Computational methods applied to syphilis: where are we, and where are we going?

Area of Science:

• Computational epidemiology
• Public health informatics
• Machine learning in infectious disease control

Background:

• Syphilis is a curable yet increasingly prevalent infectious disease globally.
• Effective public health strategies are needed to combat rising syphilis rates.
• Computational methods offer potential for data analysis to inform syphilis control policies.

Approach:

• Systematic review of studies (2015-2022) using computational methods for syphilis.
• Searched major scientific databases (e.g., PubMed, Scopus, Web of Science).
• Included 26 primary studies after rigorous quality assessment.

Key Points:

• Computational approaches, particularly Machine Learning, are applied to syphilis surveillance (61.54%), diagnosis (34.62%), and policy evaluation (3.85%).
• These methods improve understanding of disease dynamics and inform targeted interventions.
• Tools support enhanced syphilis surveillance, prevention, and diagnostic strategies.

Conclusions:

• Computational tools are valuable for understanding and managing the global syphilis epidemic.
• These methods can guide public health policy and optimize interventions.
• Machine learning and data analysis show promise for syphilis control and surveillance efforts.