The role of machine learning in HIV risk prediction

Abstract

Despite advances in reducing HIV-related mortality, persistently high HIV incidence rates are undermining global efforts to end the epidemic by 2030. The UNAIDS Fast-track targets as well as other preventative strategies, such as pre-exposure prophylaxis, have been identified as priority areas to reduce the ongoing transmission threatening to undermine recent progress. Accurate and granular risk prediction is critical for these campaigns but is often lacking in regions where the burden is highest. Owing to their ability to capture complex interactions between data, machine learning and artificial intelligence algorithms have proven effective at predicting the risk of HIV infection in both high resource and low resource settings. However, interpretability of these algorithms presents a challenge to the understanding and adoption of these algorithms. In this perspectives article, we provide an introduction to machine learning and discuss some of the important considerations when choosing the variables used in model development and when evaluating the performance of different machine learning algorithms, as well as the role emerging tools such as Shapely Additive Explanations may play in helping understand and decompose these models in the context of HIV. Finally, we discuss some of the potential public health and clinical use cases for such decomposed risk assessment models in directing testing and preventative interventions including pre-exposure prophylaxis, as well as highlight the potential integration synergies with algorithms that predict the risk of sexually transmitted infections and tuberculosis.

Use of feature importance statistics to accurately predict asthma attacks using machine learning: A cross-sectional cohort study of the US population

“…This alignment of these covariates with literature not only in statistical significance, but also in the direction of the relationships increase our confidence that the model accurately captures the physiological relationships of these factors. By using transparent machine learning tools, we can ensure that the model is detecting genuine signals within these covariates to predict asthma attacks, rather than simply replicating biases present in the dataset [32][33][34][35]. The SHAP visualizations further support the increased predictive power of these non-parametric methods by demonstrating their ability to accurately capture the non-linear interactions between covariates, without overfitting the model to achieve greater accuracy [20,[36][37][38][39].…”

Building gender-specific sexually transmitted infection risk prediction models using CatBoost algorithm and NHANES data

“…Bao et al [ 7 ] aimed to develop and evaluate the performance of machine learning models in predicting the diagnosis of HIV and STIs based on a large retrospective cohort of Australian men who have sex with men (MSM). Fieggen et al [ 8 ] discussed crucial considerations when selecting variables for model development and evaluating the performance of various machine learning algorithms, as well as the potential role of emerging tools such as Shapley Additive Explanations in understanding and decomposing these models in the context of HIV. Xu et al [ 9 ] sought to identify determinants and predict chlamydia re-testing and re-infection within one year among heterosexuals with chlamydia to pinpoint potential PDPT (Patient-Delivered Partner Therapy) candidates.…”

Predicting the individualized risk of human immunodeficiency virus infection among sexually active women in Ethiopia using a nomogram: prediction model development and validation

“…In addition, psychosocial factors such as perception of barriers to safe sex, condom use negotiation self-efficacy, and HIV prevention knowledge play a significant role in the utilization of condoms ( 23 , 24 ). In addition, three mechanisms, namely, pre-exposure prophylaxis, behavioral change communications, and early initiation of ART remain vital strategies for preventing HIV/AIDS transmission ( 25 ).…”

“…Identification of individuals at high risk for HIV/AIDS and linking them to prevention services is essential for continued progress toward ending HIV as a public health threat ( 26 , 27 ). Risk estimation tools, such as nomograms, could play a role in directing targeted preventive strategies through the quantification of individualized risk ( 25 ). Predicting the risk of HIV infection is also used as an early-warning system to notify prevention programs ( 28 ).…”