Work

Artificial Intelligence in Neglected Tropical Diseases: Current Applications, Challenges, and Opportunities

Year: 2026
Type: preprint
Study design: Systematic Review
Abstract: 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.
Language: English
Field: Medicine
Open Access status: green
OpenAlex ID: W7236633708
Cites: 108
Cited by:
Related to: 10