Machine-learning classification of neurocognitive performance in children with perinatal HIV initiating de novo antiretroviral therapy

Robert H. Paul*, Kyu S. Cho, Andrew C. Belden, Claude A. Mellins, Kathleen M. Malee, Reuben N. Robbins, Lauren E. Salminen, Stephen J. Kerr, Badri Adhikari, Paola M. Garcia-Egan, Jiratchaya Sophonphan, Linda Aurpibul, Kulvadee Thongpibul, Pope Kosalaraksa, Suparat Kanjanavanit, Chaiwat Ngampiyaskul, Jurai Wongsawat, Saphonn Vonthanak, Tulathip Suwanlerk, Victor G. ValcourRebecca N. Preston-Campbell, Jacob D. Bolzenious, Merlin L. Robb, Jintanat Ananworanich, Thanyawee Puthanakit

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Objective:To develop a predictive model of neurocognitive trajectories in children with perinatal HIV (pHIV).Design:Machine learning analysis of baseline and longitudinal predictors derived from clinical measures utilized in pediatric HIV.Methods:Two hundred and eighty-five children (ages 2-14 years at baseline; Mage = 6.4 years) with pHIV in Southeast Asia underwent neurocognitive assessment at study enrollment and twice annually thereafter for an average of 5.4 years. Neurocognitive slopes were modeled to establish two subgroups [above (n = 145) and below average (n = 140) trajectories). Gradient-boosted multivariate regressions (GBM) with five-fold cross validation were conducted to examine baseline (pre-ART) and longitudinal predictive features derived from demographic, HIV disease, immune, mental health, and physical health indices (i.e. complete blood count [CBC]).Results:The baseline GBM established a classifier of neurocognitive group designation with an average AUC of 79% built from HIV disease severity and immune markers. GBM analysis of longitudinal predictors with and without interactions improved the average AUC to 87 and 90%, respectively. Mental health problems and hematocrit levels also emerged as salient features in the longitudinal models, with novel interactions between mental health problems and both CD4+cell count and hematocrit levels. Average AUCs derived from each GBM model were higher than results obtained using logistic regression.Conclusion:Our findings support the feasibility of machine learning to identify children with pHIV at risk for suboptimal neurocognitive development. Results also suggest that interactions between HIV disease and mental health problems are early antecedents to neurocognitive difficulties in later childhood among youth with pHIV.

Original languageEnglish (US)
Pages (from-to)737-748
Number of pages12
Issue number5
StatePublished - Apr 1 2020


  • cognition
  • development
  • machine learning
  • mental health
  • perinatal HIV

ASJC Scopus subject areas

  • Immunology and Allergy
  • Immunology
  • Infectious Diseases

Fingerprint Dive into the research topics of 'Machine-learning classification of neurocognitive performance in children with perinatal HIV initiating de novo antiretroviral therapy'. Together they form a unique fingerprint.

Cite this