Designing and delivering bioinformatics project-based learning in East Africa.

BACKGROUND: The Eastern Africa Network for Bioinformatics Training (EANBiT) has matured through continuous evaluation, feedback, and codesign. We highlight how the program has evolved to meet challenges and achieve its goals and how experiential learning through mini projects enhances the acquisition of skills and collaboration. We continued to learn and grow through honest feedback and evaluation of the program, trainers, and modules, enabling us to provide robust training even during the Coronavirus disease 2019 (COVID-19) pandemic, when we had to redesign the program due to restricted travel and in person group meetings. RESULTS: In response to the pandemic, we developed a program to maintain "residential" training experiences and benefits remotely. We had to answer the following questions: What must change to still achieve the RT goals? What optimal platforms should be used? How would we manage connectivity and data challenges? How could we avoid online fatigue? Going virtual presented an opportunity to reflect on the essence and uniqueness of the program and its ability to meet the objective of strengthening bioinformatics skills among the cohorts of students using different delivery approaches. It allowed an increase in the number of participants. Evaluating each program component is critical for improvement, primarily when feedback feeds into the program's continuous amendment. Initially, the participants noted that there were too many modules, insufficient time, and a lack of hands-on training as a result of too much focus on theory. In the subsequent iterations, we reduced the number of modules from 27 to five, created a harmonized repository for the materials on GitHub, and introduced project-based learning through the mini projects. CONCLUSION: We demonstrate that implementing a program design through detailed monitoring and evaluation leads to success, especially when participants who are the best fit for the program are selected on an appropriate level of skills, motivation, and commitment.

Generalizability of machine learning in predicting antimicrobial resistance in E. coli: a multi-country case study in Africa.

BACKGROUND: Antimicrobial resistance (AMR) remains a significant global health threat particularly impacting low- and middle-income countries (LMICs). These regions often grapple with limited healthcare resources and access to advanced diagnostic tools. Consequently, there is a pressing need for innovative approaches that can enhance AMR surveillance and management. Machine learning (ML) though underutilized in these settings, presents a promising avenue. This study leverages ML models trained on whole-genome sequencing data from England, where such data is more readily available, to predict AMR in E. coli, targeting key antibiotics such as ciprofloxacin, ampicillin, and cefotaxime. A crucial part of our work involved the validation of these models using an independent dataset from Africa, specifically from Uganda, Nigeria, and Tanzania, to ascertain their applicability and effectiveness in LMICs. RESULTS: Model performance varied across antibiotics. The Support Vector Machine excelled in predicting ciprofloxacin resistance (87% accuracy, F1 Score: 0.57), Light Gradient Boosting Machine for cefotaxime (92% accuracy, F1 Score: 0.42), and Gradient Boosting for ampicillin (58% accuracy, F1 Score: 0.66). In validation with data from Africa, Logistic Regression showed high accuracy for ampicillin (94%, F1 Score: 0.97), while Random Forest and Light Gradient Boosting Machine were effective for ciprofloxacin (50% accuracy, F1 Score: 0.56) and cefotaxime (45% accuracy, F1 Score:0.54), respectively. Key mutations associated with AMR were identified for these antibiotics. CONCLUSION: As the threat of AMR continues to rise, the successful application of these models, particularly on genomic datasets from LMICs, signals a promising avenue for improving AMR prediction to support large AMR surveillance programs. This work thus not only expands our current understanding of the genetic underpinnings of AMR but also provides a robust methodological framework that can guide future research and applications in the fight against AMR.

Research ethics and artificial intelligence for global health: perspectives from the global forum on bioethics in research.

BACKGROUND: The ethical governance of Artificial Intelligence (AI) in health care and public health continues to be an urgent issue for attention in policy, research, and practice. In this paper we report on central themes related to challenges and strategies for promoting ethics in research involving AI in global health, arising from the Global Forum on Bioethics in Research (GFBR), held in Cape Town, South Africa in November 2022. METHODS: The GFBR is an annual meeting organized by the World Health Organization and supported by the Wellcome Trust, the US National Institutes of Health, the UK Medical Research Council (MRC) and the South African MRC. The forum aims to bring together ethicists, researchers, policymakers, research ethics committee members and other actors to engage with challenges and opportunities specifically related to research ethics. In 2022 the focus of the GFBR was "Ethics of AI in Global Health Research". The forum consisted of 6 case study presentations, 16 governance presentations, and a series of small group and large group discussions. A total of 87 participants attended the forum from 31 countries around the world, representing disciplines of bioethics, AI, health policy, health professional practice, research funding, and bioinformatics. In this paper, we highlight central insights arising from GFBR 2022. RESULTS: We describe the significance of four thematic insights arising from the forum: (1) Appropriateness of building AI, (2) Transferability of AI systems, (3) Accountability for AI decision-making and outcomes, and (4) Individual consent. We then describe eight recommendations for governance leaders to enhance the ethical governance of AI in global health research, addressing issues such as AI impact assessments, environmental values, and fair partnerships. CONCLUSIONS: The 2022 Global Forum on Bioethics in Research illustrated several innovations in ethical governance of AI for global health research, as well as several areas in need of urgent attention internationally. This summary is intended to inform international and domestic efforts to strengthen research ethics and support the evolution of governance leadership to meet the demands of AI in global health research.

The Ugandan sickle Pan-African research consortium registry: design, development, and lessons.

BACKGROUND: Sub-Saharan Africa bears the highest burden of sickle cell disease (SCD) globally with Nigeria, Democratic Republic of Congo, Tanzania, Uganda being the most affected countries. Uganda reports approximately 20,000 SCD births annually, constituting 6.67% of reported global SCD births. Despite this, there is a paucity of comprehensive data on SCD from the African continent. SCD registries offer a promising avenue for conducting prospective studies, elucidating disease severity patterns, and evaluating the intricate interplay of social, environmental, and genetic factors. This paper describes the establishment of the Sickle Pan Africa Research Consortium (SPARCo) Uganda registry, encompassing its design, development, data collection, and key insights learned, aligning with collaborative efforts in Nigeria, Tanzania, and Ghana SPARCo registries. METHODS: The registry was created using pre-existing case report forms harmonized from the SPARCo data dictionary and ontology to fit Uganda clinical needs. The case report forms were developed with SCD data elements of interest including demographics, consent, baseline, clinical, laboratory and others. That data was then parsed into a customized REDCap database, configured to suit the optimized ontologies and support retrieval aggregations and analyses. Patients were enrolled from one national referral and three regional referral hospitals in Uganda. RESULTS: A nationwide electronic patient-consented registry for SCD was established from four regional hospitals. A total of 5,655 patients were enrolled from Mulago National Referral Hospital (58%), Jinja Regional Referral (14.4%), Mbale Regional Referral (16.9%), and Lira Regional Referral (10.7%) hospitals between June 2022 and October 2023. CONCLUSION: Uganda has been able to develop a SCD registry consistent with data from Tanzania, Nigeria and Ghana. Our findings demonstrate that it's feasible to develop longitudinal SCD registries in sub-Saharan Africa. These registries will be crucial for facilitating a range of studies, including the analysis of SCD clinical phenotypes and patient outcomes, newborn screening, and evaluation of hydroxyurea use, among others. This initiative underscores the potential for developing comprehensive disease registries in resource-limited settings, fostering collaborative, data-driven research efforts aimed at addressing the multifaceted challenges of SCD in Africa.

Digital tools for youth health promotion: principles, policies and practices in sub-Saharan Africa.

Although digital health promotion (DHP) technologies for young people are increasingly available in low- and middle-income countries (LMICs), there has been insufficient research investigating whether existing ethical and policy frameworks are adequate to address the challenges and promote the technological opportunities in these settings. In an effort to fill this gap and as part of a larger research project, in November 2022, we conducted a workshop in Cape Town, South Africa, entitled 'Unlocking the Potential of Digital Health Promotion for Young People in Low- and Middle-Income Countries'. The workshop brought together 25 experts from the areas of digital health ethics, youth health and engagement, health policy and promotion and technology development, predominantly from sub-Saharan Africa (SSA), to explore their views on the ethics and governance and potential policy pathways of DHP for young people in LMICs. Using the World Café method, participants contributed their views on (i) the advantages and barriers associated with DHP for youth in LMICs, (ii) the availability and relevance of ethical and regulatory frameworks for DHP and (iii) the translation of ethical principles into policies and implementation practices required by these policies, within the context of SSA. Our thematic analysis of the ensuing discussion revealed a willingness to foster such technologies if they prove safe, do not exacerbate inequalities, put youth at the center and are subject to appropriate oversight. In addition, our work has led to the potential translation of fundamental ethical principles into the form of a policy roadmap for ethically aligned DHP for youth in SSA.

HIVseqDB: a portable resource for NGS and sample metadata integration for HIV-1 drug resistance analysis.

Summary: Human immunodeficiency virus (HIV) remains a public health threat, with drug resistance being a major concern in HIV treatment. Next-generation sequencing (NGS) is a powerful tool for identifying low-abundance drug resistance mutations (LA-DRMs) that conventional Sanger sequencing cannot reliably detect. To fully understand the significance of LA-DRMs, it is necessary to integrate NGS data with clinical and demographic data. However, freely available tools for NGS-based HIV-1 drug resistance analysis do not integrate these data. This poses a challenge in interpretation of the impact of LA-DRMs, mainly for resource-limited settings due to the shortage of bioinformatics expertise. To address this challenge, we present HIVseqDB, a portable, secure, and user-friendly resource for integrating NGS data with associated clinical and demographic data for analysis of HIV drug resistance. HIVseqDB currently supports uploading of NGS data and associated sample data, HIV-1 drug resistance data analysis, browsing of uploaded data, and browsing and visualizing of analysis results. Each function of HIVseqDB corresponds to an individual Django application. This ensures efficient incorporation of additional features with minimal effort. HIVseqDB can be deployed on various computing environments, such as on-premises high-performance computing facilities and cloud-based platforms. Availability and implementation: HIVseqDB is available at https://github.com/AlfredUg/HIVseqDB. A deployed instance of HIVseqDB is available at https://hivseqdb.org.

A unified Foot and Mouth Disease dataset for Uganda: evaluating machine learning predictive performance degradation under varying distributions.

In Uganda, the absence of a unified dataset for constructing machine learning models to predict Foot and Mouth Disease outbreaks hinders preparedness. Although machine learning models exhibit excellent predictive performance for Foot and Mouth Disease outbreaks under stationary conditions, they are susceptible to performance degradation in non-stationary environments. Rainfall and temperature are key factors influencing these outbreaks, and their variability due to climate change can significantly impact predictive performance. This study created a unified Foot and Mouth Disease dataset by integrating disparate sources and pre-processing data using mean imputation, duplicate removal, visualization, and merging techniques. To evaluate performance degradation, seven machine learning models were trained and assessed using metrics including accuracy, area under the receiver operating characteristic curve, recall, precision and F1-score. The dataset showed a significant class imbalance with more non-outbreaks than outbreaks, requiring data augmentation methods. Variability in rainfall and temperature impacted predictive performance, causing notable degradation. Random Forest with borderline SMOTE was the top-performing model in a stationary environment, achieving 92% accuracy, 0.97 area under the receiver operating characteristic curve, 0.94 recall, 0.90 precision, and 0.92 F1-score. However, under varying distributions, all models exhibited significant performance degradation, with random forest accuracy dropping to 46%, area under the receiver operating characteristic curve to 0.58, recall to 0.03, precision to 0.24, and F1-score to 0.06. This study underscores the creation of a unified Foot and Mouth Disease dataset for Uganda and reveals significant performance degradation in seven machine learning models under varying distributions. These findings highlight the need for new methods to address the impact of distribution variability on predictive performance.

Virtual reality technology for surgical learning: qualitative outcomes of the first virtual reality training course for emergency and essential surgery delivered by a UK-Uganda partnership.

INTRODUCTION: The extensive resources needed to train surgeons and maintain skill levels in low-income and middle-income countries (LMICs) are limited and confined to urban settings. Surgical education of remote/rural doctors is, therefore, paramount. Virtual reality (VR) has the potential to disseminate surgical knowledge and skill development at low costs. This study presents the outcomes of the first VR-enhanced surgical training course, 'Global Virtual Reality in Medicine and Surgery', developed through UK-Ugandan collaborations. METHODS: A mixed-method approach (survey and semistructured interviews) evaluated the clinical impact and barriers of VR-enhanced training. Course content focused on essential skills relevant to Uganda (general surgery, obstetrics, trauma); delivered through: (1) hands-on cadaveric training in Brighton (scholarships for LMIC doctors) filmed in 360°; (2) virtual training in Kampala (live-stream via low-cost headsets combined with smartphones) and (3) remote virtual training (live-stream via smartphone/laptop/headset). RESULTS: High numbers of scholarship applicants (n=130); registrants (Kampala n=80; remote n=1680); and attendees (Kampala n=79; remote n=556, 25 countries), demonstrates widespread appetite for VR-enhanced surgical education. Qualitative analysis identified three key themes: clinical education and skill development limitations in East Africa; the potential of VR to address some of these via 360° visualisation enabling a 'knowing as seeing' mechanism; unresolved challenges regarding accessibility and acceptability. CONCLUSION: Outcomes from our first global VR-enhanced essential surgical training course demonstrating dissemination of surgical skills resources in an LMIC context where such opportunities are scarce. The benefits identified included environmental improvements, cross-cultural knowledge sharing, scalability and connectivity. Our process of programme design demonstrates that collaboration across high-income and LMICs is vital to provide locally relevant training. Our data add to growing evidence of extended reality technologies transforming surgery, although several barriers remain. We have successfully demonstrated that VR can be used to upscale postgraduate surgical education, affirming its potential in healthcare capacity building throughout Africa, Europe and beyond.

Airway microbiome signature accurately discriminates Mycobacterium tuberculosis infection status.

Mycobacterium tuberculosis remains one of the deadliest infectious agents globally. Amidst efforts to control TB, long treatment duration, drug toxicity, and resistance underscore the need for novel therapeutic strategies. Despite advances in understanding the interplay between microbiome and disease in humans, the specific role of the microbiome in predicting disease susceptibility and discriminating infection status in tuberculosis still needs to be fully investigated. We investigated the impact of M.tb infection and M.tb-specific IFNγ immune responses on airway microbiome diversity by performing TB GeneXpert and QuantiFERON-GOLD assays during the follow-up phase of a longitudinal HIV-Lung Microbiome cohort of individuals recruited from two large independent cohorts in rural Uganda. M.tb rather than IFNγ immune response mainly drove a significant reduction in airway microbiome diversity. A microbiome signature comprising Streptococcus, Neisseria, Fusobacterium, Prevotella, Schaalia, Actinomyces, Cutibacterium, Brevibacillus, Microbacterium, and Beijerinckiacea accurately discriminated active TB from Latent TB and M.tb-uninfected individuals.