[Paper Review] Artificial Intelligence for Public Health Surveillance in Africa: Applications and Opportunities

Jean Marie Tshimula, Mbowa R. Kalengayi+29 more|arXiv (Cornell University)|Aug 5, 2024

Data-Driven Disease Surveillance9 citations

TL;DR

The paper surveys how AI can enhance public health surveillance in Africa, highlighting disease detection, prediction, real-time reporting, case studies, opportunities, and implementation challenges.

ABSTRACT

Artificial Intelligence (AI) is revolutionizing various fields, including public health surveillance. In Africa, where health systems frequently encounter challenges such as limited resources, inadequate infrastructure, failed health information systems and a shortage of skilled health professionals, AI offers a transformative opportunity. This paper investigates the applications of AI in public health surveillance across the continent, presenting successful case studies and examining the benefits, opportunities, and challenges of implementing AI technologies in African healthcare settings. Our paper highlights AI's potential to enhance disease monitoring and health outcomes, and support effective public health interventions. The findings presented in the paper demonstrate that AI can significantly improve the accuracy and timeliness of disease detection and prediction, optimize resource allocation, and facilitate targeted public health strategies. Additionally, our paper identified key barriers to the widespread adoption of AI in African public health systems and proposed actionable recommendations to overcome these challenges.

Motivation & Objective

• Motivate the use of AI to strengthen disease detection, prediction, and surveillance in Africa's resource-limited health systems.
• Catalog AI-enabled applications across infectious diseases and mental health to inform policy and practice.
• Identify success stories and practical barriers to AI adoption in African public health settings.
• Provide actionable recommendations to overcome ethical, infrastructural, and data-quality challenges.

Proposed method

• Review and synthesize existing AI-based public health surveillance applications in Africa from diverse data sources (EHRs, social media, environmental data, genomic data).
• Organize applications into disease detection/prediction and real-time surveillance/reporting with disease-specific case studies.
• Highlight methodological approaches used in cited studies (machine learning, deep learning, ensemble methods, risk scores).
• Discuss opportunities for improving healthcare delivery, resource allocation, and equity through AI integration.
• Outline barriers and ethical considerations, and propose strategies to address them.

Figure 1: Taxonomy of AI applications for public health.

Experimental results

Research questions

• RQ1 RQ1: How can artificial intelligence improve disease detection, prediction, and surveillance in public health in low-resource regions?
• RQ2 RQ2: What are the key challenges and barriers to implementing AI technologies in public health systems in low-resource regions, and what strategies can overcome these challenges?

Key findings

• AI has potential to improve accuracy and timeliness of disease detection and prediction in Africa.
• AI-driven approaches integrate diverse data (socioeconomic, environmental, climatic, genomic) to inform surveillance and resource allocation.
• Applications span HIV, cholera, Ebola, measles, tuberculosis, influenza, Zika, COVID-19, malaria, poliovirus, and mental health.
• Case studies show AI can enhance HIV testing, drug resistance prediction, outbreak forecasting, and self-test interpretation.
• Real-time AI systems can support early outbreak detection and more efficient public health responses.
• Barriers include data quality, infrastructure, expertise, data sharing, and ethical considerations, with actionable recommendations proposed.

Figure 3: Performance metrics of best models per disease for Disease prediction and detection. Note that y-axis indicates Disease + Authors + Model + Metric .