Facilitators and Barriers to the Sustainability of eHealth Solutions in Low- and Middle-Income Countries: Descriptive Exploratory Study.

BACKGROUND: Despite the widely anticipated benefits of eHealth technologies in enhancing health care service delivery, the sustainable usage of eHealth in transitional countries remains low. There is limited evidence supporting the low sustainable adoption of eHealth in low- and middle-income countries. OBJECTIVE: The aim of this study was to explore the facilitators and barriers to the sustainable use of eHealth solutions in low- and middle-income nations. METHODS: A qualitative descriptive exploratory study was conducted in 4 African nations from September to December 2021. A semistructured interview guide was used to collect the data. Data were audio-recorded and transcribed from the local to the English language verbatim, and the audio data were transcribed. On the basis of the information gathered, we assigned codes to the data, searched for conceptual patterns, and created emerging themes. Data were analyzed thematically using OpenCode software. RESULTS: A total of 49 key informant interviews (10 from Tunisia, 15 from Ethiopia, 13 from Ghana, and 11 from Malawi) were conducted. About 40.8% (20/49) of the study participants were between the ages of 26 and 35 years; 73.5% (36/49) of them were male participants; and 71.4% (35/49) of them had a master's degree or higher in their educational background. Additionally, the study participants' work experience ranged from 2 to 35 years. Based on the data we gathered, we identified 5 themes: organizational, technology and technological infrastructure, human factors, economy or funding, and policy and regulations. CONCLUSIONS: This study explores potential facilitators and barriers to long-term eHealth solution implementation. Addressing barriers early in the implementation process can aid in the development of eHealth solutions that will better fulfill the demands of end users. Therefore, focusing on potential challenges would enhance the sustainability of eHealth solutions in low- and middle-income countries.

Digital literacy level and associated factors among health professionals in a referral and teaching hospital: An implication for future digital health systems implementation.

Background: In Ethiopia and other developing countries, electronic medical record systems and other health information technology are being introduced. However, a small proportion of low-income countries have successfully implemented national health information systems. One cause for this can be the lack of digital literacy among medical practitioners. As a result, this study aimed to assess health professionals' digital literacy level and associated factors in Northwest Ethiopia. Method: A quantitative cross-sectional study was employed among 423 health professionals working in a teaching and referral hospital in Northwest Ethiopia. We modified and applied the European commission's framework for digital competency to assess the level of digital literacy among health professionals. We used stratified random sampling with proportional allocation to the size of the departments in the hospital to select study participants. Data were collected using a semi-structured, self-administered, and pretested questionnaire. Descriptive and binary logistic regression analysis techniques were used to describe respondents' digital literacy level and identify its associated factor, respectively. The odds ratio with 95% CI and value of p were used to assess the strength of the association and statistical significance, respectively. Results: Out of 411 participants, 51.8% (95% CI, 46.9-56.6%) of health professionals had adequate digital literacy. Holding a master's degree (Adjusted OR = 2.13, 95% CI: 1.18-3.85), access to digital technology (AOR = 1.89, 95% CI: 1.12-3.17), having training in digital technology (AOR = 1.65, 95% CI: 1.05-2.59), and having a positive attitude towards digital health technology (AOR = 1.64, 95% CI: 1.02-2.68) were found to be significant factors associated with health professionals digital literacy level of health professionals. Conclusion: Low level of digital literacy among health professionals was observed, with nearly half (48.2%) of them having poor digital literacy levels. Access to digital technology, training on digital technology, and attitude toward digital health technology were significant factors associated with digital literacy. It is suggested to increase computer accessibility, provide a training program on digital health technology, and promote a positive attitude toward this technology to improve the deployment of health information systems.

Organizational and health professional readiness for the implementation of electronic medical record system: an implication for the current EMR implementation in northwest Ethiopia.

OBJECTIVE: The WHO developed a manual outlining the preliminary organizational and health professionals' readiness to implement electronic medical records (EMR). On the other hand, the readiness assessment in Ethiopia only includes the evaluation of health professionals, leaving out organisational readiness components. As a result, this research aimed to determine health professionals' and organizational readiness to implement EMR at a specialized teaching hospital. METHODS: An institutional-based cross-sectional study design was conducted among 423 health professionals and 54 managers. Self-administered and pretested questionnaires were used to collect data. Binary logistic regression analysis was used to identify factors associated with health professionals' readiness for EMR implementation. An OR with a 95% CI and p<0.05 was used to determine the strength of the association and the statistical significance, respectively. RESULTS: In this study, 53.7% management capacity, 33.3% finance and budget capacity, 42.6% operational capacity, 37.0% technology capability and 53.7% organisational alignment among the five dimensions evaluated to assess an organisation's readiness to implement an EMR system. Of 411 health professionals in this study, 173 (42.1%) with (95 CI 37.3% to 46.8%) were ready to implement an EMR system at the hospital. Sex (AOR 2.69, 95% CI 1.73 to 4.18), basic computer training (AOR 1.59, 95% CI 1.02 to 2.46), knowledge of EMR (AOR 1.88, 95% CI 1.19 to 2.97) and attitudes towards EMR (AOR 1.65, 95% CI 1.05 to 2.59) were significantly associated with health professionals' readiness towards EMR system implementation. CONCLUSIONS: Findings showed that most dimensions of organizational readiness for EMR implementation were below 50%. This study also revealed a lower level of EMR implementation readiness among health professionals compared with previous research studies' results. To improve organisational readiness to implement an electronic medical record system, a focus on management capability, financial and budget capability, operational capability, technical capability and organisational alignment was crucial. Likewise, having basic computer training, giving special attention to female health professionals and improving health professionals' knowledge of and attitudes towards EMR could help improve the readiness level of health professionals for implementing an EMR system.

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis.

Introduction: Gynecological cancers pose a significant threat to women worldwide, especially those in resource-limited settings. Human analysis of images remains the primary method of diagnosis, but it can be inconsistent and inaccurate. Deep learning (DL) can potentially enhance image-based diagnosis by providing objective and accurate results. This systematic review and meta-analysis aimed to summarize the recent advances of deep learning (DL) techniques for gynecological cancer diagnosis using various images and explore their future implications. Methods: The study followed the PRISMA-2 guidelines, and the protocol was registered in PROSPERO. Five databases were searched for articles published from January 2018 to December 2022. Articles that focused on five types of gynecological cancer and used DL for diagnosis were selected. Two reviewers assessed the articles for eligibility and quality using the QUADAS-2 tool. Data was extracted from each study, and the performance of DL techniques for gynecological cancer classification was estimated by pooling and transforming sensitivity and specificity values using a random-effects model. Results: The review included 48 studies, and the meta-analysis included 24 studies. The studies used different images and models to diagnose different gynecological cancers. The most popular models were ResNet, VGGNet, and UNet. DL algorithms showed more sensitivity but less specificity compared to machine learning (ML) methods. The AUC of the summary receiver operating characteristic plot was higher for DL algorithms than for ML methods. Of the 48 studies included, 41 were at low risk of bias. Conclusion: This review highlights the potential of DL in improving the screening and diagnosis of gynecological cancer, particularly in resource-limited settings. However, the high heterogeneity and quality of the studies could affect the validity of the results. Further research is necessary to validate the findings of this study and to explore the potential of DL in improving gynecological cancer diagnosis.

Health information exchange policy and standards for digital health systems in africa: A systematic review.

Lack of interoperability and integration between heterogeneous health systems is a big challenge to realize the potential benefits of eHealth. To best move from siloed applications to interoperable eHealth solutions, health information exchange (HIE) policy and standards are necessary to be established. However, there is no comprehensive evidence on the current status of HIE policy and standards on the African continent. Therefore, this paper aimed to systematically review the status of HIE policy and standards which are currently in practice in Africa. A systematic search of the literature was conducted from Medical Literature Analysis and Retrieval System Online (MEDLINE), Scopus, Web of Science, and Excerpta Medica Database (EMBASE), and a total of 32 papers (21 strategic documents and 11 peer-reviewed papers) were selected based on predefined criteria for synthesis. Results revealed that African countries have paid attention to the development, improvement, adoption, and implementation of HIE architecture for interoperability and standards. Synthetic and semantic interoperability standards were identified for the implementation of HIE in Africa. Based on this comprehensive review, we recommend that comprehensive interoperable technical standards should be set at each national level and should be guided by appropriate governance and legal frameworks, data ownership and use agreements, and health data privacy and security guidelines. On top of the policy issues, there is a need to identify a set of standards (health system standards, communication, messaging standards, terminology/vocabulary standards, patient profile standards, privacy and security, and risk assessment) and implement them throughout all levels of the health system. On top of this, we recommend that the Africa Union (AU) and regional bodies provide the necessary human resource and high-level technical support to African countries to implement HIE policy and standards. To realize the full potential of eHealth in the continent, it is recommended that African countries need to have a common HIE policy, interoperable technical standards, and health data privacy and security guidelines. Currently, there is an ongoing effort by the Africa Centres for Disease Control and Prevention (Africa CDC) towards promoting HIE on the continent. A task force has been established from Africa CDC, Health Information Service Provider (HISP) partners, and African and global HIE subject matter experts to provide expertise and guidance in the development of AU policy and standards for HIE. Although the work is still ongoing, the African Union shall continue to support the implementation of HIE policy and standards in the continent. The authors of this review are currently working under the umbrella of the African Union to develop the HIE policy and standard to be endorsed by the head of states of the Africa Union. As a follow-up publication to this, the result will be published in mid-2022.

The Influenceof Parallel Reporting SystemsonData Quality and Information Use in Northwest Ethiopia: Qualitative Study

Background:Ethiopia utilisesthedistrict health information systemfor health information management. However,the lower level health structure seems inaccurate in comparisonto theparallel reportingsystem, withlimited evidence on its effect ondata quality and information use.Therefore,the present study aimed to assess the influence of a parallel reporting system on data quality and information use at the lower level structuresof the Amhara region, Northwest Ethiopia.Methods:The study was conducted in five districts of the Amhara region using an explanatory case study design. Twenty respondents were interviewed from the 1st­30thApril 2021,usinga semi-structured key informant interview(KII)guide with multiple probes to explore relevant information. The data was transcribed into English and transferred to the Open-Code 4.02 software for analysis. Textual data werecoded, and themes were identified from the synthesis. Inductive thematic analysis was applied to identify the relationships among the emerging themes in order todraw a relevant conclusion. Results:Five themeswere emerged fromthe analysis, includingthe current practice of parallel reporting, a program area of parallel reporting, the influence of parallel reporting, reasonsfor parallel reporting,and means to avoid parallel reporting.Likewise, parallelreportingwasdone at the district level and at the point of service delivery. The respondents described maternal and child health programs often usingparallel reporting. Parallel reporting was described as havingundesirable impacts on routinely collected health data quality and use. Moreover, it increases the work burden; andaffects service quality,the the satisfactionlevelsof clients and staff, and the overall efficiency. The main reasons for practicingparallel reporting were:missing important data elements in DHIS2, single language, varying stakeholders' interests, and lack of conductinga partnerforum.Conclusion and implication:Against the national health information system'sguiding principlesand vision, parallelreporting is practicedat the lower health system levelsfor various programs. Therefore, a corrective measure should be taken to achieve the country's information revolution (IR) agenda. To avoid parallel reporting mechanisms, it is recommended that regular partner forums at the district level must be strengthened, important data elements should beincorporated into the DHIS 2, and additional language platforms should be be included in theDHIS2 system.

Strengthening the national health information system through a capacity-building and mentorship partnership (CBMP) programme: a health system and university partnership initiative in Ethiopia.

BACKGROUND: A strong health information system (HIS) is one of the essential building blocks for a resilient health system. The Ministry of Health (MOH) of Ethiopia is working on different initiatives to strengthen the national HIS. Among these is the Capacity-Building and Mentorship Partnership (CBMP) Programme in collaboration with public universities in Ethiopia since November 2017. This study aims to evaluate the outcomes and share experiences of the country in working with universities to strengthen the national HIS. METHODS: The study employed a mixed-methods approach that included 247 health organizations (health offices and facilities) of CBMP-implementing woredas (districts) and 23 key informant interviews. The programme focused on capacity-building and mentoring facilities and woreda health offices. The status of HIS was measured using a connected woreda checklist before and after the intervention. The checklist consists of items related to HIS infrastructure, data quality and administrative use. The organizations were classified as emerging, candidate or model based on the score. The findings were triangulated with qualitative data collected through key informant interviews. RESULTS: The results showed that the overall score of the HIS implementation was 46.3 before and 74.2 after implementation of the programme. The proportion of model organizations increased from 1.2% before to 31.8% after the programme implementation. The health system-university partnership has provided an opportunity for higher education institutions to understand the health system and tune their curricula to address real-world challenges. The partnership brought opportunities to conduct and produce local- and national-level evidence to improve the HIS. Weak ownership, poor responsiveness and poor perceptions of the programme were mentioned as major challenges in programme implementation. CONCLUSION: The overall HIS has shown substantial progress in CBMP implementation woredas. A number of facilities became models in a short period of time after the implementation of the programme. The health system-university partnership was found to be a promising approach to improve the national HIS and to share the on-the-ground experiences with the university academicians. However, weak ownership and poor responsiveness to feedback were the major challenges identified as needing more attention in future programme implementation.

Level and contributing factors of health data quality and information use in two districts in Northwest Ethiopia: social-ecological perspective.

BACKGROUND: The health management information system has been implemented at all levels of healthcare delivery to ensure quality data production and information use in Ethiopia. Including the capacity-building activities and provision of infrastructure, various efforts have been made to improve the production and use of quality health data though the result is still unsatisfactory. This study aimed to examine the quality of health data and use in Wogera and Tach-Armacheho districts and understand its barriers and facilitators. METHODS: The study utilized a mixed-method; for the quantitative approach, institution-based cross-sectional study was conducted to determine the quality of health data and use by 95 departments in the two districts. The qualitative approach involved 16 in-depth interviewees from Wogera district. A descriptive Phenomenological design was used to explore factors influencing the quality and use of health data. The quantitative data were expressed descriptively with tables, graphs, and percent whereas the qualitative data were analyzed with content analysis guided by the social-ecological model framework. RESULT: The average levels of information use for Wogera and Tach-Armacheho districts were estimated at 29 and 35.9, respectively. The overall average level of accuracy of reports for six different health services in the HCs of Wogera and Tach Armacheho districts were 0.95 and 0.86, respectively. The qualitatively identified factors that influence the production and use of quality health data include valuing data, getting staff training, being a patriotic staff, and getting supportive supervision, were identified from individual-level characteristics; similarly, coaching, supportive supervision, and peer-to-peer learning from relational/interpersonal level characteristics, and organizational culture, incentive, infrastructure establishing accountability, and staff turnover, were identified from organizational level characteristics. CONCLUSION: The quality of data and routine information utilization was low and were influenced by a number of actors presented in and around the health system including individual, interpersonal, and organizational characteristics. Incentive affects data quality and information use directly or indirectly after modifying factors at all levels of the social-ecological model. Therefore, interventions should gear towards addressing multiple social-ecological factors of the health system concomitantly or intervene on incentive which has a multifaceted effect on the outcome.

Developing and Piloting TB Medication and Refilling Reminder System in Ethiopia.

This project followed waterfall model to develop a context tailored and user-friendly reminder system to support home based TB treatment. Piloting was conducted on expert and patient levels. We developed a flexible and user-friendly web-based system that allows medication and refiling reminder. Participants agreed on its usefulness despite infrastructure and personal related challenges.

Development of automated text-message reminder system to improve uptake of child vaccination in Ethiopia.

INTRODUCTION: Non-attendance and delay for vaccination schedules remains a big challenge to healthcare workers. Among the frequently mentioned reasons for missed vaccination in children is forgetfulness of caretakers to show up in vaccination schedules. This necessitates developing an automated reminder system with integration of mobile technologies. OBJECTIVES: This paper aimed to develop and test an automated mobile text message reminder system in the local context of Ethiopia. METHODS: This system is developed using iterative development process through phases of requirement analysis, design, development, testing and refinement. Requirement gathering was done before development of the system. Front end application was developed using java technologies while back end applications were developed with oracle database. Finally, pilot testing of the automated reminder system was done on 30 participants. RESULTS: The automated system has been developed based on requirements. The text message reminder system has two components: 1. Web based application for client registration and automatic reminder scheduling; 2. SMS application for automatic SMS text messaging. In the pilot testing, all the text messages (100%) were dispatched from the automated system to the respective participants. Finally, the system has shown a notification that the text messages have been sent successfully. CONCLUSION: Text message reminder system has been developed for routine childhood immunization program in Ethiopian context. Text message based mHealth interventions should be carefully designed, developed, tested and refined before actual implementation.

A Comparison of Electronic Medical Record Data to Paper Records in Antiretroviral Therapy Clinic in Ethiopia: What is affecting the Quality of the Data?

BACKGROUND: Anti-Retroviral Therapy (ART) care is a lifelong treatment, which needs accurate and reliable data collected for long period of time. Poor quality of medical records data remains a challenge and is directly related to the quality of care of patients. To improve this, there is an increasing trend to implement electronic medical record (EMR) in hospitals. However, there is little evidence on the impact of EMR on the quality of health data in low- resource setting hospitals like Ethiopia. This comparative study aims to fill this evidence gap by assessing the completeness and reliability of paper-based and electronic medical records and explore the challenges of ensuring data quality at the Anti-Retroviral Therapy (ART) clinic at the University of Gondar Referral Hospital in Northwest Ethiopia. METHODS: An institution-based comparative cross-sectional study, supplemented with a qualitative approach was conducted from February 1 to March 30, 2017 at the ART clinic of the University of Gondar Hospital. A total of 250 medical records having both electronic and paper-based versions were collected and assessed. A national ART registration form which consists of 40 ART data elements was used as a checklist to assess completeness and reliability dimensions of data quality on medical records of patients on HIV care. Kappa statistics were computed to describe the level of data agreement between paper-based and electronic records across patient characteristics. In-depth interviews were conducted using semi-structured questionnaires with ten key informants to explore the challenges related with the quality of medical records. Responses of the key informant interviews were analyzed using thematic analysis. RESULTS: The overall completeness of medical records was 78% with 95% CI (70.8% - 85.1%) in paper-based and 76% with 95%CI (67.8% - 83.2%) EMR. The data reliability measured in Kappa statistics shows strong agreements on the socio-demographic data such as educational status 0.93 (0.891, 0.963), WHO staging 0.86 (0.808, 0.906); general appearance 0.83 (0.755, 0.892) and patient referral record 0.87 (0.795, 0.932). The major challenges hindering good data quality was the current side by side dual data documentation practice (the need to document both on the paper and the EMR for a single record), patient overload and low data documentation practice of health workers. CONCLUSION: The overall completeness of ART medical records was still slightly better in paper-based records than EMR. The main reason affecting the EMR data quality was the current dual documentation practice both on the paper and electronic for each patient in the hospital and the high load of patients in the clinic. The hospital management need to decide to use either the paper or the electronic system and build the capacity of health workers to improve data quality in the hospital.