Predicting congenital syphilis cases: a performance evaluation of different machine learning models

Abstract

Background Communicable diseases represent a huge economic burden for healthcare systems and for society. Sexually transmitted infections (STIs) are a concerning issue, especially in developing and underdeveloped countries, in which environmental factors and other determinants of health play a role in contributing to its fast spread. In light of this situation, machine learning techniques have been explored to assess the incidence of syphilis and contribute to the epidemiological surveillance in this scenario. Objective The main goal of this work is to evaluate the performance of different machine learning models on predicting undesirable outcomes of congenital syphilis in order to assist resources allocation and optimize the healthcare actions, especially in a constrained health environment. Method We use clinical and sociodemographic data from pregnant women that were assisted by a social program in Pernambuco, Brazil, named Ma˜e Coruja Pernambucana Program (PMCP). Based on a rigorous methodology, we propose six experiments using three feature selection techniques to select the most relevant attributes, pre-process and clean the data, apply hyperparameter optimization to tune the machine learning models, and train and test models to have a fair evaluation and discussion. Results The AdaBoost-BODS-Expert model, an Adaptive Boosting (AdaBoost) model that used attributes selected by health experts, presented the best results in terms of evaluation metrics and acceptance by health experts from PMCP. By using this model, the results are more reliable and allows adoption on a daily usage to classify possible outcomes of congenital syphilis using clinical and sociodemographic data.

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

“…The number of records in the pre-processed data set used in our study uses an updated data set with new records from 2022. This increases the total data set from 41,762 records as per Teixeira et al [1] to 47,604 records in this study. This increase also led to an increase in the number of positive cases for CS from 826 in Teixeira et al [1] to 1002 in this study.…”

“…This increases the total data set from 41,762 records as per Teixeira et al [1] to 47,604 records in this study. This increase also led to an increase in the number of positive cases for CS from 826 in Teixeira et al [1] to 1002 in this study.…”

“…For comparison, we use the scenario that produced the best results by Teixeira et al [1]. This scenario, called BODS-Expert (Balanced with One-hot Encoding Data Set from the expert), which is a data set built by considering attributes carefully chosen by health experts with balanced data, applying the one-hot encoding technique.…”

“…Our main objective is to examine whether the inclusion of additional information acquired during the gestational follow-up process leads to an improvement in the predictive performance of models for CS. We supplement the clinical and sociodemographic data used by Teixeira et al [1] with venereal disease research laboratory (VDRL) and rapid test results from pregnant women. By incorporating this extra information for training our models, our hypothesis is that we can improve the model prediction process and, consequently, may be able to provide more precise predictions.…”

“…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.…”