Unsupervised machine learning predicts future sexual behaviour and sexually transmitted infections among HIV-positive men who have sex with men

Abstract

Machine learning is increasingly introduced into medical fields, yet there is limited evidence for its benefit over more commonly used statistical methods in epidemiological studies. We introduce an unsupervised machine learning framework for longitudinal features and evaluate it using sexual behaviour data from the last 20 years from over 3'700 participants in the Swiss HIV Cohort Study (SHCS). We use hierarchical clustering to find subgroups of men who have sex with men in the SHCS with similar sexual behaviour up to May 2017, and apply regression to test whether these clusters enhance predictions of sexual behaviour or sexually transmitted diseases (STIs) after May 2017 beyond what can be predicted with conventional parameters. We find that behavioural clusters enhance model performance according to likelihood ratio test, Akaike information criterion and area under the receiver operator characteristic curve for all outcomes studied, and according to Bayesian information criterion for five out of ten outcomes, with particularly good performance for predicting future sexual behaviour and recurrent STIs. We thus assess a methodology that can be used as an alternative means for creating exposure categories from longitudinal data in epidemiological models, and can contribute to the understanding of time-varying risk factors.

Fig 1. Overview of clustering and prediction method.

nsCAI = condomless anal intercourse with non-steady partners.

Fig 2. Trends in nsCAI proportion in behavioural clusters.

The clusters contain the following proportions of the study population (from 0 through 4): 49%, 11%, 17%, 10% and 13%. Cluster 0 consists of participants who never reported nsCAI during the observation period (in this case mid-2001 until the cut-off date). The dashed vertical line on the 1^st of May 2017 represents the cut-off date between the observation period (which corresponds to the period used to infer the clusters) and the outcome period. The shaded area shows the time in which nsCAI, nurse/physician-reported STIs and laboratory-confirmed syphilis were recorded as outcomes. nsCAI = condomless anal intercourse with non-steady partners.

Fig 3. Bar plots for Bayesian information criterion values.

Regression models with different combinations of predictor variables to predict nurse/physician-reported STIs (left), laboratory-confirmed syphilis (center) and nsCAI (right) after cut-off. A smaller BIC represents a better prediction. Numbers to the right of the bars represent the p value of the likelihood ratio test between the two models in question. nsCAI = condomless anal intercourse with non-steady partners. BIC = Bayesian information criterion. p_LRT = p value of likelihood ratio test comparing the respective models with and without clusters.