Artificial Intelligence in Neglected Tropical Diseases: Current Applications, Challenges, and Opportunities
Neglected tropical diseases (NTDs) affect more than one billion people globally, disproportionately burdening populations in low-resource tropical and subtropical settings. Recent advances in artificial intelligence (AI) offer considerable opportunities to strengthen NTD control, yet the scope, maturity, and translational readiness of AI applications across this disease portfolio remain incompletely characterized. We conducted a systematic review of peer-reviewed studies applying AI methods to NTD-related problems, searching multiple databases using predefined strategies and screening studies against explicit inclusion and exclusion criteria. Data were extracted on disease focus, AI methodology, data modalities, validation strategies, performance metrics, and implementation context. Thematic analyses were performed to characterize research trends, geographic distribution, and research priorities. Reporting followed PRISMA guidelines. We identified a rapidly expanding but uneven body of literature spanning 289 studies, dominated by applications in disease diagnosis (40.1%), prognosis (17.7%), surveillance (15.2%), outbreak prediction (13.5%), treatment monitoring (7.3%), and drug discovery (6.2%). Over 70% of studies employed supervised machine learning or deep learning applied to imaging, clinical, or epidemiological data. Performance was frequently reported using discrimination metrics, while calibration, external validation, and prospective evaluation remained uncommon. Research activity is concentrated in a small number of countries and institutions, notably Brazil and India, with limited representation from other highly endemic regions, particularly sub-Saharan Africa and South-East Asia. Only a minority of studies addressed considerations critical for real-world deployment, including data governance, health system integration, explainability, fairness, and interpretability. AI holds substantial promise for supporting NTD control and elimination, but the current evidence base reveals important methodological, geographic, and translational gaps. Future research should prioritize robust validation, transparent reporting, equity-aware design, and meaningful engagement with endemic-country stakeholders. Coordinated investment in data infrastructure, capacity building, and governance frameworks will be essential if AI-enabled innovations are to translate into sustainable public health impact for the populations most affected by NTDs.
Authors
- Oghenekaro Nelson Odume (ORCID: https://orcid.org/0000-0001-5220-3254)
- Ntethelelo Hopewell Sibiya (ORCID: https://orcid.org/0000-0001-5894-8935)
- Habte Tadesse Likassa (ORCID: https://orcid.org/0000-0002-9334-8588)
- Pedzisai A. Makoni (ORCID: https://orcid.org/0000-0002-8475-447X)
- Shoeshoe Mokhele (ORCID: https://orcid.org/0000-0001-8899-7711)
- Mikel K. Ngueajio (ORCID: https://orcid.org/0000-0002-9696-2372)
- Sébastien Lalléchère (ORCID: https://orcid.org/0000-0001-7517-672X)
- H. M. Tenkam (ORCID: https://orcid.org/0000-0001-6901-8047)
- Yolande Ngueabou (ORCID: https://orcid.org/0000-0001-9718-0893)
- Chika Felicitas Nnadozie (ORCID: https://orcid.org/0000-0001-6177-2627)
- Thierry Bouwmans (ORCID: https://orcid.org/0000-0003-4018-8856)
- Blaise Ravelo (ORCID: https://orcid.org/0000-0001-7334-5016)
- Yusuf Brima (ORCID: https://orcid.org/0000-0002-9975-8676)
- Lansana Hassim Kallon (ORCID: https://orcid.org/0000-0002-3804-5218)
- Bwalya Angel Witika (ORCID: https://orcid.org/0000-0002-4034-9368)
- Louis P. Sandjo (ORCID: https://orcid.org/0000-0001-5840-7733)
- Arnaud Nguembang Fadja (ORCID: https://orcid.org/0000-0003-3352-5260)
- Marcellin Atemkeng (ORCID: https://orcid.org/0000-0002-9020-3885)
- Stephen Gbenga Fashoto (ORCID: https://orcid.org/0000-0002-2919-9434)
- Siphendulwe Zaza
- Ding-Geng Chen
- Xavier Siwe Noundou
- Elizabeth Mukusya Mwania
- Lerato Sarah Mosima
- Bruno Gabriel Larsen Soares
- Lukeman Sahid Kamara
- Linuce Demanou Kitio
- Samuel Saidu
- Adam Kargbo
- Ndzamba Bonginkosi
- Jean Louis Ebongue Kedieng Fendji
- Masixole Jojo
- Tatchou Nkouindja Daniel Nathan
Institutions
- Namibia University of Science and Technology (NA)
- Howard University (US)
- African Institute for Mathematical Sciences (ZA)
- Osnabrück University (DE)
- Nanjing University of Information Science and Technology (CN)
- University of Ferrara (IT)
- Rhodes University (ZA)
- North-West University (ZA)
- Sefako Makgatho Health Sciences University (ZA)
- University of Makeni (SL)
- Universidade Federal de Santa Catarina (BR)
- London School of Hygiene & Tropical Medicine (GB)
- African Institute for Mathematical Sciences (CM)
- Deutsche Lepra- und Tuberkulosehilfe (DE)
- Huazhong University of Science and Technology (CN)
- Arizona State University (US)
- University of Ngaoundéré (CM)
- La Rochelle Université (FR)
Publication Details
- Journal
- Research Square
- Published
- 2026-11-19
- DOI
- https://doi.org/10.21203/rs.3.rs-9290347/v1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- preprint