A Roadmap for Building Data Science Capacity for Health Discovery and Innovation in Africa

A collaborative approach to advancing research and training in Public Health Data Science-challenges, opportunities, and lessons learnt

The unprecedented availability of increasingly complex, voluminous, and multi-dimensional data as well as the emergence of data science as an evolving field provide ideal opportunities to address the multi-faceted public health challenges faced by low and middle income countries (LMIC), especially those in sub-Saharan Africa. However, there is a severe lack of well-trained data scientists and home-grown educational programs to enable context-specific training. The lack of human capacity and resources for public health data analysis as well as the dire need to use modern technology for better understanding and possible intervention cannot be dealt with currently available educational programs and computing infrastructure, demanding a great deal of collaboration and investments within Africa and with the Global North This paper describes processes undertaken to establish sustainable research training programs and to train a new generation of data scientists with knowledge, mentoring, professional skills, and research immersion. The goal is to position them for rigorous, biomedically grounded and ethically conscious Public Health Data Science practice with a focus on Ethiopia and Kenya. The programs are realized through partnership among Columbia University (CU, USA), Addis Ababa University (AAU, Ethiopia), and the University of Nairobi (UoN, Kenya). In this paper, we describe the collaborative project named "Advancing Public Health Research in Eastern Africa through Data Science Training (APHREA-DST)" delving on its conceptualization, implementation framework and activities undertaken. We adopted both qualitative and quantitative approaches to understand the needs of the stakeholders for such educational and training programs. Through harmonized online surveys and stakeholder engagements via focus group discussions in Ethiopia and Kenya, a curriculum was developed for a masters degree program in Public Health Data Science (PHDS). Moreover, the engagement with local projects in both countries as well as active collaboration with other data science related projects in Africa under DSI-Africa consortium benefited the project to start the M. Sc. program successfully. So far, the launching of the graduate program in both countries and the two-cycle experience sharing program done at Columbia University as well as the numerous MoUs signed between partners for data sharing and internships are the major successes of the project. In this paper, we discuss in detail the challenges faced as well as the existing opportunities and lessons learnt this far in implementing this tripartite collaborative teaching and research project.

Current data science capacity building initiatives for health researchers in LMICs: global & regional efforts

Background

Data science approaches have proved crucial for generating major insights to address public health challenges. While such approaches have played significant roles during the COVID-19 pandemic, there has been limited investment in capacity building in data science skills and infrastructure for health researchers in LMICs.

Objectives

This review aims to identify current health data science capacity building initiatives and gaps in Africa, Asia, and Latin America and the Caribbean (LAC), to support knowledge sharing and collaborations, and inform future initiatives and associated investment.

Methods

We conducted a literature review using PubMed and Scopus, supplemented by a grey literature search on Google to identify relevant initiatives. Articles were screened based on inclusion criteria.

Findings

From 212 records, 85 met inclusion criteria, with 20 from PubMed and Scopus, and 65 from grey literature. The majority of programmes are tailored to specific disease areas, varying by region. Despite these efforts, there are limited initiatives with a clear, documented strategy on data science capacity building to accelerate global research insights, with the majority adopting a fragmented approach.

Conclusion and future directions

Despite the integration of data science approaches into health research initiatives in LMICs, there is a need for a standardised framework on data science capacity building to facilitate multidisciplinary and global collaboration. Structured approaches, inter-disciplinary, inter-regional connections and robust impact measurement will all be vital for advancing health research insights in these settings.

Harnessing genomics and translational research to improve health in Africa: a report of the 13th African Society of Human Genetics meeting in Dar es Salaam, Tanzania

The thirteenth conference of the African Society of Human Genetics with the theme "harnessing genomics and translational research to improve health in Africa" was held in Dar es Salaam, Tanzania, in August 2021, using a hybrid in-person and virtual model for participation in the wake of COVID-19 pandemic. During the meeting, African research across various human genetics disciplines was presented, including talks on the genetics of infectious and non-communicable diseases, population genetics, and translational research. The meeting also featured presentations on pharmacogenomics, genetics of developmental disorders, cancer genetics and genetics of rare diseases. In-depth discussions on ethical legal and social issues in genomics research and community and patient engagement were also key sessions of this meeting. The primary focus of the conference and the discussions was how to translate the wealth of genomic research in the continent into improved health outcomes in the continent. In this report, we summarize the key scientific research relevant to Africa presented and discussed during the meeting providing an overview of the progress of human genetics in the continent. We also discuss opportunities and challenges of harnessing genomics for health improvement in Africa.

Health Data Sciences and Cardiovascular Disease in Africa: Needs and the Way Forward

PURPOSE OF REVIEW

The rising burden of cardiovascular disease (CVD) in Africa is of great concern. Health data sciences is a rapidly developing field which has the potential to improve health outcomes, especially in low-middle income countries with burdened healthcare systems. We aim to explore the current CVD landscape in Africa, highlighting the importance of health data sciences in the region and identifying potential opportunities for application and growth by leveraging health data sciences to improve CVD outcomes.

RECENT FINDINGS

While there have been a number of initiatives aimed at developing health data sciences in Africa over the recent decades, the progress and growth are still in their early stages. Its maximum potential can be leveraged through adequate funding, advanced training programs, focused resource allocation, encouraging bidirectional international partnerships, instituting best ethical practices, and prioritizing data science health research in the region. The findings of this review explore the current landscape of CVD and highlight the potential benefits and utility of health data sciences to address CVD challenges in Africa. By understanding and overcoming the barriers associated with health data sciences training, research, and application in the region, focused initiatives can be developed to promote research and development. These efforts will allow policymakers to form informed, evidence-based frameworks for the prevention and management of CVDs, and ultimately result in improved CVD outcomes in the region.

Digital Competencies and Training Approaches to Enhance the Capacity of Practitioners to Support the Digital Transformation of Public Health: Rapid Review of Current Recommendations

Background

The COVID-19 pandemic highlighted gaps in the public health workforce's capacity to deploy digital technologies while upholding ethical, social justice, and health equity principles. Existing public health competency frameworks have not been updated to reflect the prominent role digital technologies play in contemporary public health, and public health training institutions are seeking to integrate digital technologies in their curricula.

Objective

As a first step in a multiphase study exploring recommendations for updates to public health competency frameworks within the Canadian public health context, we conducted a rapid review of literature aiming to identify recommendations for digital competencies, training approaches, and inter- or transdisciplinary partnerships that can enhance public health practitioners' capacity to support the digital transformation of public health.

Methods

Following the World Health Organization's (2017) guidelines for rapid reviews, a systematic search was conducted on Ovid MEDLINE, Ovid Embase, ERIC (Education Resources Information Center), and Web of Science for peer-reviewed articles. We also searched Google Scholar and various public health agency and public health association websites for gray literature using search terms related to public health, digital health, practice competencies, and training approaches. We included articles with explicit practice competencies and training recommendations related to digital technologies among public health practitioners published between January 2010 and December 2022. We excluded articles describing these concepts in passing or from a solely clinical perspective.

Results

Our search returned 2023 titles and abstracts, of which only 12 studies met the inclusion criteria. We found recommendations for new competencies to enable public health practitioners to appropriately use digital technologies that cut across all existing categories of the core competencies for public health framework of the Public Health Agency of Canada. We also identified a new competency category related to data, data systems management, and governance. Training approaches identified include adapted degree-awarding programs like combined public health and informatics or data science degree programs and ongoing professional certifications with integration of practice-based learning in multi- and interdisciplinary training. Disciplines suggested as important to facilitate practice competency and training recommendations included public health, public health informatics, data, information and computer sciences, biostatistics, health communication, and business.

Conclusions

Despite the growth of digital technologies in public health, recommendations about practice competencies and training approaches necessary to effectively support the digital transformation of public health remain limited in the literature. Where available, evidence suggests the workforce requires new competencies that cut across and extend existing public health competencies, including new competencies related to the use and protection of new digital data sources, alongside facilitating health communication and promotion functions using digital media. Recommendations also emphasize the need for training approaches that focus on interdisciplinarity through adapted degree-awarding public health training programs and ongoing professional development.

Data sharing: A Long COVID perspective, challenges, and road map for the future

'Long COVID' is the term used to describe the phenomenon in which patients who have survived a COVID-19 infection continue to experience prolonged SARS-CoV-2 symptoms. Millions of people across the globe are affected by Long COVID. Solving the Long COVID conundrum will require drawing upon the lessons of the COVID-19 pandemic, during which thousands of experts across diverse disciplines such as epidemiology, genomics, medicine, data science, and computer science collaborated, sharing data and pooling resources to attack the problem from multiple angles. Thus far, there has been no global consensus on the definition, diagnosis, and most effective treatment of Long COVID. In this work, we examine the possible applications of data sharing and data science in general with a view to, ultimately, understand Long COVID in greater detail and hasten relief for the millions of people experiencing it. We examine the literature and investigate the current state, challenges, and opportunities of data sharing in Long COVID research.

Predicting infectious disease for biopreparedness and response: A systematic review of machine learning and deep learning approaches

The complex, unpredictable nature of pathogen occurrence has required substantial efforts to accurately predict infectious diseases (IDs). With rising popularity of Machine Learning (ML) and Deep Learning (DL) techniques combined with their unique ability to uncover connections between large amounts of diverse data, we conducted a PRISMA systematic review to investigate advances in ID prediction for human and animal diseases using ML and DL. This review included the type of IDs modeled, ML and DL techniques utilized, geographical distribution, prediction tasks performed, input features utilized, spatial and temporal scales, error metrics used, computational efficiency, uncertainty quantification, and missing data handling methods. Among 237 relevant articles published between January 2001 and May 2021, highly contagious diseases in humans were most often represented, including COVID-19 (37.1%), influenza/influenza-like illnesses (9.3%), dengue (8.9%), and malaria (5.1%). Out of 37 diseases identified, 51.4% were zoonotic, 37.8% were human-only, and 8.1% were animal-only, with only 1.6% economically significant, non-zoonotic livestock diseases. Despite the number of zoonoses, 86.5% of articles modeled humans whereas only a few articles (5.1%) contained more than one host species. Eastern Asia (32.5%), North America (17.7%), and Southern Asia (13.1%) were the most represented locations. Frequent approaches included tree-based ML (38.4%) and feed-forward neural networks (26.6%). Articles predicted temporal incidence (66.7%), disease risk (38.0%), and/or spatial movement (31.2%). Less than 10% of studies addressed uncertainty quantification, computational efficiency, and missing data, which are essential to operational use and deployment. This study highlights trends and gaps in ML and DL for ID prediction, providing guidelines for future works to better support biopreparedness and response. To fully utilize ML and DL for improved ID forecasting, models should include the full disease ecology in a One-Health context, important food and agricultural diseases, underrepresented hotspots, and important metrics required for operational deployment.

Malaria and Helminthic Co-Infection during Pregnancy in Sub-Saharan Africa: A Systematic Review and Meta-Analysis

Malaria and helminthic co-infection during pregnancy causes fetomaternal haemorrhage and foetal growth retardation. This study determined the pooled burden of pregnancy malaria and helminthic co-infection in sub-Saharan Africa. CINAHL, EMBASE, Google Scholar, Scopus, PubMed, and Web of Science databases were used to retrieve data from the literature, without restricting language and publication year. The Joanna Briggs Institute's critical appraisal tool for prevalence studies was used for quality assessment. STATA Version 14.0 was used to conduct the meta-analysis. The I2 statistics and Egger's test were used to test heterogeneity and publication bias. The random-effects model was used to estimate the pooled prevalence at a 95% confidence interval (CI). The review protocol has been registered in PROSPERO, with the number CRD42019144812. In total, 24 studies (n = 14,087 participants) were identified in this study. The pooled analysis revealed that 20% of pregnant women were co-infected by malaria and helminths in sub-Saharan Africa. The pooled prevalence of malaria and helminths were 33% and 35%, respectively. The most prevalent helminths were Hookworm (48%), Ascaris lumbricoides (37%), and Trichuris trichiura (15%). Significantly higher malaria and helminthic co-infection during pregnancy were observed. Health systems in sub-Saharan Africa must implement home-grown innovative solutions to underpin context-specific policies for the early initiation of effective intermittent preventive therapy.