Predicting sexually transmitted infections among men who have sex with men in Zimbabwe using deep learning and ensemble machine learning models.

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.

Access to HIV prevention, treatment, and care services during COVID-19 by men who have sex with men in Zimbabwe, An interpretive phenomenological analysis study.

BACKGROUND: Key populations are disproportionately affected by the human immunodeficiency virus (HIV) but have less access to HIV prevention and treatment services. The Coronavirus disease-2019 (COVID-19) pandemic is reinforcing health inequities among vulnerable populations, including men who have sex with men (MSM). Therefore, this article presents the findings describing the experiences of MSM in accessing HIV services during COVID-19 in the second largest city of Zimbabwe. METHODS: An interpretative phenomenological analysis design was applied to gain some insights regarding the lived experiences of MSM in accessing HIV prevention, treatment, and care services during COVID-19 lockdowns era in Zimbabwe. Data were collected from 14 criterion purposively selected MSM using in-depth, one-on-one interviews. Data were analysed thematically guided by the interpretative phenomenological analysis framework for data analysis. RESULTS: The findings demonstrated that during the COVID -19 lockdowns in Zimbabwe, MSM faced several barriers as they tried to access HIV services. Some of the barriers included the need for travel authorisation letters and treatment interruption. The study also found that COVID-19 and related restrictive measures had psychosocial and economic effects that encompassed loss of income, intimate partner violence and psychological effects. CONCLUSIONS: Limited access to healthcare services by MSM due to COVID-19 lockdown may negatively affect the viral suppression and fuel the spread of HIV, which may reverse the gains toward the control of HIV epidemic. To sustain the gains toward HIV epidemic control and to ensure continuity of treatment, particularly for members of key populations, it is critical that the health-care delivery system adjusts by taking service to the community through adopting a differentiated service delivery approach.