Explainable artificial intelligence and domain adaptation for predicting HIV infection with graph neural networks
Open Access
- 17 October 2024
- journal article
- research article
- Published by Taylor & Francis in Annals of Medicine
- Vol. 56 (1)
Abstract
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. 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. 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. 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.Keywords
Funding Information
- Gulf Coast Consortia
- NLM Training Program in Biomedical Informatics and Data Science (T15 LM007093)
- National Institutes of Health (R56AI150272, R01MH100021, U24AI171008)
This publication has 37 references indexed in Scilit:
- Depression severity is associated with increased risk behaviors and decreased CD4 cell countsAIDS Care, 2014
- Social Networks, Sexual Networks and HIV Risk in Men Who Have Sex with MenCurrent HIV/AIDS Reports, 2014
- Characteristics associated with HIV infection among heterosexuals in urban areas with high AIDS prevalence --- 24 cities, United States, 2006-2007.2011
- Epidemiology of HIV Infection in Large Urban Areas in the United StatesPLOS ONE, 2010
- Mathematical Models for HIV Transmission DynamicsJAIDS Journal of Acquired Immune Deficiency Syndromes, 2008
- HIV and African Americans in the Southern United States: Sexual Networks and Social ContextSexually Transmitted Diseases, 2006
- Emerging future issues in HIV/AIDS social researchAIDS, 2006
- Risk factors for HIV infection among men who have sex with menAIDS, 2006
- Depression and HIV Risk Behaviors Among Patients in a Sexually Transmitted Disease ClinicAmerican Journal of Psychiatry, 2004
- Effectiveness of condoms in preventing HIV transmissionSocial Science & Medicine, 1997