Network context matters: graph convolutional network model over social networks improves the detection of unknown HIV infections among young men who have sex with men

Explainable artificial intelligence and domain adaptation for predicting HIV infection with graph neural networks

OBJECTIVE

Investigation of explainable deep learning methods for graph neural networks to predict HIV infections with social network information and performing domain adaptation to evaluate model transferability across different datasets.

METHODS

Network data from two cohorts of younger sexual minority men (SMM) from two U.S. cities (Chicago, IL, and Houston, TX) were collected between 2014 and 2016. Feature importance from graph attention network (GAT) models were determined using GNNExplainer. Domain adaptation was performed to examine model transferability from one city dataset to the other dataset, training with 100% of the source dataset with 30% of the target dataset and prediction on the remaining 70% from the target dataset.

RESULTS

Domain adaptation showed the ability of GAT to improve prediction over training with single city datasets. Feature importance analysis with GAT models in single city training indicated similar features across different cities, reinforcing potential application of GAT models in predicting HIV infections through domain adaptation.

CONCLUSION

GAT models can be used to address the data sparsity issue in HIV study populations. They are powerful tools for predicting individual risk of HIV that can be further explored for better understanding of HIV transmission.

Web-Based Risk Prediction Tool for an Individual's Risk of HIV and Sexually Transmitted Infections Using Machine Learning Algorithms: Development and External Validation Study

Background

HIV and sexually transmitted infections (STIs) are major global public health concerns. Over 1 million curable STIs occur every day among people aged 15 years to 49 years worldwide. Insufficient testing or screening substantially impedes the elimination of HIV and STI transmission.

Objective

The aim of our study was to develop an HIV and STI risk prediction tool using machine learning algorithms.

Methods

We used clinic consultations that tested for HIV and STIs at the Melbourne Sexual Health Centre between March 2, 2015, and December 31, 2018, as the development data set (training and testing data set). We also used 2 external validation data sets, including data from 2019 as external “validation data 1” and data from January 2020 and January 2021 as external “validation data 2.” We developed 34 machine learning models to assess the risk of acquiring HIV, syphilis, gonorrhea, and chlamydia. We created an online tool to generate an individual’s risk of HIV or an STI.

Results

The important predictors for HIV and STI risk were gender, age, men who reported having sex with men, number of casual sexual partners, and condom use. Our machine learning–based risk prediction tool, named MySTIRisk, performed at an acceptable or excellent level on testing data sets (area under the curve [AUC] for HIV=0.78; AUC for syphilis=0.84; AUC for gonorrhea=0.78; AUC for chlamydia=0.70) and had stable performance on both external validation data from 2019 (AUC for HIV=0.79; AUC for syphilis=0.85; AUC for gonorrhea=0.81; AUC for chlamydia=0.69) and data from 2020-2021 (AUC for HIV=0.71; AUC for syphilis=0.84; AUC for gonorrhea=0.79; AUC for chlamydia=0.69).

Conclusions

Our web-based risk prediction tool could accurately predict the risk of HIV and STIs for clinic attendees using simple self-reported questions. MySTIRisk could serve as an HIV and STI screening tool on clinic websites or digital health platforms to encourage individuals at risk of HIV or an STI to be tested or start HIV pre-exposure prophylaxis. The public can use this tool to assess their risk and then decide if they would attend a clinic for testing. Clinicians or public health workers can use this tool to identify high-risk individuals for further interventions.

Organizational Geosocial Network: A Graph Machine Learning Approach Integrating Geographic and Public Policy Information for Studying the Development of Social Organizations in China

This study aims to give an insight into the development trends and patterns of social organizations (SOs) in China from the perspective of network science integrating geography and public policy information embedded in the network structure. Firstly, we constructed a first-of-its-kind database which encompasses almost all social organizations established in China throughout the past decade. Secondly, we proposed four basic structures to represent the homogeneous and heterogeneous networks between social organizations and related social entities, such as government administrations and community members. Then, we pioneered the application of graph models to the field of organizations and embedded the Organizational Geosocial Network (OGN) into a low-dimensional representation of the social entities and relations while preserving their semantic meaning. Finally, we applied advanced graph deep learning methods, such as graph attention networks (GAT) and graph convolutional networks (GCN), to perform exploratory classification tasks by training models with county-level OGNs dataset and make predictions of which geographic region the county-level OGN belongs to. The experiment proves that different regions possess a variety of development patterns and economic structures where local social organizations are embedded, thus forming differential OGN structures, which can be sensed by graph machine learning algorithms and make relatively accurate predictions. To the best of our knowledge, this is the first application of graph deep learning to the construction and representation learning of geosocial network models of social organizations, which has certain reference significance for research in related fields.

Integrated molecular and affiliation network analysis: Core-periphery social clustering is associated with HIV transmission patterns

This study investigates the two-mode core-periphery structures of venue affiliation networks of younger Black men who have sex with men (YBMSM). We examined the association between these structures and HIV phylogenetic clusters, defined as members who share highly similar HIV strains that are regarded as a proxy for sexual affiliation networks. Using data from 114 YBMSM who are living with HIV in two large U.S. cities, we found that HIV phylogenetic clustering patterns were associated with social clustering patterns whose members share affiliation with core venues that overlap with those of YBMSM. Distinct HIV transmission patterns were found in each city, a finding that can help to inform tailored venue-based and network intervention strategies.

Application of artificial intelligence and machine learning for HIV prevention interventions

In 2019, the US Government announced its goal to end the HIV epidemic within 10 years, mirroring the initiatives set forth by UNAIDS. Public health prevention interventions are a crucial part of this ambitious goal. However, numerous challenges to this goal exist, including improving HIV awareness, increasing early HIV infection detection, ensuring rapid treatment, optimising resource distribution, and providing efficient prevention services for vulnerable populations. Artificial intelligence has had a pivotal role in revolutionising health care and has shown great potential in developing effective HIV prevention intervention strategies. Although artificial intelligence has been used in a few HIV prevention intervention areas, there are challenges to address and opportunities to explore.

Machine Learning Classification of False-Positive Human Immunodeficiency Virus Screening Results

BACKGROUND

Human immunodeficiency virus (HIV) screening has improved significantly in the past decade as we have implemented tests that include antigen detection of p24. Incorporation of p24 detection narrows the window from 4 to 2 weeks between infection acquisition and ability to detect infection, reducing unintentional spread of HIV. The fourth- and fifth-generation HIV (HIV5G) screening tests in low prevalence populations have high numbers of false-positive screens and it is unclear if orthogonal testing improves diagnostic and public health outcomes.

METHODS

We used a cohort of 60,587 HIV5G screening tests with molecular and clinical correlates collected from 2016 to 2018 and applied machine learning to generate a classifier that could predict likely true and false positivity.

RESULTS

The best classification was achieved by using support vector machines and transformation of results with principle component analysis. The final classifier had an accuracy of 94% for correct classification of false-positive screens and an accuracy of 92% for classification of true-positive screens.

CONCLUSIONS

Implementation of this classifier as a screening method for all HIV5G reactive screens allows for improved workflow with likely true positives reported immediately to reduce infection spread and initiate follow-up testing and treatment and likely false positives undergoing orthogonal testing utilizing the same specimen already drawn to reduce distress and follow-up visits. Application of machine learning to the clinical laboratory allows for workflow improvement and decision support to provide improved patient care and public health.

Identifying influential neighbors in social networks and venue affiliations among young MSM: a data science approach to predict HIV infection

OBJECTIVE

Young MSM (YMSM) bear a disproportionate burden of HIV infection in the United States and their risks of acquiring HIV may be shaped by complex multilayer social networks. These networks are formed through not only direct contact with social/sex partners but also indirect anonymous contacts encountered when attending social venues. We introduced a new application of a state-of-the-art graph-based deep learning method to predict HIV infection that can identify influential neighbors within these multiple network contexts.

DESIGN AND METHODS

We used empirical network data among YMSM aged 16-29 years old collected from Houston and Chicago in the United States between 2014 and 2016. A computational framework GAT-HIV (Graph Attention Networks for HIV) was proposed to predict HIV infections by identifying influential neighbors within social networks. These networks were formed by multiple relations constituted of social/sex partners and shared venue attendances, and using individual-level variables. Further, GAT-HIV was extended to combine multiple social networks using multigraph GAT methods. A visualization tool was also developed to highlight influential network members for each individual within the multiple social networks.

RESULTS

The multigraph GAT-HIV models obtained average AUC values of 0.776 and 0.824 for Chicago and Houston, respectively, performing better than empirical predictive models (e.g. AUCs of random forest: 0.758 and 0.798). GAT-HIV on single networks also delivered promising prediction performances.

CONCLUSION

The proposed methods provide a comprehensive and interpretable framework for graph-based modeling that may inform effective HIV prevention intervention strategies among populations most vulnerable to HIV.

Addressing Intersecting Social and Mental Health Needs Among Transition-Age Homeless Youths: A Review of the Literature

Homelessness among youths is a poorly understood and complex social phenomenon. The authors examined the risk factors for homelessness among transition-age young adults, including the unique mental health concerns that often perpetuate the cycle of poverty and housing instability among these youths. The authors discuss the treatment gaps for mental health conditions in this population and identify potential solutions for reducing existing barriers to care. A literature review revealed that many studies report high rates of trauma and subsequent mental health problems among homeless youths. Intervention studies are challenging to conduct with this population and often have high attrition rates. Youths who are homeless desire mental health services and are especially enthusiastic about programs that address interpersonal difficulties and emotion regulation. Clinical data suggest that future interventions should address trauma more directly in this population. Technology-based interventions may help address the needs of homeless youths and may maximize their access to care. Because youths strongly prefer technology-based platforms, future research should integrate these platforms to better address the mental health needs identified as most salient by homeless youths. The authors discuss proposed policy changes at local, state, and federal levels to improve uptake of this proposed strategy.

Revealing Intention In Health-related Peer Interactions: Implications For Optimizing Patient Engagement In Self-health Management

Risky health behaviors such as poor diet, physical inactivity are the main contributors to the development of diabetes, one of the major causes of death and disability in the United States. Online health communities provide new avenues for individuals to efficiently manage their health conditions and adopt a positive lifestyle. So far, analysis of health-related online social exchanges has focused solely on communication content and structure of social ties, ignoring implicit user intentions underlying communication exchanges. In this paper, we propose an analytical framework to characterize communication intent, content, and social ties in online peer interactions. We integrate models from socio-behavioral sciences and linguistics with network analytics and apply it to understand Diabetes Self-Management. Results indicate the informational needs of users expressed in forms of speech acts can vary across different user engagement and disease management profiles. Implications for the design of interventions for better self-management of diabetes are discussed.