Temporal and Spatiotemporal Arboviruses Forecasting by Machine Learning: A Systematic Review.

Area of Science:

• Epidemiology
• Public Health
• Vector-borne Diseases

Background:

• Arboviruses, transmitted by arthropod vectors, are significant Neglected Tropical Diseases (NTDs) posing global public health challenges.
• Disease dynamics are influenced by complex interactions between climate, environment, and human mobility.
• Effective prediction models are crucial for public health decision-making and disease surveillance.

Approach:

• A systematic literature review was conducted to identify arbovirus prediction models and their vector dynamics.
• Searches were performed on major scientific databases (IEEE Xplore, PubMed, Science Direct, Springer Link, Scopus).
• Studies published between 2015 and 2020 were analyzed, with 139 articles included after filtering.

Key Points:

• Identified challenges in developing accurate arbovirus prediction models.
• Highlighted a significant gap in the development of spatiotemporal models for arboviruses.
• The review synthesizes current knowledge on modeling arbovirus and vector dynamics.

Conclusions:

• Systematic review provides insights into the current state of arbovirus prediction modeling.
• Identified limitations and future research directions, particularly in spatiotemporal analysis.
• Findings support enhanced public health strategies for managing arboviral diseases.