Embargoed and Restricted Access
Reason: Under embargo until 2023. After this date a copy can be supplied under Section 51(2) of the Australian Copyright Act 1968 by submitting a document delivery request through your library.
Investigating the transmission dynamics and predicting the risk of HIV and sexually transmitted infections using mathematical modelling and machine learning algorithms
Sequential sexual practices involving the oropharynx and saliva may increase the transmission of Neisseria gonorrhoeae and Chlamydia trachomatis at multiple anatomical sites in MSM. For Mycoplasma genitalium, only oral and anal sex can explain the transmission at multiple anatomical sites without the need to invoke transmission by kissing or rimming. Machine learning predictive models based on self-reported questions can predict the current and future risk of HIV/STIs acquisition and have been translated into a web-based prediction tool named MySTIRisk. Using routinely collected data in clinical settings, machine learning algorithms also can predict clinic visits and HIV/STIs testing.