Additive cortical gray matter deficits in people living with HIV who use cocaine.

Cocaine use, which is disproportionately common in people living with HIV (PWH), is known to have neurotoxic effects that may exacerbate HIV neuropathogenesis. While both cocaine use and HIV disease are independently associated with deficits in gray matter (GM) volume, the additive effect of cocaine use to HIV disease on GM volume has not been explored. Here, we investigated subcortical and cortical brain volume differences between four groups of individuals with and without HIV disease and/or cocaine use. Participants also completed a comprehensive neuropsychological testing battery, and HIV disease characteristics were recorded. Within subcortical regions, cocaine use was independently associated with higher volume in the dorsal striatum and pallidum, while HIV disease was associated with lower volume in the nucleus accumbens and thalamus. For cortical regions, there was an additive effect of cocaine use on HIV disease in parietal and occipital lobe volume with PWH who used cocaine displaying the lowest GM volume. Within regions that differed between groups, higher neurocognitive function was positively associated with thalamic, nucleus accumbens, dorsal striatum, and occipital lobe volume. For regions that showed a significant main effect of HIV disease, lower nadir CD4 + T cell count was associated with lower nucleus accumbens and occipital lobe volume. Lower current CD4 + T cell count was associated with lower occipital lobe volume. These results suggest that PWH who use cocaine are at greater risk for cortical atrophy than cocaine use or HIV disease alone.

Machine learning prediction of neurocognitive impairment among people with HIV using clinical and multimodal magnetic resonance imaging data.

Diagnosis of HIV-associated neurocognitive impairment (NCI) continues to be a clinical challenge. The purpose of this study was to develop a prediction model for NCI among people with HIV using clinical- and magnetic resonance imaging (MRI)-derived features. The sample included 101 adults with chronic HIV disease. NCI was determined using a standardized neuropsychological testing battery comprised of seven domains. MRI features included gray matter volume from high-resolution anatomical scans and white matter integrity from diffusion-weighted imaging. Clinical features included demographics, substance use, and routine laboratory tests. Least Absolute Shrinkage and Selection Operator Logistic regression was used to perform variable selection on MRI features. These features were subsequently used to train a support vector machine (SVM) to predict NCI. Three different classification tasks were performed: one used only clinical features; a second used only selected MRI features; a third used both clinical and selected MRI features. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity with a tenfold cross-validation. The SVM classifier that combined selected MRI with clinical features outperformed the model using clinical features or MRI features alone (AUC: 0.83 vs. 0.62 vs. 0.79; accuracy: 0.80 vs. 0.65 vs. 0.72; sensitivity: 0.86 vs. 0.85 vs. 0.86; specificity: 0.71 vs. 0.37 vs. 0.52). Our results provide preliminary evidence that combining clinical and MRI features can increase accuracy in predicting NCI and could be developed as a potential tool for NCI diagnosis in HIV clinical practice.