Machine learning analysis of global leishmaniasis distribution reveals a 17% increase in disease risk since the 1990s, with Africa, Asia, and the Americas showing the greatest expansion. The study mapped five European sand fly vector species and found that land use patterns, particularly shrubland and forest cover, were the strongest predictors of disease presence, alongside climatic factors like mean temperature during cold quarters and humidity patterns. Socio-economic indicators consistently improved model accuracy, confirming poverty as a key disease determinant. This research illuminates how climate change is reshaping the global burden of neglected tropical diseases. Leishmaniasis, transmitted by sand flies and causing devastating skin lesions or potentially fatal organ damage, predominantly affects marginalized populations lacking healthcare access. The northward European expansion and geographic shifts in vector species distribution suggest that regions previously considered safe may face emerging risks. The study's integration of environmental and social determinants provides a more complete picture than purely climatic models. However, as an unreviewed preprint, these findings require validation through peer review. The results represent important but incremental progress in disease modeling, offering valuable insights for public health preparedness as climate patterns continue shifting globally.