Dataset Information

A Machine-Learning-Based Risk-Prediction Tool for HIV and Sexually Transmitted Infections Acquisition over the Next 12 Months.

ABSTRACT: More than one million people acquire sexually transmitted infections (STIs) every day globally. It is possible that predicting an individual's future risk of HIV/STIs could contribute to behaviour change or improve testing. We developed a series of machine learning models and a subsequent risk-prediction tool for predicting the risk of HIV/STIs over the next 12 months. Our data included individuals who were re-tested at the clinic for HIV (65,043 consultations), syphilis (56,889 consultations), gonorrhoea (60,598 consultations), and chlamydia (63,529 consultations) after initial consultations at the largest public sexual health centre in Melbourne from 2 March 2015 to 31 December 2019. We used the receiver operating characteristic (AUC) curve to evaluate the model's performance. The HIV/STI risk-prediction tool was delivered via a web application. Our risk-prediction tool had an acceptable performance on the testing datasets for predicting HIV (AUC = 0.72), syphilis (AUC = 0.75), gonorrhoea (AUC = 0.73), and chlamydia (AUC = 0.67) acquisition. Using machine learning techniques, our risk-prediction tool has acceptable reliability in predicting HIV/STI acquisition over the next 12 months. This tool may be used on clinic websites or digital health platforms to form part of an intervention tool to increase testing or reduce future HIV/STI risk.

SUBMITTER: Xu X

PROVIDER: S-EPMC8999359 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine-Learning-Based Risk-Prediction Tool for HIV and Sexually Transmitted Infections Acquisition over the Next 12 Months.

Xu Xianglong X Ge Zongyuan Z Chow Eric P F EPF Yu Zhen Z Lee David D Wu Jinrong J Ong Jason J JJ Fairley Christopher K CK Zhang Lei L

Journal of clinical medicine 20220325 7

<h4>Background</h4>More than one million people acquire sexually transmitted infections (STIs) every day globally. It is possible that predicting an individual's future risk of HIV/STIs could contribute to behaviour change or improve testing. We developed a series of machine learning models and a subsequent risk-prediction tool for predicting the risk of HIV/STIs over the next 12 months.<h4>Methods</h4>Our data included individuals who were re-tested at the clinic for HIV (65,043 consultations), ...[more]

PMID: 35407428

Similar Datasets

Project description:Sexually transmitted infections (STIs) such as herpes simplex virus (HSV)-2 are associated with an increased risk of HIV infection. Human papillomavirus (HPV) is a common STI, but little is know about its role in HIV transmission. The objective of this study was to determine whether cervico-vaginal HPV infection increases the risk of HIV acquisition in women independent of other common STIs.This prospective cohort study followed 2040 HIV-negative Zimbabwean women (average age 27 years, range 18-49 years) for a median of 21 months. Participants were tested quarterly for 29 HPV types (with L1 PCR primers) and HIV (antibody testing on blood samples with DNA or RNA PCR confirmation). HIV incidence was 2.7 per 100 woman-years. Baseline HPV prevalence was 24.5%, and the most prevalent HPV types were 58 (5.0%), 16 (4.7%), 70 (2.4%), and 18 (2.3%). In separate regression models adjusting for baseline variables (including age, high risk partner, positive test for STIs, positive HSV-2 serology and condom use), HIV acquisition was associated with having baseline prevalent infection with HPV 58 (aHR 2.13; 95% CI 1.09-4.15) or HPV 70 (aHR 2.68; 95% CI 1.08-6.66). In separate regression models adjusting for both baseline variables and time-dependent variables (including HSV-2 status, incident STIs, new sexual partner and condom use), HIV acquisition was associated with concurrent infection with any non-oncogenic HPV type (aHR 1.70; 95% CI 1.02-2.85), any oncogenic HPV type (aHR 1.96; 95% CI 1.16-3.30), HPV 31 (aHR 4.25; 95% CI 1.81-9.97) or HPV 70 (aHR 3.30; 95% CI 1.50-7.20). Detection of any oncogenic HPV type within the previous 6 months was an independent predictor of HIV acquisition, regardless of whether HPV status at the HIV acquisition visit was included (aHR 1.95; 95% CI 1.19-3.21) or excluded (aHR 1.96; 95% CI 1.02-2.85) from the analysis.Cervico-vaginal HPV infection was associated with an increased risk of HIV acquisition in women, and specific HPV types were implicated in this association. The observational nature of our study precludes establishment of causation between HPV infection and HIV acquisition. However, given the high prevalence of HPV infection in women, further investigation of the role of HPV in HIV transmission is warranted.

Dataset Information

A Machine-Learning-Based Risk-Prediction Tool for HIV and Sexually Transmitted Infections Acquisition over the Next 12 Months.

Publications

A Machine-Learning-Based Risk-Prediction Tool for HIV and Sexually Transmitted Infections Acquisition over the Next 12 Months.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets