The Role of Big Data in Developing Innovative Predictive Learning Models for Neglected Tropical Diseases within the New Generation of the Evidence-Based Medicine Pyramid

Neglected tropical diseases (NTDs) have been identified as a major global health burden, particularly in low- and middle-income countries, yet limited scientific attention has been given to them. Simultaneously, the emergence of Big Data and artificial intelligence has been transforming the way medical evidence is produced. Despite this, minimal integration between Big Data approaches and NTDs research has been observed. To explore this gap, a narrative review with a brief scientometrics analysis was conducted alongside a critical review of 13 original studies and systematic reviews that applied Big Data to NTDs. Studies were assessed according to design, objectives, disease focus, and geographic scope. Findings revealed a significant disparity: although extensive literature exists on Big Data and on NTDs separately, only a small number of studies combine both. Most of these were focused on dengue, with limited geographic representation and methodological consistency. These results suggest that the field remains underdeveloped and fragmented. Opportunities for interdisciplinary and data-intensive approaches have not been fully utilized. It is proposed that, by aligning Big Data applications with the new generation of the evidence-based medicine pyramid, more inclusive, predictive, and context-sensitive research on NTDs could be enabled, supporting equitable health decision-making in historically neglected populations.