Related Experiment Video
Updated: Jun 22, 2025
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
Predicting sexually transmitted infections among men who have sex with men in Zimbabwe using deep learning and
Owen Mugurungi1, Elliot Mbunge2, Rutendo Birri-Makota3
1AIDS and TB Programme, Ministry of Health and Child Care, AIDS & TB Programme, Harare, Zimbabwe.
Abstract:
There is a substantial increase in sexually transmitted infections (STIs) among men who have sex with men (MSM) globally. Unprotected sexual practices, multiple sex partners, criminalization, stigmatisation, fear of discrimination, substance use, poor access to care, and lack of early STI screening tools are among the contributing factors. Therefore, this study applied multilayer perceptron (MLP), extremely randomized trees (ExtraTrees) and XGBoost machine learning models to predict STIs among MSM using bio-behavioural survey (BBS) data in Zimbabwe. Data were collected from 1538 MSM in Zimbabwe. The dataset was split into training and testing sets using the ratio of 80% and 20%, respectively. The synthetic minority oversampling technique (SMOTE) was applied to address class imbalance. Using a stepwise logistic regression model, the study revealed several predictors of STIs among MSM such as age, cohabitation with sex partners, education status and employment status. The results show that MLP performed better than STI predictive models (XGBoost and ExtraTrees) and achieved accuracy of 87.54%, recall of 97.29%, precision of 89.64%, F1-Score of 93.31% and AUC of 66.78%. XGBoost also achieved an accuracy of 86.51%, recall of 96.51%, precision of 89.25%, F1-Score of 92.74% and AUC of 54.83%. ExtraTrees recorded an accuracy of 85.47%, recall of 95.35%, precision of 89.13%, F1-Score of 92.13% and AUC of 60.21%. These models can be effectively used to identify highly at-risk MSM, for STI surveillance and to further develop STI infection screening tools to improve health outcomes of MSM.
Insights
Machine learning models accurately predict sexually transmitted infections (STIs) in men who have sex with men (MSM). Multilayer perceptron (MLP) showed the highest accuracy, aiding in identifying high-risk individuals for improved STI surveillance and screening.
Area of Science:
- Public Health
- Infectious Diseases
- Machine Learning in Healthcare
Background:
- Sexually transmitted infections (STIs) pose a significant global health challenge, particularly among men who have sex with men (MSM).
- Contributing factors include unprotected sex, multiple partners, stigma, substance use, and limited access to screening and care.
- Predictive modeling can enhance early detection and intervention strategies for STIs in vulnerable populations.
Purpose of the Study:
- To apply and compare machine learning models for predicting STIs among MSM using bio-behavioural survey data.
- To identify key demographic and behavioral predictors associated with STI risk in this population.
- To evaluate the performance of Multilayer Perceptron (MLP), XGBoost, and ExtraTrees models in STI prediction.
Main Methods:
- Utilized bio-behavioural survey (BBS) data from 1538 MSM in Zimbabwe.
- Employed Multilayer Perceptron (MLP), Extremely Randomized Trees (ExtraTrees), and XGBoost machine learning models.
- Applied Synthetic Minority Oversampling Technique (SMOTE) for class imbalance and logistic regression for predictor identification.
Main Results:
- MLP achieved the highest accuracy (87.54%), recall (97.29%), precision (89.64%), F1-Score (93.31%), and AUC (66.78%).
- XGBoost and ExtraTrees also demonstrated strong predictive performance, with accuracies of 86.51% and 85.47%, respectively.
- Age, cohabitation, education, and employment status were identified as significant predictors of STIs among MSM.
Conclusions:
- Machine learning models, particularly MLP, are effective tools for predicting STIs in MSM populations.
- These models can significantly aid in identifying high-risk individuals for targeted STI surveillance and screening.
- Improved prediction tools can lead to better health outcomes and more effective public health interventions for MSM.
More Related Videos
Related Concept Videos
01:18Steps in Outbreak Investigation
01:26Sexually Transmitted Infections