Data-driven decision making in malaria control: the role of AI in the public health policy

INTRODUCTION

Malaria remains a major global health burden, impacting millions of cases reported annually. It is caused by the Plasmodium parasites and are transmitted through the bites of infected female Anopheles mosquitoes. The malaria disease is also responsible for the mortality, morbidity, economic loss and social disruption in affected communities.¹ In 2023, global malaria cases were estimated to be 263 million, with an incidence rate of 60.4 per 1,000 at-risk individuals, with an increase of 11 million cases and a 1.8% rise from 2022. (World Health Organisation, 2023).

Mortality rates were recorded at 13.7 deaths per 100,000 population, with the African Region accounting for 95% of the global malaria mortality burden. High burden to high impact (HBHI) countries, excluding India, were accounted for 66% of global malaria cases and 68% of malaria deaths, marking a 13.8% growth in cases and a 2.3% increase in deaths compared to 2017.³ These statistics highlights the persistent and dynamic nature of malaria, particularly in endemic regions with limited access to health care facilities for effective prevention and treatment strategies. Vulnerable groups, particularly pregnant women and children below five years of age, remain disproportionately affected by malaria-related mortality. Beyond its direct health impacts, malaria exerts substantial economic burden on affected regions, hindering economic growth and perpetuating cycles of poverty. The disease significantly affects key sectors including healthcare, education and workforce productivity. These challenges emphasize the urgent necessity for comprehensive and sustained malaria control and elimination efforts to protect global health and development.

CHALLENGES IN MALARIA CONTROL

Significant progress has been achieved in malaria control over the past two decades but several challenges continue to impede global efforts. The growing resistance to antimalarial drugs, such as Artemisinin and to insecticides used in vector control, particularly pyrethroids, poses a major threat to malaria prevention and treatment. This resistance risks reversing the substantial reductions in malaria morbidity and mortality achieved in recent years.⁴

In many malaria-endemic regions, the healthcare infrastructure remains inadequate to support effective malaria control efforts. Limited access to healthcare, especially in rural and remote areas, hinders prompt diagnosis and treatment, while shortages of skilled health personnel and diagnostic resources exacerbates the situation.⁵ Sustaining financial support for malaria control remains challenging, as many endemic nations depend on international donors and struggle to maintain consistent funding for long-term elimination efforts.⁶

India recorded a substantial decline in malaria burden, with estimated cases falling from 6.4 million in 2017 to 2 million in 2023 with a 69% reduction, while malaria-related deaths decreased from 11,100 to 3,500 at a 68% reduction (World malaria report 2024). The complex and diverse epidemiology of malaria in India, which varies from state to sub-district levels, necessitates targeted strategies tailored to specific contexts, risk groups, vector behavior and existing infrastructure, including healthcare system coverage.⁸

Malaria transmission in India is now localized and focal, particularly in hilly, forested and forest fringe areas, as well as in regions along inter-state and international borders. High-burden states such as Mizoram, Tripura, Odisha, Chhattisgarh and Jharkhand experience persistent transmission. Socioeconomic inequalities affect health-seeking practices and limit access to preventive tools such as insecticide-treated nets (ITNs) and indoor residual spraying (IRS).⁹

AI: TRANSFORMATIVE TOOL IN HEALTHCARE

AI has become a transformative tool in healthcare, incorporating technologies such as machine learning, neural networks and natural language processing for enable rapid and large-scale analysis of complex data. It’s ability to identify patterns, predict outcomes and generate real-time insights holds the potential to revolutionize various aspects of healthcare, from diagnosis and treatment to disease prevention and health system management.^10-12

APPLICATIONS AND ADVANTAGES OF AI

The integration of AI and data-driven decision-making in malaria control presents significant potential for overcoming persistent challenges in combating this disease. AI offers several advantages over traditional methods, enabling public health authorities to improve intervention effectiveness, optimize resource distribution and advance toward malaria eradication (Table 1).¹³

AI can integrate and analyse the real-time data from various surveillance systems, offering a comprehensive understanding of malaria transmission dynamics.¹⁴ AI-powered platforms minimize the requirement of manual data entries, improve accuracy of data collection and facilitate the timely identification of disease patterns.¹⁵ Through machine learning algorithms, data from various sources, such as health facilities, mobile applications, diagnostic tools and satellite imagery can be integrated to enable real-time case mapping, anomaly detection and early outbreak alerts.¹⁶

AI-driven predictive models can forecast malaria outbreaks by analysing large datasets from diverse sources, such as weather patterns, vector mapping, population movements and historical incidence rates.^17,18 Studies have shown that machine learning approaches, such as neural networks and decision tree models, can effectively predict malaria outbreaks by analyzing environmental and socioeconomic factors.^19,20

AI can play a pivotal role in optimizing allocation of resources, ensuring that interventions like ITNs, antimalarial drugs and IRS are directed to areas with the greatest need. AI algorithms have been successfully employed to model and streamline resource distribution, minimizing wastage and maximizing the impact of interventions in malaria-endemic regions.^21,22 AI holds the potential to revolutionize malaria treatment through the designing patient-specific treatment plans based on individual data, including genomics.²³ AI techniques are being used to tailor malaria treatments to specific genetic profiles, enhancing drug efficacy and minimizing adverse effects.²⁴ This approach can reduce treatment failure and prevent the development of drug resistance.²⁵

CASE STUDIES

AI applications in malaria control across regions

The application of AI in malaria control offers substantial opportunities to improve public health outcomes. In malaria endemic regions, AI technologies have driven innovative approaches to predictive analytics, diagnosis, treatment, surveillance and resource optimization.

Africa

AI is playing a transformative role in malaria control across Africa by enabling more data-driven, timely and targeted interventions.

Machine learning models have been developed to predict malaria outbreaks using environmental data such as rainfall, temperature and humidity alongside historical case records and satellite imagery. In Kenya, such AI-based systems have supported early warning and proactive response mechanisms, enabling better resource planning and targeted.²⁷

AI tools are being employed to optimize the distribution of ITNs and antimalarial drugs. These tools process epidemiological data and population density metrics to identify malaria hotspots, resulting in improved cost-effectiveness and intervention reach.²⁸

In Uganda, AI-powered mobile applications using image recognition are being used to analyze blood smear images for malaria diagnosis. These tools have been instrumental in increasing diagnostic accuracy and reducing time to diagnosis, particularly in remote regions with limited access to laboratory services (Mirugwe, 2023.)

AI-driven digital platforms integrated with mHealth applications are enabling real-time tracking of malaria cases. These systems allow health authorities to quickly detect and respond to emerging outbreaks, thereby enhancing surveillance capacity and public health responsiveness.³⁰

Southeast Asia

Southeast Asia faces complex malaria challenges, including the emergence of drug-resistant Plasmodium strains and diverse vector ecologies. AI applications are being adapted to these specific challenges.

AI-based analysis of genomic surveillance data is being used to track artemisinin resistance in Thailand. Machine learning models analyze patient records and parasite genetic markers to detect resistance patterns and inform treatment decisions.³¹ AI-enhanced vector surveillance tools, including drone-assisted mapping and satellite image analysis, are supporting the identification of mosquito breeding habitats. These technologies enable targeted larval source management and improve the overall effectiveness of vector control programs.³² AI-powered platforms utilizing natural language processing (NLP) are delivering personalized health messages and malaria prevention tips to community members in Vietnam. These platforms have demonstrated increased community awareness and engagement, driving positive behavioral changes.^33,34

AI models analyzing genetic data and patient records in Cambodia have monitored and predicted the spread of drug-resistant malaria strains. This supports adaptive treatment protocols and policy-making to mitigate resistance.³¹

India

AI technologies are being deployed in surveillance, diagnosis, vector mapping and operational efficiency across public health programs.

AI and machine learning tools have been integrated with digital surveillance platforms like the Integrated Health Information Platform (IHIP) to monitor malaria trends in real-time. AI algorithms analyze case reports, weather data and mobility patterns to identify high-risk zones and guide targeted interventions. These efforts have contributed to localized outbreak prevention and efficient resource use.³⁵

Indian Council of Medical Research (ICMR) issued Ethical Guidelines for the use of AI across various healthcare domains, including diagnosis and screening, therapeutics, preventive care, public health surveillance, clinical decision support, complex data analysis, disease outcome prediction, behavioral and mental health and healthcare management systems, highlighting the diverse applications of AI in healthcare (ICMR 2023).

AI-based digital microscopy tools are being tested to automate blood smear analysis. These tools use deep learning to identify Plasmodium species with high accuracy particularly useful in detecting drug-resistant parasite strains and reduce dependency.³⁶

Geographic Information Systems (GIS) combined with AI models are being utilized to map vector breeding habitats using satellite data. These systems enable spatial targeting of vector control measures, such as risk mapping, predictive modelling, larviciding and fogging, leading to improved operational planning.^37,38

COMPARATIVE ANALYSIS ACROSS REGIONS

The application of AI in malaria control demonstrates significant potential to transform public health policy and improve outcomes across various regions. By leveraging AI technologies, regions can enhance predictive analytics, optimize resource allocation, improve diagnostics and strengthen surveillance systems. The impact of AI applications in malaria control depends on the availability of reliable data, technological infrastructure and human resources. Regions with robust healthcare systems and data collection capabilities tend to experience more successful AI integration. For example, countries with established health information systems, such as Kenya and India, have leveraged these resources to implement AI-driven solutions effectively.^26,27,39 In many regions, the lack of high-quality, standardized data poses a significant challenge to AI implementation. Enhancing data collection and sharing is essential for the effective implementations of AI-driven solutions. The integration of various data inputs, including electronic health records and community health data, is essential for building effective AI models.^5,40 AI solutions must be tailored to the specific needs and contexts of different regions. This necessitates collaboration between local stakeholders, governments and international organizations to ensure that AI applications are scalable and adaptable to diverse environments. Collaborative efforts in Southeast Asia, for instance, have demonstrated the essential role of adapting AI tools to local epidemiological and socio-economic situations.

ETHICAL AND PRACTICAL CONSIDERATIONS

The significance of integration of AI into public health systems offers potential for improving healthcare, particularly in areas like malaria and other diseases. However, the use of AI also raises substantial ethical concerns, particularly around data privacy and security. Ensuring that patient data is protected and used ethically is paramount to the success and acceptance of AI-driven public health initiatives (Table 2).

Data privacy and security

AI applications in public health require vast amounts of data, often including sensitive personal health information. The processes of collecting, storing and analyzing this data can put individuals at risk of privacy breaches and unauthorized access. Such violations of data privacy can erode public confidence in health systems, reduce participation in health initiatives and may also lead to discrimination or stigma against affected individuals.⁴¹

Bias and fairness

AI models may inadvertently perpetuate or exacerbate existing biases within the data they are trained on which leads to unfair treatment of certain groups and affect the equitable distribution of healthcare resources. Biases in AI systems can effect in misdiagnoses, unequal access to healthcare services and reinforcement of the health disparities.^42,43

Informed consent

Securing informed consent for utilising personal data in AI-driven public health initiatives can be complex, particularly in low-resource settings where literacy and awareness of data rights may be limited. Without informed consent, individuals may be unaware of how their data is being used, potentially leading to ethical breaches and loss of autonomy.⁴⁴

Transparency and accountability

The "black boxes" nature of AI systems often hampers understanding that how decisions are made. Which leads to absence of transparency can hinder accountability and complicate the verification of AI-driven decisions. The opaqueness of AI models can lead to mistrust among stakeholders and pose challenges in validating AI-driven public health interventions.⁴⁵

Strategies for ensuring ethical use of AI in public health

Ethical use of AI in public health relies on strong data governance, modern infrastructure, skilled workforce and cross-sector partnerships. Ensuring transparency, explain ability and addressing equity and bias are essential to avoid unintended harm. Table 3 details the core principles include preserving human oversight, ensuring technical reliability, protecting privacy and promoting fairness, accountability and societal well-being throughout the AI lifecycle.⁴⁶

Equity and access

Addressing disparities in access to AI technologies is essential for maximizing their impact on malaria control and public health policy. However, high-income and low-income regions have significant disparities in terms of access and utilization of AI tools. These disparities pose a risk of deepening existing inequalities in health outcomes and interventions.⁴⁷

RECOMMENDATIONS FOR BRIDGING THE GAP

AI technologies, while promising, are often concentrated in high-income countries where resources for development and implementation are more readily available. Low-income regions, which bear the greatest burden of malaria, often face challenges such as inadequate infrastructure, financial resources and insufficient technical expertise. These barriers hinder the deployment and effective applications of AI technologies in these regions. To address these disparities and promote equitable access to AI technologies, several strategies are recommended.⁴⁸

Collaborative efforts among international organizations, governments and private sector entities are supporting AI initiatives in low-income regions. Financial support in the form of grants, subsidies or investments can help overcome initial barriers to technology adoption. Investing in education and training programs is vital for developing local expertise in AI and data science. By equipping local researchers and practitioners with the necessary skills, we can enhance their ability to utilize AI tools effectively and integrate them into existing health systems. AI applications must be adaptable according to specific needs and constraints of low-income regions. Improving digital infrastructure, such as internet connectivity and data storage capabilities, is vital for the successful implementation of AI technologies. Investments in these areas will support the deployment of AI tools and enhance data-driven decision-making. Policymakers should establish frameworks that promote equitable access to AI technologies.

BIAS IN AI ALGORITHMS

Identifying and Mitigating Biases in AI Models, AI algorithms hold immense promise in enhancing malaria control and public health decision-making. However, these technologies can inadvertently perpetuate biases present in their training data, which may lead to unfair or suboptimal outcomes. Bias in AI algorithms can stem from several sources, including biased training data, flawed model assumptions and skewed algorithmic processes.

To ensure fair and unbiased decision-making in malaria control, it is crucial to adopt strategies designed to identify and mitigate potential biases. Ensuring that training data is diverse and representative of the populations and regions affected by malaria is crucial. Implementing regular bias detection and testing procedures can help identify and address biases in AI models. Enhancing transparency in AI algorithms and decision-making processes facilitates better evaluation and accountability by making it easier for stakeholders to understand how conclusions are reached and identify potential biases. Techniques such as explainable AI (XAI) allow users to interpret the reasoning behind AI outputs, thereby aiding in bias detection and correction. Several approaches can be employed to minimize bias in AI models, including re-evaluating and adjusting training data, incorporating fairness constraints during the development process and implementing post-processing corrections to address identified biases. Table 3 presents key insights and strategic approaches for integrating AI into malaria control, covering critical areas such as data quality, infrastructure, ethics, collaboration, scalability and equity.

RECOMMENDATIONS FOR INTEGRATING AI INTO PUBLIC HEALTH POLICY

The successful integration of AI into public health policy requires comprehensive and adaptive policy frameworks. These developing policy frameworks must address various challenges, such as data privacy, ethical considerations, infrastructure requirements and workforce training to support AI integration in public health.

Establish clear governance structures

Developing governance structures to oversee AI integration into public health is important. This includes defining roles and responsibilities for stakeholders such as government agencies, healthcare providers, technology companies and researchers. Clear governance structures ensure accountability and coordination among stakeholders, fostering collaboration and preventing duplication of efforts. Establishing governance frameworks for AI in healthcare helps address the complexities of AI implementation and ensures that AI-driven solutions are safe and efficient. For example, the European Union's General Data Protection Regulation (GDPR) serves as a benchmark for data governance by establishing rules for the collection, processing and storage of personal data aimed at safeguarding individual privacy. GDPR has set a global standard for data protection and serves as a model for developing governance structures in AI integration.

Create ethical guidelines and standards

Establishing ethical guidelines and standards to guide AI development and deployment in public health is necessary. These guidelines should address issues such as data privacy, informed consent, bias and transparency. The importance of ethical AI use to maintain public trust and prevent potential harm is highlighted. The World Health Organization (WHO) emphasizes that ethical guidelines should be developed with input from ethicists, technologists, healthcare professionals and the public.⁴⁹ For example, WHO’s ethical guidelines stress human rights, inclusivity and accountability as foundational principles for AI in healthcare.⁴⁶

Support research and development

Allocating funds and resources for supporting research and development (R&D) of AI technologies in public health. Encourage public-private partnerships to accelerate innovation and facilitate knowledge transfer. Investing in R&D enables the development of AI solutions tailored to specific health challenges, such as malaria control.¹¹ Public-private partnerships can leverage the strengths of different sectors to drive innovation and scalability.

Promote data sharing and interoperability

Develop policies to promote data sharing and interoperability among health systems, research institutions and technology providers. Establish common data standards to facilitate collaboration and integration of AI technologies. Data sharing and interoperability are crucial for maximizing the potential of AI in public health, enabling the integration of diverse data sources, improving the accuracy of AI models and enhancing decision-making processes.⁵⁰ The Global Health Data Partnership advocates standardized data formats and protocols to enhance data sharing and interoperability across health systems.⁵¹

Ensure workforce training and capacity building

Implement training programs to build the capacity of healthcare workers, policymakers and technologists to understand and leverage AI technologies. Focus on developing skills in data science, machine learning and AI ethics. A well-trained workforce is essential for the successful deployment and management of AI technologies in public health.⁵² Capacity building initiatives ensure that stakeholders can effectively use AI tools and address challenges as they arise. The WHO has developed training programs to equip healthcare workers with the skills needed to integrate AI into their practice, emphasizing the importance of continuous learning and adaptation.⁴⁹

Align with international standards

Align national policies with international standards and guidelines for AI in public health. This includes adopting frameworks from organizations such as the WHO, the international telecommunication union (ITU) and the organisation for economic co-operation and development (OECD). Aligning with international standards ensures consistency and compatibility across borders, facilitating collaboration and knowledge exchange. International guidelines emphasize key principles such as transparency, accountability and inclusivity, essential for building trust and ensuring ethical AI deployment in healthcare.⁴⁹ The OECD Principles on AI provide guidelines for promoting trustworthy AI, emphasizing values such as transparency, accountability and robustness, serving as a benchmark for evaluating AI applications globally (OECD, 2019).

Foster international collaboration

Foster international collaboration and partnerships to share best practices, experiences and resources in AI deployment for public health. Participation in global forums and networks enables countries to stay informed about emerging trends and innovations. International collaboration accelerates the adoption of effective AI solutions and facilitates the pooling of resources and expertise to address common health challenges.⁵³ The GPAI exemplifies such collaboration by bringing experts from various countries together to tackle AI-related issues, including public health applications (GPAI, 2023).

CAPACITY BUILDING

The successful implementation of AI in public health hinges on building robust technical and infrastructural capacity. Training programs should focus on enhancing AI literacy among healthcare workers, enabling them to make informed decisions and effectively collaborate with AI systems.¹⁰

The WHO has initiated programs on digital health technologies, emphasizing continuous learning to keep pace with rapidly evolving AI technologies.^25,49 Interdisciplinary collaboration fosters deeper understanding of AI applications (Jiang et al, 2017). India’s AI in Healthcare Bootcamp provides practical experience, emphasizing real-world applications and case studies. Developing local expertise is essential for sustainable AI implementation.^54,55

COLLABORATIVE APPROACHES

Collaboration between governments, non-governmental organizations (NGOs) and the private sector are important in scaling up and implementing AI solutions in malaria control effectively. By combining resources, expertise and influence, these partnerships can drive innovation and enhance public health outcomes. The collaboration allows for leveraging resources, expertise and technology from different sectors.⁵⁶ Cross-sector collaboration fosters innovation by combining diverse perspectives and skill sets.⁵⁷ The Global Fund, a partnership between governments, civil society, the private sector and people affected by diseases, exemplifies successful collaboration (The Global Fund, 2023).

Establishing transparent communication channels between stakeholders fosters trust, transparency and ensures alignment of goals and priorities. The collaboration between Zambia's Ministry of Health, PATH (an NGO) and a private AI firm led to the development of a predictive analytics platform for malaria surveillance.¹⁹ A collaborative effort between the Thai Ministry of Public Health, a local university and an international tech company focused on developing AI-driven diagnostic tools for malaria. The Indian government's collaboration with technology companies and healthcare NGOs has led to the development of AI-powered health information systems for malaria control.

NEED FOR INNOVATIVE APPROACHES TO ENHANCE DECISION-MAKING

Traditional methods of data collection and analysis in malaria control have notable limitations, highlighting the necessity for innovative approaches. The integration of AI and data-driven decision-making presents a promising avenue to effectively address these challenges.

AI offers the potential to provide real-time, accurate and actionable insights, thereby enhancing capacity of public health authorities for predicting outbreaks, optimize resource allocation and personalize treatment plans Machine learning algorithms can help identify transmission hotspots, forecast disease trends and support timely intervention strategies, particularly in resource-constrained settings (Figure 1).⁵⁸

FACTORS INFLUENCING THE IMPLEMENTATION AND IMPACT OF AI IN MALARIA CONTROL

The impact of AI applications in malaria control greatly depends on data quality and its integration. Accurate, comprehensive and timely data are essential for effective AI models. Collaboration between governments, research institutions and technology providers are crucial to overcoming data-related challenges. Establishing standardized data collection methods and improving data-sharing protocols are vital.¹² AI implementation requires robust digital infrastructure and capacity building. Investments in digital infrastructure, internet connectivity and healthcare worker training are necessary for successful deployment and scaling.

Strengthening digital health ecosystems enables AI integration into healthcare systems, enhancing efficiency and effectiveness. Ethical frameworks must guide AI use in public health to ensure interventions are equitable and inclusive. Addressing privacy, data security and model bias is critical to maintaining public trust and maximizing benefits.⁵⁹ multi-sectoral partnerships involving governments, NGOs, research institutions and the private sector enable effective AI deployments. These collaborations foster knowledge exchange and resource mobilization necessary for context-specific solutions.^53,60 AI solutions must be adaptable and scalable across diverse regions, respecting local cultural, epidemiological and health system contexts.¹⁰

FRAMEWORK FOR AI-DRIVEN, DATA-DRIVEN DECISION-MAKING IN MALARIA CONTROL

Figure 2 presents the conceptual framework for AI-driven, data-informed decision-making in malaria control, illustrating the progression from data collection and integration to AI-based analysis and interpretation. This framework emphasizes how analytical insights derived from AI can inform targeted policies and programmatic interventions. By connecting technological processes with practical outcomes, it highlights the potential of AI to improve accuracy, effectiveness and impact of malaria control efforts.

CONCLUSION

AI holds transformative potential for malaria control by improving surveillance, diagnostics and treatment through the analysis of large-scale data using advanced algorithms. AI-driven tools have demonstrated promise in predicting outbreaks, optimizing resource allocation and personalizing treatment strategies. However, challenges related to equity, infrastructure and algorithmic bias persist. Disparities in technological capacity between high and low-income regions risk exacerbating health inequities. Addressing these gaps through international collaboration, infrastructure investment and capacity building is essential for inclusive AI adoption. The incorporation of genomic data into AI models can enhance understanding of parasite evolution and drug resistance, enabling more targeted interventions. To ensure ethical and effective use, frameworks must be established to mitigate bias, promote transparency and guide equitable decision-making. Moving forward, cross-disciplinary collaboration among researchers, technologists and policymakers will be key to scaling AI tools that are responsive to diverse public health needs.

Funding: No funding sources

Conflict of interest: None declared

Ethical approval: Not required

REFERENCES

1. 1. Bhan S, Sharma AK, Thomas TG, Singh R. Entomological assessment of malaria outbreak in Bareilly and Budaun districts of Uttar Pradesh, India. 53 Int J Mosq Res. 2020;7(5):874.
2. 2. World Health Organization. WHO guidelines for malaria. 2024.
3. 3. Bhatt S, Weiss DJ, Cameron E, et al. The effect of malaria control on Plasmodium falciparum in Africa between 2000 and 2015. Nature. 2015;526(7572):207-11.
4. 4. Hemingway J, Ranson H, Magill A. Averting a malaria disaster: will insecticide resistance derail malaria control. Lancet Lond Engl. 2016;387(10029):1785-8.
5. 5. Oladipo HJ, Tajudeen YA, Oladunjoye IO. Increasing challenges of malaria control in sub-Saharan Africa: Priorities for public health research and policymakers. Ann Med Surg. 2022;81:104366.
6. 6. Whittaker M, Smith C. Reimagining malaria: five reasons to strengthen community engagement in the lead up to malaria elimination. Malar J. 2015;14:410.
7. 7. V’kovski P, Kratzel A, Steiner S, Stalder H, Thiel V. Coronavirus biology and replication: implications for SARS-CoV-2. Nature Rev Microbiol. 2021;19(3):155-70.
8. 8. Kumar A, Valecha N, Jain T, Dash AP. Burden of Malaria in India: Retrospective and Prospective View. Am J Trop Med Hyg. 2007;77(6):69-78.
9. 9. Rajvanshi H, Singh MP, Bharti PK. Science of malaria elimination: using knowledge of bottlenecks and enablers from the Malaria Elimination Demonstration Project in Central India for eliminating malaria in the Asia Pacific region. Front Public Health. 2024;11:1303095.
10. 10. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56.
11. 11. Esteva A, Robicquet A, Ramsundar B. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-9.
12. 12. Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med. 2019;380(14):1347-58.
13. 13. Benke K, Benke G. Artificial Intelligence and Big Data in Public Health. Int J Environ Res Public Health. 2018;15(12):2796.
14. 14. Kamilaris A, Prenafeta-Boldú FX. Deep learning in agriculture: A survey. Comput Electron Agric. 2018;147:70-90.
15. 15. Ogbaga I. Artificial Intelligence (AI)-Based Solution to Malaria Fatalities In Africa: An Exploratory Review. Computer Science and Mathematics. 2023.
16. 16. Alaran MA, Lawal SK, Jiya MH. Challenges and opportunities of artificial intelligence in African health space. Digit Health. 2025;11:205915.
17. 17. Et. Al. YAA. Malaria Prediction Model Using Machine Learning Algorithms. Turk J Comput Math Educ Turcomat. 2021;12(10):7488-96.
18. 18. Muriithi DK, Lumumba VW, Awe OO, Muriithi DM. An Explainable Artificial Intelligence Models for Predicting Malaria Risk in Kenya. Eur J Artif Intell Mach Learn. 2025;4(1):1-8.
19. 19. Khan O, Ajadi JO, Hossain MP. Predicting malaria outbreak in The Gambia using machine learning techniques. PloS One. 2024;19(5):99386.
20. 20. Nkiruka O, Prasad R, Clement O. Prediction of malaria incidence using climate variability and machine learning. Inform Med Unlocked. 2021;22:100508.
21. 21. Vij P, Prashant PM. Novel AI-driven Malaria Prediction for Optimizing Public Health Management. South East Eur J Public Health. Published online September 2, 2024:413-8.
22. 22. Alowais SA, Alghamdi SS, Alsuhebany N. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ. 2023;23(1):689.
23. 23. Libbrecht MW, Noble WS. Machine learning applications in genetics and genomics. Nat Rev Genet. 2015;16(6):321-32.
24. 24. Serrano DR, Luciano FC, Anaya BJ. Artificial Intelligence (AI) Applications in Drug Discovery and Drug Delivery: Revolutionizing Personalized Medicine. Pharmaceutics. 2024;16(10):1328.
25. 25. Lyutsova E, Pavlova K, Gospodinova M, Radkova D. The integration of artificial intelligence in malaria control and surveillance. Scr Sci Medica. 2024;56(4):15.
26. 26. Muriithi DK, Lumumba VW, Awe OO, Muriithi DM. An Explainable Artificial Intelligence Models for Predicting Malaria Risk in Kenya. Eur J Artif Intell Mach Learn. 2025;4(1):1-8.
27. 27. Muriithi D, Lumumba V, Okongo M. A Machine Learning-Based Prediction of Malaria Occurrence in Kenya. Am J Theor Appl Stat. 2024;13(4):65-72.
28. 28. Chidoluo Vitus O. The impact of artificial intelligence on healthcare delivery in nigeria. Winsome Publishing LLC, ed. New Healthc Adv Explor. 2024;01(2):1-3.
29. 29. Mirugwe A. Adoption of artificial intelligence in the Ugandan health sector: a review of literature. International J Biomed Res. 2023;17:23.
30. 30. Larocca A, Moro Visconti R, Marconi M. Malaria diagnosis and mapping with m-Health and geographic information systems (GIS): evidence from Uganda. Malar J. 2016;15(1):520.
31. 31. Ford CT, Janies D. Ensemble machine learning modeling for the prediction of artemisinin resistance in malaria. F1000Research. 2020;9:62.
32. 32. Pley C, Evans M, Lowe R, Montgomery H, Yacoub S. Digital and technological innovation in vector-borne disease surveillance to predict, detect and control climate-driven outbreaks. Lancet Planet Health. 2021;5(10):739-45.
33. 33. Alqahtani T, Badreldin HA, Alrashed M. The emergent role of artificial intelligence, natural learning processing and large language models in higher education and research. Res Soc Adm Pharm. 2023;19(8):1236-42.
34. 34. Chanh HQ, Ming D, Nguyen QH. Applying artificial intelligence and digital health technologies, Viet Nam. Bull World Health Organ. 2023;101(07):487-92.
35. 35. Goel K, Chaudhuri S, Saxena A. India’s strategy on surveillance system- A paradigm shift from an Integrated Disease Surveillance Programme (IDSP) to an Integrated Health Information Platform (IHIP). Clin Epidemiol Glob Health. 2022;15:101030.
36. 36. Nema S, Rahi M, Sharma A, Bharti PK. Strengthening malaria microscopy using artificial intelligence-based approaches in India. Lancet Reg Health - Southeast Asia. 2022;5:100054.
37. 37. Prakash Nayak P, Pai B. J, Govindan S. Leveraging geographic information system for dengue surveillance: a scoping review. Trop Med Health. 2025;53(1):102.
38. 38. Mopuri R, Kadiri MR, Bhimala KR, Mutheneni SR. Identification of malaria vulnerable zones in North East Region of India: Spatiotemporal assessment through geographical information system and self-organizing maps. Acta Trop. 2025;270:107783.
39. 39. Zuhair V, Babar A, Ali R. Exploring the Impact of Artificial Intelligence on Global Health and Enhancing Healthcare in Developing Nations. J Prim Care Community Health. 2024;15:21545847.
40. 40. Oladipo EK, Adeyemo SF, Oluwasanya GJ. Impact and Challenges of Artificial Intelligence Integration in the African Health Sector: A Review. Trends Med Res. 2024;19(1):220-35.
41. 41. Yadav N, Pandey S, Gupta A, Dudani P, Gupta S, Rangarajan K. Data Privacy in Healthcare: In the Era of Artificial Intelligence. Indian Dermatol Online J. 2023;14(6):788-92.
42. 42. Rajkomar A, Hardt M, Howell MD, Corrado G, Chin MH. Ensuring Fairness in Machine Learning to Advance Health Equity. Ann Intern Med. 2018;169(12):866-72.
43. 43. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447-53.
44. 44. Vezyridis P, Timmons S. Resisting big data exploitations in public healthcare: free riding or distributive justice. Soc Health Illn. 2019;41(8):1585-99.
45. 45. Samek W, Wiegand T, Müller KR. Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. 2017;(1):34.
46. 46. Morley J, Machado CCV, Burr C. The ethics of AI in health care: A mapping review. Soc Sci Med. 2020;260:113172.
47. 47. Dankwa-Mullan I. Health equity and ethical considerations in using artificial intelligence in public health and medicine. Prev Chronic Dis. 2024;21:64.
48. 48. Western MJ, Smit ES, Gültzow T. Bridging the digital health divide: a narrative review of the causes, implications and solutions for digital health inequalities. Health Psychol Behav Med. 2025;13(1):2493139.
49. 49. Global Strategy on Digital Health 2020-2025. 1st ed. World Health Organization. 2021.
50. 50. Ristevski B, Chen M. Big Data Analytics in Medicine and Healthcare. J Integr Bioinforma. 2018;15(3):20170030.
51. 51. Macfarlane SB, AbouZahr C, eds. The Palgrave Handbook of Global Health Data Methods for Policy and Practice. Palgrave Macmillan UK. 2019;2:279.
52. 52. Longoni C, Bonezzi A, Morewedge CK. Resistance to medical artificial intelligence. J Consum Res. 2019;46(4):629-50.
53. 53. Yun T, Zhang L. International Partnerships in AI-driven healthcare: opportunities and challenges for advancing the UN sustainable development goals—a perspective. Healthcare. 2025;13(16):2053.
54. 54. Geneva Tamunobarafiri Igwama, Ejike Innocent Nwankwo, Ebube Victor Emeihe, Mojeed Dayo Ajegbile. The role of community health workers in implementing AI-based health solutions in rural areas. Int J Biol Pharm Res Updat. 2024;4(1):1-7.
55. 55. Wibowo MF, Pyle A, Lim E, Ohde JW, Liu N, Karlström J. Insights into the current and future state of ai adoption within health systems in Southeast Asia: cross-sectional qualitative study. J Med Internet Res. 2025;27:71591.
56. 56. Brinkel J, Krämer A, Krumkamp R, May J, Fobil J. Mobile phone-based mHealth approaches for public health surveillance in sub-Saharan Africa: a systematic review. Int J Environ Res Public Health. 2014;11(11):11559-82.
57. 57. Lee D, Yoon SN. Application of Artificial Intelligence-Based Technologies in the Healthcare Industry: Opportunities and Challenges. Int J Environ Res Public Health. 2021;18(1):271.
58. 58. Panteli D, Adib K, Buttigieg S. Artificial intelligence in public health: promises, challenges and an agenda for policy makers and public health institutions. Lancet Publ Health. 2025;10(5):e428-32.
59. 59. Char DS, Shah NH, Magnus D. Implementing machine learning in health care-addressing ethical challenges. N Engl J Med. 2018;378(11):981-3.
60. 60. Bates DW, Saria S, Ohno-Machado L, Shah A, Escobar G. Big data in health care: using analytics to identify and manage high-risk and high-cost patients. Health Aff Proj Hope. 2014;33(7):1123-31.