Machine learning models reveal neurocognitive impairment type and prevalence are associated with distinct variables in HIV/AIDS.

Neurocognitive impairment (NCI) among HIV-infected patients is heterogeneous in its reported presentations and frequencies. To determine the prevalence of NCI and its associated subtypes as well as predictive variables, we investigated patients with HIV/AIDS receiving universal health care. Recruited adult HIV-infected subjects underwent a neuropsychological (NP) test battery with established normative (sex-, age-, and education-matched) values together with assessment of their demographic and clinical variables. Three patient groups were identified including neurocognitively normal (NN, n = 246), HIV-associated neurocognitive disorders (HAND, n = 78), and neurocognitively impaired-other disorders (NCI-OD, n = 46). Univariate, multiple logistic regression and machine learning analyses were applied. Univariate analyses showed variables differed significantly between groups including birth continent, quality of life, substance use, and PHQ-9. Multiple logistic regression models revealed groups again differed significantly for substance use, PHQ-9 score, VACS index, and head injury. Random forest (RF) models disclosed that classification algorithms distinguished HAND from NN and NCI-OD from NN with area under the curve (AUC) values of 0.87 and 0.77, respectively. Relative importance plots derived from the RF model exhibited distinct variable rankings that were predictive of NCI status for both NN versus HAND and NN versus NCI-OD comparisons. Thus, NCI was frequently detected (33.5%) although HAND prevalence (21%) was lower than in several earlier reports underscoring the potential contribution of other factors to NCI. Machine learning models uncovered variables related to individual NCI types that were not identified by univariate or multiple logistic regression analyses, highlighting the value of other approaches to understanding NCI in HIV/AIDS.

Empiric neurocognitive performance profile discovery and interpretation in HIV infection.

The measurement and determinants of HIV-associated neurocognitive disorders (HAND) are under intense debate. We used latent profile analysis (LPA) and machine learning to define neurocognitive performance profiles and identify their associated risk factors in HIV patients receiving antiretroviral therapy (ART). Neurocognitive performance was assessed by a multidomain neuropsychological test battery. LPA was used to define individual neurocognitive profiles. Random forest analyses (RFA) identified the most important factors distinguishing each profile. Three profiles emerged from the LPA: profile 1 (P1, n = 159) achieved the highest performance, while profile 2 (P2, n = 163) had lowered executive functions and verbal memory, and profile 3 (P3, n = 59) was globally impaired. RFA achieved good prediction (area under the curve ≥ 0.80) only for global impairment (P3). Non-North American descent was the dominant predictor of P3, followed by factors coinciding with non-North American descent (female sex and toxoplasma seropositivity). Additional predictors included unemployment, current depressive symptoms, lower nadir CD4, and longstanding HIV. Restricting analyses to North Americans pointed to the additional importance of ART achieving high CSF levels and older age in prediction of P3. HAND diagnoses were most common in the globally impaired profile (P3 = 89.8%), followed by the group with reduced higher-order neurocognitive performance (P2 = 16.6%). Thus, implementation of LPA and RFA empirically distinguished three distinct neurocognitive performance profiles in this HIV-infected cohort while also highlighting potential risk factors and their relative importance to neurocognitive impairment. These data-driven analytical methods pointed to discernible demographic, HIV- and treatment-related risk factor constellations in patients born outside and within North America that might influence diagnostic and therapeutic decisions.

Associations between Depressive Symptomatology and Neurocognitive Impairment in HIV/AIDS.

OBJECTIVE: Mood disorders and neurocognitive impairments are debilitating conditions among patients with HIV/AIDS. How these comorbidities interact and their relationships to systemic factors remain uncertain. Herein, we investigated factors contributing to depressive symptomatology (DS) in a prospective cohort of patients with HIV/AIDS in active care that included neuropsychological assessment. METHODS: Among patients with HIV/AIDS receiving combination antiretroviral therapy (cART) and ongoing clinical assessments including measures of sleep, health-related quality of life (HQoL), neuropsychological testing, and mood evaluation (Patient Health Questionnaire-9 [PHQ-9]) were performed. Univariate and multivariate analyses were applied to the data. RESULTS: In 265 persons, 3 categories of DS were established: minimal (PHQ-9: 0-4; n = 146), mild (PHQ-9: 5-9; n = 62), and moderate to severe (PHQ-9: 10+; n = 57). Low education, unemployment, diabetes, reduced adherence to treatment, HIV-associated neurocognitive disorders (HAND), low health-related quality of life (HQoL), reduced sleep times, and domestic violence were associated with higher PHQ-9 scores. Motor impairment was also associated with more severe DS. In a multinomial logistic regression model, only poor HQoL and shorter sleep duration were predictive of moderate to severe depression. In this multivariate model, the diagnosis of HAND and neuropsychological performance (NPz) were not predictive of DS. CONCLUSIONS: Symptoms of depression are common (45%) in patients with HIV/AIDS and represent a substantial comorbidity associated with multiple risk factors. Our results suggest that past or present immunosuppression and HAND are not linked to DS. In contrast, sleep quality and HQoL are important variables to consider in screening for mood disturbances among patients with HIV/AIDS and distinguishing them from neurocognitive impairments.

Montreal Cognitive Assessment Performance in HIV/AIDS: Impact of Systemic Factors.

BACKGROUND: A large proportion of people living with human immunodeficiency virus/acquired immunodeficiency syndrome (HIV/AIDS) suffer from neurocognitive impairment (NCI). The causes of the NCI are multifold in HIV infection although a subset of HIV/AIDS patients are affected by the spectrum syndrome, HIV-associated neurocognitive disorder (HAND). We investigated the Montreal Cognitive Assessment (MoCA) in relation to clinical, demographic and laboratory findings as well as its ability to predict symptomatic HAND (sHAND) among patients with HIV/AIDS. METHODS: All subjects were receiving regular HIV care including CD4+ T cell counts, plasma viral load measurements, clinical evaluations and antiretroviral therapy. The diagnosis of sHAND was based upon clinical, neuroimaging, and neuropsychological assessments. RESULTS: Among HIV-1 seropositive subjects (n=125), ethnicity, education and employment were positively correlated with their MoCA scores (p<0.05). In contrast, polypharmacy, central nervous system penetration-effectiveness (CPE) score, antiretroviral drug exposure, substance use and nucleoside/nucleotide reverse transcriptase inhibitor side effects were negatively correlated with MoCA scores (p<0.05). Of note, MoCA scores were not associated with CD4 T cell nadir levels, age, peak viral load, or veterans aging cohort study index. In subjects with or without sHAND, mean MoCA scores differed (sHAND, 22.8±3.51; non-HAND 25.2±2.64) (p<0.05) with a receiver operating characteristic curve showing an area under curve of 0.71 and an optimal MoCA cut-off value of 23.5 when compared to the established diagnostic paradigm. CONCLUSIONS: MoCA scores were generally lower in this HIV/AIDS population compared to reported scores in the general population. MoCA performance was associated with multiple clinical variables but displayed limited predictive utility in detecting sHAND.