Peer-reviewed article
Development and external validation of a risk calculator to predict internalising symptoms among Ugandan youths affected by HIV
Rachel Brathwaite, Fred M. Ssewamala, Torsten B. Neilands, Proscovia Nabunya, William Byansi et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001Researchers developed and tested a prediction model to identify which Ugandan adolescents orphaned by AIDS or living with HIV are at risk of internalizing symptoms like depression and anxiety. The model uses seven key factors including gender, family relationships, social support, and recent health problems to estimate individual risk. The model performed reasonably well in both the original group and an independent group of adolescents living with HIV, suggesting it could help guide mental health services for youth affected by HIV and AIDS.
Key points
- Best predictors of internalizing symptoms were gender, family cohesion, social support, asset ownership, recent STI diagnosis, physical health self-rating, and previous poor mental health
- The model achieved an area under the curve (AUC) of 72.2 in the development sample and 69.7 in the external validation sample, indicating reasonable predictive performance
- The model showed good calibration and generalizability across different populations of AIDS-affected youth
- For adolescents without previous mental health history, different predictors were most important: gender, drug use, social support, asset ownership, STI diagnosis, and physical health rating
- The model could support design of public health interventions for mental health among youth affected by HIV/AIDS
Limitations
The study does not describe whether the model has been implemented in practice or what impact it has on actual service delivery and youth outcomes. The document provides predictive accuracy measures but does not assess whether using the calculator leads to better mental health outcomes for identified at-risk youth.
Abstract
The aim of the study was to develop and externally validate a model to predict individualized risk of internalizing symptoms among AIDS-affected youths in low-resource settings in sub-Saharan Africa. Longitudinal data from 558 Ugandan adolescents orphaned by AIDS was used to develop our predictive model. Least Absolute Shrinkage and Selection Operator logistic regression was used to select the best subset of predictors using 10-fold cross-validation. External validation of the final model was conducted in a sample of 372 adolescents living with HIV in Uganda. Best predictors for internalizing symptoms were gender, family cohesion, social support, asset ownership, recent sexually transmitted infection (STI) diagnosis, physical health self-rating, and previous poor mental health; area under the curve (AUC) = 72.2; 95% CI = 67.9-76.5. For adolescents without history of internalizing symptoms, the AUC = 69.0, 95% CI = 63.4-74.6, and was best predicted by gender, drug use, social support, asset ownership, recent STI diagnosis, and physical health self-rating. Both models were well calibrated. External validation in adolescents living with HIV sample was similar, AUC = 69.7; 95% CI = 64.1-75.2. The model predicted internalizing symptoms among African AIDS-affected youth reasonably well and showed good generalizability. The model offers opportunities for the design of public health interventions addressing poor mental health among youth affected by HIV/AIDS.