Background Adolescents living with HIV (ALWHIV) face a high prevalence of depression. In Uganda, limited access to mental health services exacerbates depression, necessitating innovative solutions for early detection and intervention. Machine learning (ML) provides a promising approach for identifying adolescents at risk of depression to facilitate early intervention. This study aims to use machine learning to predict depression among ALWHIV in Uganda. Methods This study analyzed cross-sectional data from 833 ALWHIV aged 10-17 years in Southern Uganda. Depression was assessed using the Children's Depression Inventory (CDI) -short version. Seven ML models, including Random Forest, Logistic Regression, Gradient Boosting, decision tree, XGBoost, Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine, were evaluated using stratified 10-fold cross-validation. Model performance metrics included Area under receiver operating characteristic curve (AUROC), Area under precision-recall curve (AUPRC), accuracy, sensitivity, specificity, and F1-score. SHapley Additive exPlanations (SHAP) analysis was used to interpret feature importance. Results The median age was 13 years, and the majority of the participants were females (55.5%). The prevalence of depression was 30.97%. The Random Forest model achieved the highest performance (AUROC = 0.79, AUPRC = 0.66). Key predictors of depression included hopelessness, HIV stigma, shame, self-esteem, teacher support, and caregiver support. SHAP analysis highlighted psychosocial challenges as primary predictors of depression, emphasizing the need for psychosocial-based interventions. Conclusion Our study results demonstrated good performance of ML in predicting depression among ALWHIV. However, we acknowledge that the absence of external validation limits the generalizability of these findings. Future research should seek to validate these models in independent cohorts of ALWHIV to confirm their robustness and applicability across different settings.
In Uganda, children orphaned by HIV are at a high risk of emotional and behavioral difficulties (EBDs). This elevated risk of EBDs has implication on caregivers’ mental health given that caregiving is an involving responsibility that can affect mental, physical health and overall well-being. While the existence of child EBDs and its impact on caregivers’ mental health is well documented in high-income countries, few studies in Sub-Saharan Africa have examined the impact of child emotional and behavioral difficulties on caregiver mental health among families of children orphaned by HIV. This study aims to examine the relationship between child difficulties and caregiver mental health in Southern Uganda. Utilizing baseline data from the Suubi-Maka study (N = 346 dyads), a two-arm cluster-randomized controlled trial, the current study examines the relationship between children’s EBDs and caregiver mental health. Child EBDs were measured using the Child Strengths and Difficulties scale as reported by caregivers. Caregiver mental health was measured by the Brief Symptom Inventory. Mixed effect linear regression model was used to examine the relationship between child difficulties and caregiver mental health. Control variables were caregiver age, gender, household size, family size, social support, family cohesion, family assets, and substance use (alcohol and cigarettes). The mean age of the caregivers was 45.78 years. Results showed a significant positive association between child EBDs and caregiver mental health problems. High levels of child difficulties were associated with poorer caregiver mental health functioning (β = 0.85, 95
One in six people are aged 10-19 years. Adolescence is a unique and formative time. Physical, emotional, and social changes, including exposure to poverty, abuse, or violence, can make adolescents vulnerable to mental health problems. Protecting adolescents from adversity, promoting socio-emotional learning and psychological well-being, and ensuring access to mental healthcare are critical for their health and well-being during adolescence and adulthood. Globally, it is estimated that 1 in 7 (14%) 10-19 year-olds experience mental health conditions (1), yet these remain largely unrecognized and untreated. Adolescents with mental health conditions are particularly vulnerable to social exclusion, discrimination, stigma (affecting readiness to seek help), educational difficulties, risk-taking behaviors, physical ill-health, and human rights violations.
This study examined the association between COVID-19-related experiences and the psychological wellbeing of school-going adolescent girls in Uganda. We utilized cross-sectional data collected from 1165 adolescent girls (14–17 years), participating in a longitudinal randomized clinical trial (2017–2022). Due to social distancing and mitigation measures, data were collected using telephone interviewer-administered surveys. We fitted hierarchical regression models to assess the association between COVID-19-related experiences (such as resource changes and disruptions, and access to medical care), and two aspects of psychological wellbeing (emotional and cognitive wellbeing). Resource changes and disruptions due to the pandemic were negatively associated with adolescents’ emotional (β = − 0.68, 95
