Predicting congenital syphilis: Using machine learning to enhance disease management and control

ObjectiveSexually Transmitted Infections (STIs) present significant challenges to global public health, affecting physical and mental well-being and straining healthcare systems and economies. This study aims to enhance the predictive performance of models for congenital syphilis prediction by incorporating additional information obtained during gestational follow-up. Building upon the work of Teixeira et al. [1], which utilizes clinical and sociodemographic data, our model was enriched with results from venereal disease research laboratory (VDRL) and rapid tests for congenital syphilis conducted on pregnant women. MethodThe dataset utilized in this study comprised 47,604 records spanning the period from 2013 to 2022, with 27 attributes collected from pregnant women enrolled in the Mae Coruja Pernambucana Program in Pernambuco, Brazil. Among these attributes, we included clinical and sociodemographic factors, as well as results from venereal disease research laboratory (VDRL) and rapid tests for congenital syphilis. ResultsOur proposed model surpassed Teixeiras models exhibiting higher specificity (94.74%) and a slight increase in sensitivity (70.37%). ConclusionsOur study highlights the value of incorporating additional information from VDRL and rapid tests into models for predicting congenital syphilis. The combined approach involving both clinical, sociodemographic, and test result data enhances the accuracy of predictions thereby facilitating better informed healthcare decisions at different stages of pregnancy. This approach also holds significant potential in combating and managing congenital syphilis by providing assistance to health system decision makers and public policymakers. As a result, it can ultimately enhance the overall outcomes of maternal and child health and contribute to disease control.