Conclusion: HPV-related knowledge in ME countries remains insufficient and is frequently associated with vaccination attitudes and acceptance across the included studies. Improving uptake requires targeted educational interventions, healthcare provider engagement, public health campaigns, financial support, and policy-level initiatives. Strengthening awareness and addressing structural barriers are critical for enhancing vaccination acceptance. Self-efficacy, where directly reported, appeared to be associated with more favorable vaccine attitudes; however, direct evidence for parental self-efficacy as a distinct HBM construct was limited across the included studies and should not be overstated. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/myprospero/CRD42025645551 .

Background: Mental health disorders are a leading cause of disability among adolescents and young people in Kenya, yet access to appropriate and timely support remains severely limited due to shortages of trained professionals, stigma, financial barriers, and geographical inequities. Digital mental health interventions, particularly those leveraging AI, present a promising opportunity to expand access to culturally relevant, low-stigma mental wellness support in low- and middle-income country (LMIC) settings. However, evidence on the feasibility, usability, and acceptability of AI-powered mental health tools for young people in sub-Saharan Africa remains limited. Objective: This study aims to co-design, develop, and evaluate “Dəˈskəs,” a social media–based digital platform featuring an AI-powered chatbot, to support mental wellness among adolescents and young people in Kenya. The primary objectives are to assess the feasibility of implementation, usability and user experience, acceptability, and the platform’s preliminary applicability across diverse urban, peri-urban, and rural contexts. Methods: The study uses a human-centered design (HCD) methodology, conducted in 3 phases: formative research and co-design, platform development and iterative refinement, and implementation with monitoring and evaluation. Adolescents and young people aged 18 to 24 years will be purposively recruited from Kibra (urban), Kikuyu Town (peri-urban), and Nachu (rural). Formative data will be collected through focus group discussions to inform platform design, content, and functionality. During implementation, participants will use the platform for 2 months. Quantitative data will include baseline behavioral health screening using the Global Appraisal of Individual Needs–Short Screener (GAIN-SS) and platform use analytics. Qualitative data will be collected through interviews and feedback sessions to assess usability, user experience, acceptability, and perceived value. Data will be analyzed using descriptive statistics and thematic qualitative analysis. Results: Field activities for the project started in January 2026. Formative data collection was planned to be completed across the 3 Kenyan study sites by the end of February 2026. Usability and user experience testing was planned to run from March 2026 to June 2026. Findings from the formative work, baseline data, and usability and user experience testing will be reported in subsequent original research publications. The study was funded by the Royal Academy of Engineering, UK in 03/2025 and approved by the Strathmore University Institutional Scientific Ethics Review Committee (SU-ISERC; SU-ISERC 2980/25) approved from November 4, 2026. Conclusions: This protocol describes an adolescent-centered, ethically grounded approach to developing and evaluating an AI-enabled digital mental health intervention in an LMIC context. The findings are expected to contribute to the evidence base on the responsible design and implementation of AI-powered mental health tools for adolescents and young people and to inform future scale-up of accessible, culturally relevant digital mental wellness interventions in Kenya and similar settings.

BACKGROUND Machine-learning systems can identify patients at increased risk of hospital readmission, but predictive performance alone does not ensure that model outputs can be appropriately interpreted or translated into safe clinical action. Effective clinical decision support requires integration of predictive evidence with explanation, contextual reasoning, recommendation generation, and appropriate professional oversight. OBJECTIVE This study aimed to develop and demonstrate an integrated architecture that connects predictive analytics, explainability, semantic reasoning, recommendation generation, and clinician oversight within a unified clinical decision-support workflow. METHODS A design-oriented framework was implemented using a synthetic demonstration dataset and integrated machine-learning prediction with SHAP and LIME explanations, the established Medication Safety Co-Decision Ontology (MSCDO), ontology-based reasoning, recommendation generation, and clinician review. The architecture additionally incorporated uncertainty, fairness, traceability, data governance, and human oversight as cross-cutting trustworthiness considerations. The resulting workflow was demonstrated through a patient-specific scenario in which computational outputs were progressively transformed into semantically enriched information, reasoning states, potential actions, and clinician-controlled decisions. RESULTS The integrated architecture successfully connected predictive outputs with global and patient-specific explanations, semantic representations, ontology-based reasoning, and structured recommendations. In the illustrative patient scenario, an 87% predicted probability was classified as high risk, accompanied by a displayed prediction confidence of 92%. The semantic layer incorporated major contributing factors and linked them to reasoning states involving medication-related risk, polypharmacy, clinical vulnerability, and enhanced monitoring. The framework generated potential actions including medication review, pharmacist consultation, enhanced follow-up, care coordination, and discharge planning. Clinicians had explicit options to accept, modify, or override the generated outputs. CONCLUSIONS The study demonstrates the technical feasibility of integrating predictive analytics, explainability, semantic reasoning, and professional oversight within a single trustworthy clinical decision-support architecture. Rather than positioning artificial intelligence as an autonomous decision-maker, the framework establishes a structured pathway for clinicians to interpret, contextualize, and review computational evidence. External validation, quantitative assessment of fairness and uncertainty, clinician-centered evaluation, and prospective assessment of clinical utility are required before establishing effectiveness or patient-level benefit.

Background: Neonatal mortality remains a leading contributor to under-5 deaths globally, particularly in low- and middle-income countries (LMICs). While machine learning (ML)–based risk prediction models show promise for identifying high-risk neonates, published evidence describing the real-world usability and practical implementation of ML-derived neonatal risk prediction tools within routine clinical workflows in LMIC neonatal units remains limited. Objective: This study aimed to evaluate the usability, user experience, and perceived clinical utility of a paper-based neonatal risk predictor tool derived from an ML model and implemented across 3 Kenyan health facilities. Methods: A postimplementation, cross-sectional usability evaluation was conducted following a 4-month implementation period from August through November 2025. The study was embedded within a longitudinal mixed methods project. Frontline neonatal health care workers (n=10) completed standardized usability instruments, including adapted global usability items (System Usability Scale [SUS]), selected Questionnaire for User Interaction Satisfaction (QUIS) domains, and the Post-Study System Usability Questionnaire (PSSUQ), alongside a project-specific Post-Study Neonatal Utility Questionnaire (PSNUQ). Descriptive statistics (medians, IQRs, and category percentages) were computed. A total of 3 purposively selected neonatal unit leaders participated in semistructured key informant interviews (KIIs), which were analyzed using thematic analysis. Quantitative and qualitative findings were triangulated to contextualize perceptions of usability. Results: Among participating frontline health care workers, overall perceptions of usability were generally favorable. Around 75% (6/8) of respondents reported being willing to use the tool frequently, and 55% (5/9) indicated confidence in using it independently. Around half (5/10) disagreed that the tool was complex, while 22% (2/9) agreed, indicating moderate polarization in perceived complexity. Median PSSUQ composite scores were below 3 across subscales, reflecting positive usability ratings. Overall, 8 of 10 (80%) respondents agreed that the tool supports early identification of high-risk neonates and improves care prioritization within the first 48 hours. However, workflow integration was workload-sensitive: 40% (4/10) reported an increased documentation burden during periods of high patient volume. KIIs identified staffing shortages, parallel documentation systems, and the importance of administrative endorsement as key structural influences on adoption. Conclusions: The neonatal risk predictor tool demonstrated acceptable usability, learnability, and perceived clinical relevance across 3 diverse Kenyan facilities. However, variability in perceived complexity and workload sensitivity highlights the importance of structured onboarding, workflow-aligned integration, and context-aware implementation planning. These findings underscore that translating ML-derived predictor models into clinical practice requires not only technical validity but also strong usability and system-level readiness within routine neonatal care settings. International Registered Report Identifier (IRRID): RR2-10.2196/81996

Background: Digital imaging workflows depend on accurate scheduling, patient identity reconciliation, and reliable metadata continuity to ensure safe image storage and retrieval. Disruptions in these processes may not directly affect image acquisition but can delay access to imaging information and pose significant patient safety risks. Objective: To examine a recurrent ultrasound workflow failure that compromised downstream image availability and to identify practical strategies for preventing recurrence. Methods: A retrospectively reported ultrasound incident was examined using a structured case report approach. The event was analyzed using the International Classification for Patient Safety, the Health Information Technology Classification System, the 18-step medical imaging workflow model, a mini-root cause analysis, and a structured risk-control matrix. These complementary frameworks were integrated to classify the incident, localize workflow failures, identify causal mechanisms, and develop preventive and corrective strategies. Results: The incident was classified as a health information technology–related technical and workflow failure with no confirmed patient harm but clear potential for delayed diagnosis and patient misidentification. The failure originated from missing bookings, modality worklist bypass, and manual patient identity entry, resulting in downstream interoperability failures that delayed image retrieval and interpretation. The mini-root cause analysis identified two interacting causal layers: execution-level workflow deviations and latent system vulnerabilities. Risk-control analysis demonstrated that recurrence was primarily driven by inadequate validation safeguards, weak workflow enforcement, and ineffective exception handling. Conclusion: This case demonstrates that seemingly minor workflow deviations can evolve into clinically significant patient safety risks despite technically successful image acquisition. The integrated multi-framework analytical approach provides a practical method for identifying latent sociotechnical vulnerabilities, informing targeted risk-control strategies, and strengthening the safety and resilience of digital imaging workflows.

Digital health technologies have become integral to health system strengthening, yet their implementation in low-resource settings continues to face persistent challenges related to unreliable infrastructure, limited technical capacity, and constrained financial resources. Although existing digital health evaluation frameworks have advanced understanding of technology adoption, implementation, and sustainability, they frequently treat infrastructure as a contextual factor rather than a core determinant of digital health system performance. This Perspective argues that future evaluation should move beyond technology-centered assessment toward infrastructure-aware evaluation that explicitly recognizes the interdependencies among technical, infrastructural, operational, and economic dimensions. We propose an infrastructure-aware framework for evaluating digital health systems that integrates mixed-methods evaluation and builds upon established implementation science by recognizing infrastructure as a core evaluation domain alongside technical, operational, and economic considerations. The framework positions infrastructure, including energy reliability, internet connectivity, hardware availability, maintenance capacity, and technical support, as a central determinant of implementation feasibility and long-term sustainability. It is informed by implementation science, socio-technical systems thinking, and practical insights from digital health implementation in resource-constrained settings and is illustrated using the Bright Health program in Kenya and Ethiopia. By providing a structured, infrastructure-aware perspective, the proposed framework complements existing implementation science approaches and offers a more comprehensive basis for evaluating digital health systems in low-resource environments. Future research should operationalize the proposed domains, develop standardized evaluation indicators, and empirically validate the framework across diverse technologies and implementation contexts to support more resilient, equitable, and sustainable digital health systems.

Background: Digital health systems are increasingly recognised as critical components of health system strengthening in low- and middle-income countries (LMICs). However, their effectiveness is often constrained by unreliable energy infrastructure, weak governance, and fragmented implementation approaches. Solar-powered digital health systems offer a promising solution, but their scalability depends on integrated governance and sustainable implementation models. Objective: This study aimed to develop a governance and implementation framework for scaling solar-powered digital health systems in LMICs, using empirical evidence from Kenya and Ethiopia. Methods: A mixed-methods study was conducted across selected rural and peri-urban health facilities in Kenya and Ethiopia. Data sources included facility-level infrastructure assessments, key informant interviews with health system stakeholders, and a multi-sectoral validation workshop. Quantitative data were analysed descriptively, while qualitative data were analysed using thematic analysis to indicate governance, coordination, and implementation dimensions. Findings were synthesised into a policy-oriented framework. Results: The study emerged from a hybrid governance model combining national-level policy oversight with decentralised implementation as critical for scalability. Cross-sector coordination, facilitated through a Joint Technical Steering Committee, emerged as essential for aligning health, energy, and information and communication technology (ICT) actors. A phased implementation pathway was developed, incorporating facility readiness assessment, system deployment, interoperability, and lifecycle-oriented maintenance supported by public–private partnerships and blended financing mechanisms. The findings highlight the importance of integrating energy infrastructure into digital health governance to ensure system functionality and sustainability. Conclusions: Solar-powered digital health systems can strengthen health service delivery in resource-constrained settings, but require coordinated governance, sustainable financing, and structured implementation strategies. The proposed framework advances an integrated energy–digital health governance nexus, offering a practical and conceptual pathway for scaling resilient digital health infrastructure in LMICs. Policymakers should prioritise cross-sector collaboration and system-level integration to move beyond pilot-driven approaches and achieve sustainable impact.

Patient safety classification systems are fundamental to surveillance, organizational learning, research, and governance because they enable adverse events and near misses to be organized into standardized categories for comparison and analysis. However, the increasing complexity of health information technology (HIT)–related patient safety incidents challenges the assumptions underpinning conventional classification approaches, as these incidents often emerge from dynamic, distributed, and evolving sociotechnical interactions rather than discrete, time-bounded events. In this Viewpoint, I argue that many of the challenges associated with classifying HIT-related patient safety incidents arise not simply from limitations of individual classification systems but from the inherent representational logic of classification itself. By viewing classification as a knowledge practice rather than merely a technical tool for organizing incident data, I contend that abstraction, boundary-setting, and standardization inevitably simplify complex sociotechnical processes and constrain how safety problems are represented, interpreted, and acted upon. I discuss 4 recurring representational limitations that characterize the application of patient safety classification systems to HIT-related incidents: fragmentation of sociotechnical interactions, loss of temporality and evolving processes, inadequate representation of scale and propagation across systems, and normalization of “use error” through simplified attribution of responsibility. These limitations can contribute to incomplete organizational learning, misaligned safety interventions, and challenges in interpreting and comparing classified patient safety data across health care settings. Rather than arguing against the continued use of patient safety classification systems, I propose that their strengths and limitations should be recognized simultaneously. Classification remains indispensable for surveillance, learning, and governance, but it should be interpreted as one component of a broader sociotechnical understanding of patient safety. Recognizing the representational limits of classification can support more reflexive interpretation of classification-based evidence and encourage complementary approaches that better capture the complexity of HIT-related patient safety.