The utilization of artificial intelligence (AI) and machine learning (ML) for health in Nigeria: a rapid review

Introduction

The impact or potential of artificial intelligence (AI) and other forms of machine learning (ML) on health and health care delivery, including virtual health assistants, precision imaging, robotic surgery and AI-assisted drug discovery, has been described globally (1). Examples of remote patient monitoring and telemedicine continue to expand the patient experience and increase access and personalized patience care (2). These technological applications have the potential of leveraging human intelligence through various options, including ML, reinforcement learning (RL) or deep learning (DL). There are also applications leveraging computer vision (CV) and natural language processing (NLP), which guide decisions made based on extracted information from images/videos and human languages (3). The development of these algorithms and models and their deployment in health care has progressed over time since their onset in the 1950s (4). This progression is seen with the world’s first artificial medical consultant in 1971, the development of DXplain in 1980 to support clinical diagnosis and extensive leaps in the 2000’s, with examples including the development of the Watson system used in detecting RNA binding proteins for the diagnosis of amyotrophic lateral sclerosis.

The utilization and adoption of these learning options in the health sector is still suboptimal, with huge opportunities for AI use, ranging from virtual assistants, ambient assistants and autonomous virtual assistants providing care through connected systems (5). These can be deployed across the health spectrum of preventive, promotive, curative, rehabilitative and palliative care, as envisioned by the World Health Organization (WHO) through primary health care (PHC) (6). Digital rehabilitation (DR) or e-rehabilitation often refers to the use of technology and digital tools to support and enhance the recovery of individuals from illness, injuries, and medical conditions (7). This use of technology and digital tools is also currently changing practices with the integration of AI in the rehabilitation field (8). Despite these opportunities, AI in health is currently still assessed as “emergent”, where the development of an AI system is said to be important in the majority of Organization for Economic Co-operation and Development (OECD) countries, with only the USA and UK reaching the highest maturity, with a national AI health care ecosystem in place (9).

The deployment of these tools for health is guided by policies and regulations and dependent on health institutions and practitioners to drive health professional capacity building, address equity and data governance and cybersecurity applications (10). The delivery of intelligent health services is built on functional systems with a robust technological infrastructure, often providing seamless communication for efficient delivery. Furthermore, the literature on AI deployment is often reported from high-income or developed countries to a greater extent than in low- and middle-income countries (LMICs) (11). The use of Ambient Notes, a generative AI tool for clinical documentation, is being successfully implemented across the USA (12). When viewed globally, the evidence on the utilization of AI in health is least in the WHO African region, when compared to other regions (13).

A recent study in Thailand identifies multiple barriers to access and sharing of data in LMICs, including unreliable internet, lack of information technology (IT) equipment, as well as uneven resource distribution, required for the development, adoption and utilization of AI tools in resource limited settings (14). Identifying such barriers and strengthening these in specific contexts and settings will remain important in guiding various policies and investments towards the utilization of these tools in public health.

While the adoption of AI in consumer markets has been fast, its adoption in health is much slower. A review highlighted easier adoption in health administration compared to clinical care. It also posits that, while the service sector continues to change rapidly, health care processes and clinicians change more slowly (15). Some of the suggested hindrances include ethical consensus, regulation, clinician education, and return on investments (ROI) (15). In the African region, these challenges include the high cost of required infrastructure, reliable data on health and diseases, and underrepresentation in global research, amongst many others (16).

In 2024, a state of AI in health care in Africa report estimated the highest level of application in telemedicine and remote patient monitoring (31.7%) and the lowest in diagnostics (6.7%) and drug discovery (1.7%). The report also notes that the majority of the use of AI applications for health was reported from Kenya, South Africa, Uganda, Nigeria and Ghana (17). A bibliometric analysis review by Ezugwu et al. [2023] also highlighted the increasing publication of AI in health in sub-Saharan Africa (SSA), with the highest collaborations within the African continent in South Africa, Nigeria, Kenya and Ghana; a sharp increase in these publications between 2016 and 2022 (18). These publications document the evolution of AI and the deployment of ML and DL, including the commonly used convolutional neural networks (CNNs) across these countries.

Nigeria, like most countries in the African continent, continues to lag in the systematic adoption of AI and its integration into the health care system. Currently, Nigeria has a projected population of over 230 million and a population doubling time of 34 years (19). This health system is expected to provide health services to these populations, with the majority of health costs funded through out-of-pocket payments, where families/individuals have to pay for health care services from their personal resources (20). Leveraging innovations of AI in the Nigerian health system is expected to provide services to over 200 million persons annually, could increase efficiencies, lower costs of health care delivery and uptake, and eventually improve health outcomes.

Rapid reviews provide timely and efficient information based on available literature to guide or drive programmatic or policy change through engagements with key stakeholders (21). There has been an increased trend in the use of this approach to guide evidence-based decision making, especially in the health sector (22-24). This rapid review aims to highlight the available evidence of AI use for health in Nigeria and identify gaps limiting the required to drive ethical and equitable utilization and regulation of these tools. We present this article in accordance with the PRISMA reporting checklist (available at https://jmai.amegroups.com/article/view/10.21037/jmai-2025-1-227/rc).

Methods

We conducted a review of available literature on AI use for health in Nigeria following a search conducted on the PubMed/Medline database. This rapid review focused on AI and ML use across various aspects of the health system in the target geography. We were guided using key concepts for rapid reviews and methodological decisions in our design and for the conduct of our rapid review by the Cochrane Rapid Reviews Methods Group (RRMG) (21,25). Our search strategy was built around the research question: “How are artificial intelligence or machine learning tools used to enhance health and health care access in Nigeria?”

We reviewed and discussed our findings, highlighting key themes, trends, and study recommendations relating to the usage of AI to improve health outcomes directly or indirectly. Additionally, we also discussed the implications of some of these findings for public health practice in Nigeria. We also reviewed the study objectives and noted word frequencies and targets in the study aims. This was done following the listing and tabulation of study aims for all 23 studies based on the listed disease/health focus, study target and intervention outcomes and subsequent keywords were extracted.

We also categorized all studies based on findings, recommendations and conclusions on AI in health in Nigeria into: “Strongly support”, “Supports”, “Urges AI use”, “Acknowledges challenges” and “Caution”.

Study and source eligibility

This review focused on available literature between 2020 and 2025. Eligibility criteria, as shown in Table 1, included studies conducted in Nigeria or the authors’ affiliation to an institution located in Nigeria. Only papers with at least one listed author affiliated to an institution in Nigeria were included in the review. This approach allowed for an understanding of domestic scholarship frequency on AI research and levels of internal and domestic collaboration while understanding institution interest and support for in AI research. Also included were studies with available abstracts or full papers available in the English language and all studies conducted in humans.

Search methods

We conducted a literature search between 20 and 27 September 2025 using the key phrases: Artificial Intelligence, Machine Learning, Use/utilization, Health/Healthcare AND Nigeria. The search query was used was: (((((((“artificial intelligence”[MeSH Terms] OR “ai artificial intelligence”[All Fields]) AND “machine learning”[MeSH Terms] AND “utilize”[All Fields]) OR “use”[All Fields]) AND “health”[All Fields]) OR “health care”[All Fields]) AND “health interventions”[All Fields] AND “nigeria”[All Fields]) OR “federal republic of nigeria”[All Fields]) AND ((y_5[Filter]) AND (excludepreprints[Filter]) AND (humans[Filter]) AND (english[Filter])) using the Medline/PubMed database platforms and cross-referenced using Google Scholar. No grey literature was included in the search.

Data extraction and analysis

After removing duplicates, the identified studies were reviewed as shown in Figure 1 for relevance by two authors (T.N. & J.E.), after which one author (T.N.) proceeded to screen the remaining. The second author (J.E.) cross-checked the studies that were removed for accuracy. Following the screening, datasets were extracted from the included studies and reports were summarized using Microsoft Excel. The extracted data were summarised using Microsoft Excel, and findings were presented as summary tables, maps and proportions. Figures were generated using Microsoft tools, including the word cloud generator and ^©Microsoft OpenStreet Map. The details extracted from the studies for the review include the following: author name, year of publication, country of study, study design, and study aim. Six studies that initially appeared to have met the inclusion criteria were subsequently removed (summary included as supplementary information). This was done following discussions and consensus by at least two authors. This dual review process ensured the reduction of biases, literature completeness or any selection errors, thus enhancing the reliability and accuracy of the literature selection process. For the six publications finally excluded (Table S1), all authors agreed that, while the authors and data were from Nigeria, the authors’ affiliations were to institutions outside Nigeria, following an extensive review of the full publication.

Figure 1 PRISMA flow diagram for identification, screening and inclusion of publications for rapid review.

The included studies were further categorised based on the thematic areas of AI utilization in health, based on study aims. This was following an initial data extraction by one author and subsequent verification by the second author for output completeness. All authors reached a consensus on the categorization of the study conclusions regarding AI use in Nigeria. Thematic areas of AI use in health are listed and explained in Appendix 1.

Results

Figure 2 shows the trend of available literature and publications on AI use in Nigeria. Fewer than 10 papers were published prior to 2019. The increasing publication trend shows a first peak in 2021 with 22 publications and an 168% increase noted from a second peak in 2025 with 59 publications. The annual publication frequency between 2020 and 2025 ranged from 14 in 2020 to 59 in 2025. The number of publications in 2025 increased by 73% following plateaus in 2023 and 2024.

Figure 2 Trends of literature hits following initial search of AI use for health in Nigeria, 1995–2025. AI, artificial intelligence.

A summary of the 23 selected literature (26-48) is shown in Table 2, with almost 70% of the papers published after 2023. We show that 39.1% (9/23) of the papers were published in 2025, 30% (7/23) in 2024, and 13% (3/23) in 2023 and 2022 each. There was no paper published in 2021, and only one of the papers reviewed was published in 2020.

Also, cross-sectional studies were the most commonly used study methods, with 30% (7/23) amongst the reviewed publications. Three papers (13%) reported narrative/descriptive reviews while two papers (9%) each reported the conduct of clinical trials, and model performance evaluations. The remaining nine publications (48%) include a descriptive explorative qualitative study (n=1), regression analysis (n=1), retrospective study (n=1), disease prediction model evaluation (n=1), comparative review (n=1), study protocol (n=1), study pilot (n=1), opinion piece (n=1) and case study (n=1). We also note that only one out of the 23 identified publications reviewed was a qualitative study (26).

The interventions documented in the studies reviewed focused on knowledge evaluation and learning (31%), different aspects of modelling (17%), as well as public health surveillance (13%) and risk prediction (13%). Fewer publications document AI deployment for diagnostics (9%), direct patient care (4%) and AI health policy (4%), as seen in Figure 3.

Figure 3 Areas of AI intervention assessments in the reviewed literature (n=23). AI, artificial intelligence.

In 2025, the nine publications were categorised into thematic areas of disease knowledge evaluation (n=4) (27-30), pandemic/epidemic modelling (n=1) (31), disease forecasting (n=1) (32), patient care (n=1) (26), risk reduction (n=1) (33) and spatial modelling (n=1) (34). A similar pattern was seen in the seven publications published in 2024 with disease forecasting (n=1) (35), knowledge evaluation (n=2) (36,37), public health surveillance (n=2) (38,39) and one each on predictive modelling (40) and spatial modelling (41). No publication in 2024 related to direct patient care. Two publications in 2023 were on diagnostics (42,43) and one on public health policy (44). In 2022, one publication each related to knowledge evaluation (45), public health surveillance (46) and risk prediction (47). There was only one study published in 2020 included in the review and it related to risk prediction (48).

Also, 30% of the study outputs related to knowledge evaluation and learning regarding AI, with 7/23 papers reviewed (Figure 4). Other study outputs included 2/23 (9%) each in cardiology, mortality assessments, health care service (including immunization) and disease diagnosis or prevention. One paper each reported on disease surveillance, oncology, outbreak preparedness and health policy.

Figure 4 Tree map showing focus areas of health interventions across the reviewed literature.

As seen in the word cloud in Figure 5, keywords from the study aim of the reviewed publications showed a prominence of “Pharmacy”, “education” and “students” while specific disease entities include “COVID-19”, “Hepatitis B and C”, “Hypertension” and “schistosomiasis”. Health care professional fields mentioned were “Oncology”, “Pharmacy”, “Nursing”, “Cardiology”, “Public health” and “Academia/Teaching”.

Figure 5 Word cloud showing key words from the aims/objectives of the reviewed literature.

In total, 65% (13/23) of the papers reviewed either “strongly supported” or “supported” AI use or adoption in the health sector in Nigeria. The summary of study findings or recommendations presented in Table 3 shows that six out of the 23 papers drew conclusions that strongly support the adoption and use of AI in the Nigerian health sector, while seven conclusions implied support for AI use. In 5 (21.7%) of the papers reviewed, the authors’ conclusions urged policymakers to deploy AI in specific areas. On the other hand, 21.7% (5/23) of the recommendations acknowledged the challenges of AI adoption, while the remaining studies urged caution in the use of AI in health.

In Figure 6, we show the geographical location of the institution of the first author of the selected papers we reviewed. We found that the majority, 11/23 (47.8%), of the first authors’ affiliations were to Nigerian institutions. The locations of author affiliations were to institutions in UK (21.7%), the USA (13.0%), South Africa (4.3%) and Australia (4.3%). We also found that two of the papers had first authors with dual affiliations to institutions in both Nigeria and Canada (8.7%).

Figure 6 Distribution of the first author’s institutional affiliation location by country.

As seen in Figure 7, study sites in the publications reviewed were located in 26 out of the 36 states, plus the Federal Capital Territory (FCT), in Nigeria (72.2%). There were no sites reported in the other 11 states. The states without a study site were located in the South-South zone (five out of six states), Southeast zone (two out of five states), and North Central zone (three out of seven states, including FCT). One of the publications based on a study conducted in Nigeria did not report on the specific locations of sites (30).

Figure 7 Frequency of study sites in states across Nigeria documented in selected literature.

The states with the highest frequency of site location were Lagos with 5 sites (12%), Osun and Oyo each with 3 sites (7%) and 2 sites (5%) each located in Adamawa, Anambra, Ekiti, FCT, Jigawa, Kano, Kwara and Yobe states. The other 15 states had one site each.

Discussion

Our review shows that the majority of the publications on AI that we reviewed support the utilisation of tools to enhance health care in Nigeria. While this was a common finding, some evidence acknowledged challenges (capacities of healthcare workers, uninterrupted internet access, information and communication technology (ICT) infrastructure, data protection concerns) in the deployment and integration of AI in health, thus urging caution in its use. These challenges are similar to those most reported across most of Africa (49).

There are still gaps regarding knowledge, attitude, acceptance and practices of AI tools in Nigeria. We show that the majority of the publications focused on knowledge and learning evaluations. This may be related to previously reported low use of AI in the educational landscape by Bali et al. in 2024 (50). While this report is across educational institutions, the training of healthcare personnel often starts in these institutions. In our view, such institutions may benefit from updating course content and curriculum. These updates may help to enhance AI awareness and tools utilization, as part of their training. Knowledge/learning evaluations were also mainly on students in training (49). No evaluations were reported on health care workers or practitioners in any of the studies we reviewed. There is a need to better understand how the practice of health workers may be affected or influenced by AI tools in delivering care.

There has been increasing expansion of ChatGPT functionality, including medical writing, virtual assistants and other applications in health care and education (51). Addressing some limitations to its use, concerns over plagiarism and credibility can also be addressed through various knowledge management options. ChatGPT, part of the pre-training transformer (GPT) model developed by OpenAI, is one of the most commonly used DL models and healthcare workers training on its ethical use could be beneficial in the long run. We recommend that educational institutions which provide training for health providers and other ICT-related programmes should also update the current curricula to enhance the optimization of knowledge and ethical use of ChatGPT and other AI models.

Evidence on AI use was generated based on data from study sites across over 70% of the states in Nigeria in the studies reviewed. The study sites’ locations may be influenced by the location of historical long-standing health institutions, disease epidemiology and demographics. The lower reported localisation of research on AI in some of the states in the North Central and South-South could be indicative of some interest in the field of AI and health, but also corroborates with the distributions of health research and universities in the country. Some evidence alludes to study sites being often closer to the geographic location of research institutions or universities (52).

We noted an upward trend in scientific outputs in Nigeria on AI, especially after 2020. This trend is similar to a global trend reported by Xie et al. (53). The global increase reported by Xie et al. is mainly due to contributions from the USA and China. No country from the African continent is amongst the top 20 contributing countries reported in this study. A similar pattern is seen in the author’s institutional affiliations. A review of AI in health across the WHO regions by Okeibunor et al. [2023] also shows the lack of evidence from the African region, with only one publication from the WHO Regional Office for Africa (AFRO) conducted in Nigeria (13).

In our study, we show that most of the contributions were from first authors were affiliated with institutions in Nigeria and also see affiliations to the UK, USA, South Africa and Australia. Despite the low numbers, this shows increasing local capacities and contributions to science on AI specific to the Nigerian context and must be encouraged. It is also indicative of collaboration across institutions, mainly in the USA and the UK. Similar collaborations have been reported from South Africa and Egypt, mainly also with the USA and UK (54). These locations may be associated with the recent crises of brain drain in Nigeria’s health sector, with migration of health workers to American and British institutions (55). Over 113,000 health care workers are reported to have emigrated to the UK between 2021 and 2022, and a recent survey indicates that less than 20% of Nigerian doctors intended to remain in Nigeria (56,57). South-South collaboration is lagging in this context, with only one institutional affiliation in South Africa.

Challenges to collaboration and cooperation within the research landscape call for research investments in the Global South led and co-creation by locally grounded actors from the continent (58). This especially heightens the need for implementation research and the need for changes in “parachute research” while also “decolonizing” health (59,60). Evidence based on data sets on AI from developed countries cannot guide policy decisions in Africa. Nigeria, like other countries in Africa, must build on frameworks like the African Union (AU)’s Continental Artificial Intelligence Strategy [2024] to build capacity towards leveraging AI in promoting social and economic development (61). This strategy is a step in the right direction; however, not much progress in its implementation has been achieved, with some concerns reported on its governance capacities and regulation enforcement on the continental (62). There is a need to have such evidence recalibrated with context specificity to generate applicable evidence in the Global South (63). This further makes a case for more qualitative research to provide evidence on the “why” and “how” these tools can best be deployed in Nigeria (64). Our review only reported one publication which used qualitative methods in its study.

Legal and ethical regulation of AI deployment in the health sector is critical for the optimal integration in the Nigerian health sector. However, ethical AI adoption must be guided by “trustworthy AI” and be based on ethical principles including human autonomy, prevention of harm, fairness and explicability, as presented by the High Expert Group on AI in 2020 to the European Commission (EC) (65). This kind of guidance could fit into the AU’s continental strategy. It behoves regulatory bodies, health practitioners academia to collaborate towards ensuring the right use of these tools within Nigeria’s cultural context (66). Ethical committees that give credence to various research and studies play a key role, especially in the interconnection between product development and design through the spectrum of implementation research, ensuring research and participant safety (67,68). Working through data protection and sharing frameworks, regulatory bodies must have access to all the necessary information required to properly guide policy change and optimize legal frameworks needed for AI application and integration in healthcare in Nigeria.

Summary of six publications (69-74) excluded from the review also show majority of the publications in 2024 and 2025, which align with our conclusions of increased documentation in the last 2 years. The majority of the six papers (90%) assessed different types of modelling and risk prediction.

Limitations

Our review only focused on selected literature based on our search criteria for evidence specific to AI deployment in health in Nigeria. We acknowledge the limitations related to a rapid review and the possibility of leaving out other literature with important evidence related to this specific area, including those with publication dates after our search was concluded.

We also acknowledge the limitations of rapid reviews, noting a less rigorous and methodological literature review process when compared to the gold standards of systematic reviews (65). We, however, have been guided by the updated recommendations of the RRMG to limit the overall effect on our study outcomes.

Lastly, our review is also limited generalization of its findings and conclusions as the evidence presented is specific to Nigeria. We note that more research needs to be carried out to understand the drivers for academic research on AI in Nigeria and the requirements to bridge identified gaps. We believe our findings can provide guidance or context for future research on AI use within the health landscape, especially at subnational levels.

Conclusions

Documented evidence on the utilization of AI and ML tools for health in Nigeria, while relatively few, has focused mainly on knowledge evaluations, surveillance, risk prediction and multiple types of modelling. Available evidence on the deployment of AI tools in health in Nigeria is with little or no evidence on how health practice care by health care workers may be affected or influenced by the use of AI for health care delivery. However, there has been a relatively marginal increase in publications on AI in health since 2020, mainly by authors affiliated with Nigerian institutions.

While the majority of the studies we reviewed recommend the adaptation of AI tools and their use in health, a few publications also highlight the challenges of unethical and unregulated integration in the health space, while urging cautious use. The AI adoption trend may remain low without innovative policy changes that harness the efficiencies AI can offer to the health system, especially when approached holistically. As such, there is need to strengthen collaboration across academia, health practitioners and regulatory bodies to strengthen ethical and legal frameworks for the design, development, evaluation and monitoring of AI tool deployments in Nigeria. Such a framework could enhance better regulation, alignment with the AU’s continental AI strategy, and promote Nigeria’s evidence contribution in this rapidly changing landscape.

Acknowledgments

None.

Footnote

Reporting Checklist: The authors have completed the PRISMA reporting checklist. Available at https://jmai.amegroups.com/article/view/10.21037/jmai-2025-1-227/rc

Peer Review File: Available at https://jmai.amegroups.com/article/view/10.21037/jmai-2025-1-227/prf

Funding: None.

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://jmai.amegroups.com/article/view/10.21037/jmai-2025-1-227/coif). The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Bajwa J, Munir U, Nori A, et al. Artificial intelligence in healthcare: transforming the practice of medicine. Future Healthc J 2021;8:e188-94. [Crossref] [PubMed]
2. Faiyazuddin M, Rahman SJQ, Anand G, et al. The Impact of Artificial Intelligence on Healthcare: A Comprehensive Review of Advancements in Diagnostics, Treatment, and Operational Efficiency. Health Sci Rep 2025;8:e70312. [Crossref] [PubMed]
3. Kaul V, Enslin S, Gross SA. History of artificial intelligence in medicine. Gastrointest Endosc 2020;92:807-12. [Crossref] [PubMed]
4. Kaul V, Enslin S, Gross SA. History of artificial intelligence in medicine. Gastrointestinal Endoscopy 2020;92:807-12.
5. Hirani R, Noruzi K, Khuram H, et al. Artificial Intelligence and Healthcare: A Journey through History, Present Innovations, and Future Possibilities. Life (Basel) 2024;14:557. [Crossref] [PubMed]
6. Behera BK, Prasad R, Shyambhavee. Primary health-care goal and principles. Healthcare Strategies and Planning for Social Inclusion and Development 2022;221-39.
7. MohammadNamdar M. How AI-Based Digital Rehabilitation Improves End-User Adherence: Rapid Review. JMIR Rehabil Assist Technol 2025;12:e69763. [Crossref] [PubMed]
8. Alshami A, Nashwan A, AlDardour A, et al. Artificial Intelligence in rehabilitation: A narrative review on advancing patient care. Rehabilitacion 2025;59:100911.
9. Castonguay A, Wagner G, Motulsky A, et al. AI maturity in health care: An overview of 10 OECD countries. Health Policy 2024;140:104938. [Crossref] [PubMed]
10. Panteli D, Adib K, Buttigieg S, et al. Artificial intelligence in public health: promises, challenges, and an agenda for policy makers and public health institutions. Lancet Public Health 2025;10:e428-32. [Crossref] [PubMed]
11. Yang J, Dung NT, Thach PN, et al. Generalizability assessment of AI models across hospitals in a low-middle and high income country. Nat Commun 2024;15:8270. [Crossref] [PubMed]
12. Poon EG, Lemak CH, Rojas JC, et al. Adoption of artificial intelligence in healthcare: survey of health system priorities, successes, and challenges. J Am Med Inform Assoc 2025;32:1093-100. [Crossref] [PubMed]
13. Okeibunor JC, Jaca A, Iwu-Jaja CJ, et al. The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review. Front Public Health 2023;11:1102185. [Crossref] [PubMed]
14. Kaushik A, Barcellona C, Mandyam NK, et al. Challenges and Opportunities for Data Sharing Related to Artificial Intelligence Tools in Health Care in Low- and Middle-Income Countries: Systematic Review and Case Study From Thailand. J Med Internet Res 2025;27:e58338. [Crossref] [PubMed]
15. Davenport TH, Glaser JP. Factors governing the adoption of artificial intelligence in healthcare providers. Discov Health Syst 2022;1:4. [Crossref] [PubMed]
16. Ndembi N, Rammer B, Fokam J, et al. Integrating artificial intelligence into African health systems and emergency response: Need for an ethical framework and guidelines. J Public Health Afr 2025;16:876. [Crossref] [PubMed]
17. International Centre of Expertise in Montreal on Artificial Intelligence (CEIMIA). State of AI in Healthcare in Sub-Saharan Africa. 2024. Available online: https://doi.org/10.5281/zenodo.12635888
18. Ezugwu AE, Oyelade ON, Ikotun AM, et al. Machine Learning Research Trends in Africa: A 30 Years Overview with Bibliometric Analysis Review. Arch Comput Methods Eng 2023; Epub ahead of print. [Crossref]
19. UNFPA. Nigeria Population 2025 - United Nations Population Fund. Available online: https://www.unfpa.org/data/world-population/NG
20. World Bank Group. Out-of-pocket expenditure (% of current health expenditure) - Nigeria. Available online: https://data.worldbank.org/indicator/SH.XPD.OOPC.CH.ZS?locations=NG
21. Gartlehner G, Nussbaumer-Streit B, Devane D, et al. Rapid reviews methods series: Guidance on assessing the certainty of evidence. BMJ Evid Based Med 2024;29:50-4. [Crossref] [PubMed]
22. MacPherson M, Rourke S. The Power of Rapid Reviews for Bridging the Knowledge-to-Action Gap in Evidence-Based Virtual Health Care. J Med Internet Res 2024;26:e54821. [Crossref] [PubMed]
23. Langlois EV, Straus SE, Antony J, et al. Using rapid reviews to strengthen health policy and systems and progress towards universal health coverage. BMJ Glob Health 2019;4:e001178. [Crossref] [PubMed]
24. Moore G, Redman S, Rudge S, et al. Do policy-makers find commissioned rapid reviews useful? Health Res Policy Syst 2018;16:17. [Crossref] [PubMed]
25. Garritty C, Gartlehner G, Nussbaumer-Streit B, et al. Cochrane Rapid Reviews Methods Group offers evidence-informed guidance to conduct rapid reviews. J Clin Epidemiol 2021;130:13-22. [Crossref] [PubMed]
26. Olawade DB, Ojo IO, Oisakede EO, et al. Artificial intelligence in Nigerian oncology practice: A qualitative exploration of oncologists' perspectives. J Cancer Policy 2025;45:100626. [Crossref] [PubMed]
27. Olawade DB, Clement David-Olawade A, Rotifa OB, et al. Artificial intelligence in Nigerian nursing education: Are future nurses prepared for the digital revolution in healthcare? Nurse Educ Pract 2025;87:104511. [Crossref] [PubMed]
28. Elnaem MH, Okuyan B, Mubarak N, et al. Students' acceptance and use of generative AI in pharmacy education: international cross-sectional survey based on the extended unified theory of acceptance and use of technology. Int J Clin Pharm 2025;47:1097-108. [Crossref] [PubMed]
29. Clement David-Olawade A, Wada OZ, Adeniji YJ, et al. Artificial intelligence readiness among healthcare students in Nigeria: A cross-sectional study assessing knowledge gaps, exposure, and adoption willingness. Int J Med Inform 2025;204:106085. [Crossref] [PubMed]
30. Ayanwale MA, Adelana OP, Bamiro NB, et al. Large language models and GenAI in education: Insights from Nigerian in-service teachers through a hybrid ANN-PLS-SEM approach. F1000Res 2025;14:258. [Crossref] [PubMed]
31. Oyebola KM, Ligali FC, Owoloye AJ, et al. Machine learning insights on the effectiveness of non-pharmaceutical interventions against COVID-19 in Nigeria. Int Health 2025;17:809-19. [Crossref] [PubMed]
32. Akingbola A, Abiodun A, Ojo O, et al. Cholera Outbreak in Nigeria: History, Review of Socioeconomic and Meteorological Drivers, Diagnostic Challenges, and Artificial Intelligence Integration. Glob Health Epidemiol Genom 2025;2025:8898076. [Crossref] [PubMed]
33. Musti A. Usability and Usefulness of SMS-Based Artificial Intelligence Intervention (Mwana) on Breastfeeding Outcomes in Lagos, Nigeria: Pilot App Development Study. JMIR Form Res 2025;9:e65157. [Crossref] [PubMed]
34. Utazi CE, Yankey O, Chaudhuri S, et al. Geostatistical and machine learning approaches for high-resolution mapping of vaccination coverage. Spat Spatiotemporal Epidemiol 2025;54:100744. [Crossref] [PubMed]
35. Antia SE, Ajaero CC, Kalu AU, et al. Artificial Intelligence and Cardiology Practice in Nigeria: Are We Ready? Niger J Clin Pract 2024;27:933-7. [Crossref] [PubMed]
36. Mohammed M, Kumar N, Zawiah M, et al. Psychometric Properties and Assessment of Knowledge, Attitude, and Practice Towards ChatGPT in Pharmacy Practice and Education: a Study Protocol. J Racial Ethn Health Disparities 2024;11:2284-93. [Crossref] [PubMed]
37. Orok E, Okaramee C, Egboro B, et al. Pharmacy students' perception and knowledge of chat-based artificial intelligence tools at a Nigerian University. BMC Med Educ 2024;24:1237. [Crossref] [PubMed]
38. Adeleke O, Adebayo S, Aworinde H, et al. Machine learning evaluation of a hypertension screening program in a university workforce over five years. Sci Rep 2024;14:30255. [Crossref] [PubMed]
39. Adedinsewo DA, Morales-Lara AC, Afolabi BB, et al. Artificial intelligence guided screening for cardiomyopathies in an obstetric population: a pragmatic randomized clinical trial. Nat Med 2024;30:2897-906. [Crossref] [PubMed]
40. Ahmad Amshi H, Prasad R, Sharma BK, et al. How can machine learning predict cholera: insights from experiments and design science for action research. J Water Health 2024;22:21-35. [Crossref] [PubMed]
41. Adeyinka DA, Muhajarine N. Geographic inequities in neonatal survival in Nigeria: a cross-sectional evidence from spatial and artificial neural network analyses. J Biosoc Sci 2024;56:896-919. [Crossref] [PubMed]
42. Ajuwon BI, Richardson A, Roper K, et al. The development of a machine learning algorithm for early detection of viral hepatitis B infection in Nigerian patients. Sci Rep 2023;13:3244. [Crossref] [PubMed]
43. Makau-Barasa L, Assefa L, Aderogba M, et al. Performance evaluation of the AiDx multi-diagnostic automated microscope for the detection of schistosomiasis in Abuja, Nigeria. Sci Rep 2023;13:14833. [Crossref] [PubMed]
44. Olawade DB, Wada OJ, David-Olawade AC, et al. Using artificial intelligence to improve public health: a narrative review. Front Public Health 2023;11:1196397. [Crossref] [PubMed]
45. Onyema EM, Almuzaini KK, Onu FU, et al. Prospects and Challenges of Using Machine Learning for Academic Forecasting. Comput Intell Neurosci 2022;2022:5624475. [Crossref] [PubMed]
46. Hamisu AW, Blake IM, Sume G, et al. Characterizing Environmental Surveillance Sites in Nigeria and Their Sensitivity to Detect Poliovirus and Other Enteroviruses. J Infect Dis 2022;225:1377-86. [Crossref] [PubMed]
47. Edeh MO, Dalal S, Dhaou IB, et al. Artificial Intelligence-Based Ensemble Learning Model for Prediction of Hepatitis C Disease. Front Public Health 2022;10:892371. [Crossref] [PubMed]
48. Adeyinka DA, Muhajarine N. Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models. BMC Med Res Methodol 2020;20:292. [Crossref] [PubMed]
49. Dadzie Ephraim RK, Kotam GP, Evans Duah E, et al. Application of medical artificial intelligence technology in sub-Saharan Africa: Prospects for medical laboratories. Smart Health 2024;33:100505.
50. Bali B, Garba EJ, Ahmadu AS, et al. Analysis of emerging trends in artificial intelligence for education in Nigeria. Discov Artif Intell 2024;4:110.
51. Dave T, Athaluri SA, Singh S. ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell 2023;6:1169595. [Crossref] [PubMed]
52. Ponds R, van Oort F, Frenken K. The geographical and institutional proximity of research collaboration. Pap Reg Sci 2007;86:423-44.
53. Xie Y, Zhai Y, Lu G. Evolution of artificial intelligence in healthcare: a 30-year bibliometric study. Front Med (Lausanne) 2024;11:1505692. [Crossref] [PubMed]
54. Boutracheh H, El Iaziji L, Moumen A. Mapping AI-Health Research in Africa: Bibliometric Insights into Global Trends. BIO Web of Conferences 2025;200:01027.
55. Umar AA, Salihu HM, Azuine RE. Crisis of Brain Drain in Nigeria's Health Sector: Challenges, Opportunities, and the Path Forward. Int J MCH AIDS 2025;14:e011. [Crossref] [PubMed]
56. Lawal L, Lawal AO, Amosu OP, et al. The COVID-19 pandemic and health workforce brain drain in Nigeria. Int J Equity Health 2022;21:174. [Crossref] [PubMed]
57. Onah CK, Azuogu BN, Ochie CN, et al. Physician emigration from Nigeria and the associated factors: the implications to safeguarding the Nigeria health system. Hum Resour Health 2022;20:85. [Crossref] [PubMed]
58. Sinha C. Global South-led responsible AI solutions to strengthen health systems: an emergent research landscape. Oxf Open Digit Health 2025;3:oqaf016. [Crossref] [PubMed]
59. Odeny B, Bosurgi R. Time to end parachute science. PLoS Med 2022;19:e1004099. [Crossref] [PubMed]
60. Mehjabeen D, Patel K, Jindal RM. Decolonizing global health: a scoping review. BMC Health Serv Res 2025;25:828. [Crossref] [PubMed]
61. African Union. Continental Artificial Intelligence Strategy. 2024. Available online: https://au.int/sites/default/files/documents/44004-doc-EN-_Continental_AI_Strategy_July_2024.pdf
62. Diaz Pabón FA, Ahmed AMB. Africa’s Continental AI Strategy: A Black Mirror’s Mirage or a Fast Track for Development? Oxford Intersect AI Soc 2025. doi: 10.1093/9780198945215.003.0186.
63. Hussain SA, Bresnahan M, Zhuang J. Can artificial intelligence revolutionize healthcare in the Global South? A scoping review of opportunities and challenges. Digit Health 2025;11:20552076251348024.
64. Pyo J, Lee W, Choi EY, et al. Qualitative Research in Healthcare: Necessity and Characteristics. J Prev Med Public Health 2023;56:12-20. [Crossref] [PubMed]
65. Smela B, Toumi M, Świerk K, et al. Assessing the validity of a rapid review against a systematic literature review. A comparison of systematic literature reviews done by Cochrane with rapid reviews and the impact on meta-analyses results. J Epidemiol Popul Health 2024;72:202526.
66. Pham T. Ethical and legal considerations in healthcare AI: innovation and policy for safe and fair use. R Soc Open Sci 2025;12:241873. [Crossref] [PubMed]
67. Mehta P, Zimba O, Gasparyan AY, et al. Ethics Committees: Structure, Roles, and Issues. J Korean Med Sci 2023;38:e198. [Crossref] [PubMed]
68. Papagiannidis E, Mikalef P, Conboy K. Responsible artificial intelligence governance: A review and research framework. J Strateg Inf Syst 2025;34:101885.
69. Kawakatsu Y, Mosser JF, Adolph C, et al. High-resolution mapping of essential maternal and child health service coverage in Nigeria: a machine learning approach. BMJ Open 2024;14:e080135. [Crossref] [PubMed]
70. Macaulay BO, Aribisala BS, Akande SA, et al. Breast cancer risk prediction in African women using Random Forest Classifier. Cancer Treat Res Commun 2021;28:100396. [Crossref] [PubMed]
71. Ogwu MC, Izah SC, Sawyer WE, et al. Environmental Risk Assessment of Trace Metal Pollution: A Statistical Perspective. Environ Geochem Health 2025;47:94. [Crossref] [PubMed]
72. Samuel O, Zewotir T, North D. Application of machine learning methods for predicting under-five mortality: analysis of Nigerian demographic health survey 2018 dataset. BMC Med Inform Decis Mak 2024;24:86. [Crossref] [PubMed]
73. Awe OO, Mwangi PN, Goudoungou SK, et al. Explainable AI for enhanced accuracy in malaria diagnosis using ensemble machine learning models. BMC Med Inform Decis Mak 2025;25:162. [Crossref] [PubMed]
74. Eneanya OA, Reimer LJ, Fischer PU, et al. Geospatial modelling of lymphatic filariasis and malaria co-endemicity in Nigeria. Int Health 2023;15:566-72. [Crossref] [PubMed]