Search

Logistic regression (LR) is the most common prediction model in medicine. In recent years, supervised machine learning (ML) methods have gained popularity. However, there are many concerns about ML utility for small sample sizes. In this study, we aim to compare the performance of 7 algorithms in the prediction of 1-year mortality and clinical progression to AIDS in a small cohort of infants living with HIV from South Africa and Mozambique. The data set (n = 100) was randomly split into 70% training and 30% validation set. Seven algorithms (LR, Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Artificial Neural Network (ANN), and Elastic Net) were compared. The variables included as predictors were the same across the models including sociodemographic, virologic, immunologic, and maternal status features. For each of the models, a parameter tuning was performed to select the best-performing hyperparameters using 5 times repeated 10-fold cross-validation. A confusion-matrix was built to assess their accuracy, sensitivity, and specificity. RF ranked as the best algorithm in terms of accuracy (82,8%), sensitivity (78%), and AUC (0,73). Regarding specificity and sensitivity, RF showed better performance than the other algorithms in the external validation and the highest AUC. LR showed lower performance compared with RF, SVM, or KNN. The outcome of children living with perinatally acquired HIV can be predicted with considerable accuracy using ML algorithms. Better models would benefit less specialized staff in limited resources countries to improve prompt referral in case of high-risk clinical progression. [ABSTRACT FROM AUTHOR]

After sporadic reports of post-treatment control of HIV in children who initiated combination anti-retroviral therapy (cART) early, we prospectively studied 284 very-early-cART-treated children from KwaZulu-Natal, South Africa, after vertical HIV transmission to assess control of viremia. Eighty-four percent of the children achieved aviremia on cART, but aviremia persisting to 36 or more months was observed in only 32%. We observed that male infants have lower baseline plasma viral loads (P = 0.01). Unexpectedly, a subset (n = 5) of males maintained aviremia despite unscheduled complete discontinuation of cART lasting 3-10 months (n = 4) or intermittent cART adherence during 17-month loss to follow-up (n = 1). We further observed, in vertically transmitted viruses, a negative correlation between type I interferon (IFN-I) resistance and viral replication capacity (VRC) (P < 0.0001) that was markedly stronger for males than for females (r = -0.51 versus r = -0.07 for IFN-α). Although viruses transmitted to male fetuses were more IFN-I sensitive and of higher VRC than those transmitted to females in the full cohort (P < 0.0001 and P = 0.0003, respectively), the viruses transmitted to the five males maintaining cART-free aviremia had significantly lower replication capacity (P < 0.0001). These data suggest that viremic control can occur in some infants with in utero-acquired HIV infection after early cART initiation and may be associated with innate immune sex differences., (© 2024. The Author(s).)