Systematic Review of AI for Infectious Disease Studies in Sub-Saharan Africa

62 peer-reviewed studies were synthesized to assess the application of AI-based modeling techniques for infectious disease research within a One Health framework in Sub-Saharan Africa. The review, authored by Bruno Enagnon Lokonon and last updated in April 2026, finds that AI adoption has grown rapidly since 2019, with malaria, HIV, COVID-19, and tuberculosis being the most frequently targeted diseases.

Use Cases

• Analyzing trends in AI adoption for infectious disease research based on the review of 62 studies.
• Identifying research gaps in zoonotic and environmental disease modeling based on the reported underrepresentation.
• Comparing the performance of ensemble and deep-learning models based on the reported median accuracy metrics.
• Assessing geographic disparities in research leadership based on the identified dominance of South Africa, Ethiopia, Kenya, and Tanzania.

Strengths

• Systematic review methodology synthesizes evidence from 62 peer-reviewed studies.
• Provides specific metrics on disease focus (e.g., malaria at 24%) and model performance (e.g., median accuracy close to 100% for CNN).
• Identifies concrete constraints and opportunities for AI deployment in the region.

Limitations

• The dataset is a 678.3 KB document; the underlying data from the 62 reviewed studies is not directly accessible.
• Column-level documentation for any extracted data is absent; field semantics must be inferred from the review text.
• The temporal coverage of the included studies is not explicitly stated, only the review's publication trend.

Provenance

Source

Bruno Enagnon Lokonon, via figshare.

Collection Method

Systematic review of peer-reviewed literature.

Time Range

Review covers studies up to 2024, with noted surge in publications from 2021-2024.

Freshness

Last updated 2026-04-22 05:46:45; freshness should be verified.

Geography

Sub-Saharan Africa, with specific mention of South Africa, Ethiopia, Kenya, and Tanzania.