Ensemble Machine learning classification of daily living abilities among older people with HIV (eclinical medicine; May 2021)
Background: Clinically relevant methods to identify individuals at risk for impaired daily living abilities secondary to neurocognitive impairment (ADLs) remain elusive. This is especially true for complex clinical conditions such as HIV-Associated Neurocognitive Disorders (HAND). The aim of this study was to identify novel and modifiable factors that have potential to improve diagnostic accuracy of ADL risk, with the long-term goal of guiding future interventions to minimize ADL disruption. Methods: Study participants included 79 people with HIV (PWH; mean age = 63; range = 55-80) enrolled in neuroHIV studies at University California San Francisco (UCSF) between 2016 and 2019. All participants were virally suppressed and exhibited objective evidence of neurocognitive impairment. ADL status was defined as either normative (n = 39) or at risk (n = 40) based on a task-based protocol. Gradient boosted multivariate regression (GBM) was employed to identify the combination of variables that differentiated ADL subgroup classification. Predictor variables included demographic factors, HIV disease severity indices, brain white matter integrity quantified using diffusion tensor imaging, cognitive test performance, and health co-morbidities. Model performance was examined using average Area Under the Curve (AUC) with repeated five-fold cross validation. Findings: The univariate GBM yielded an average AUC of 83% using Wide Range Achievement test 4 (WRAT-4) reading score, self-reported thought confusion and difficulty reading, radial diffusivity (RD) in the left external capsule, fractional anisotropy (FA) in the left cingulate gyrus, and Stroop performance. The model allowing for two-way interactions modestly improved classification performance (AUC of 88%) and revealed synergies between race, reading ability, cognitive performance, and neuroimaging metrics in the genu and uncinate fasciculus. Conversion of Neuropsychological Assessment Battery Daily Living Module (NAB-DLM) performance from raw scores into T scores amplified differences between White and non-White study participants.
Neurocognitive trajectories after 72 weeks of first-line anti-retroviral therapy in Vietnamese adults with HIV-HCV co-infection (Front Neurology; March 2021)
Background: Long-term neurocognitive outcomes following first-line suppressive anti-retroviral therapy (ART) remain uncertain for individuals with HIV and hepatitis C (HCV) co-infection. The study examined neurocognitive performance before and after 72 weeks of ART using repeated multivariate analyses and latent trajectory models. Methods: One hundred and sixty adults with chronic, untreated HIV infection (n = 80 with HCV co-infection and n = 80 HIV mono-infected) and 80 demographically similar healthy controls were recruited from the Hospital for Tropical Diseases in Ho Chi Minh City and the surrounding community, respectively. Neurocognitive measures (adapted for use in Vietnam) and liver enzyme tests were compared across groups at baseline. Repeated multivariate and group-based trajectory analyses (GBTA) examined neurocognitive subgroup profiles of the co-infected individuals after 72 weeks of de novo efavirenz- (n = 41) or raltegravir-based (n = 39) ART. Results: Baseline analyses revealed worse motor function in HIV-HCV co-infected individuals compared to both comparison groups. Longitudinal analyses revealed improved neurocognitive performance by week 48 for most participants regardless of treatment arm. GBTA identified a subgroup (35% of HIV-HCV sample) with persistent motor impairment despite otherwise successful ART. Higher HIV viral load and lower CD4+ T cell count at baseline predicted persistent motor dysfunction. Liver indices and ART regimen did not predict neurocognitive outcomes in HIV-HCV co-infected individuals. Conclusions: Most HIV-HCV co-infected individuals achieve normative neurocognitive performance after 48 weeks of de novo suppressive ART. However, individuals with more severe HIV disease prior to ART exhibited motor impairment at baseline and 72 weeks after otherwise successful treatment. Interventions aimed at improving motor symptoms at the time of HIV treatment onset may improve long-term clinical outcomes in HIV-HCV co-infected adults.
Behavioral impairment and cognition in Thai adolescents affected by HIV (Global mental health; February 2021)
Background: Cognitive and behavioral impairment are common in children living with perinatally acquired HIV (pHIV) and children exposed to HIV in utero but uninfected (HEU). Methods: We sought to determine the prevalence of adverse behavioral symptomatology using a Thai-translated and validated version of the SNAP-IV questionnaire and assess cognitive function utilizing the Children’s Color Trails Test, Delis-Kaplan Executive Function System, and the Wechsler Intelligence Scales, in our cohort of Thai adolescents (10-20 years old) with well-controlled pHIV compared to HEU and HIV-unexposed, uninfected youth. We then evaluated the interaction between HIV status, behavioral impairment, and executive function outcomes independent of demographic variables. Results: After controlling for demographic factors of age and household income, adolescents with pHIV had higher inattentive symptomatology and poorer neuropsychological test scores compared to uninfected controls. Significant interactions were found between inattention and executive function across multiple neurocognitive tests.
Machine Learning Analysis Reveals Novel Neuroimaging and Clinical Signatures of Frailty in HIV (JAIDS; accepted pending revisions to 2020)
Frailty is now an important clinical concern for people living with HIV (PLWH) but the underlying mechanisms are not known. We utilized ensemble machine learning analysis to identify novel risk variables of frailty, leveraging diverse array of clinical and neuroimaging predictors. Our analyzes successfully distinguished PLWH according to frailty status using an algorithm comprised of lower CD4, psychomotor performance, and neuroimaging indices of visual and motor brain systems. Alterations in brain networks important for visuomotor function distinguished frail from nonfrail PLWH. Further, novel synergies between suboptimal HIV treatment response (lower CD4 count), female sex, and depressive symptoms with neuroimaging features increased the risk of frailty among individuals receiving cART. Studies are needed to determine if adjunctive interventions aimed at bolstering visuomotor skills and reducing mild to moderate depressive symptoms are effective risk modification strategies to improve health resilience as PLWH reach advanced ages.
Machine learning analysis reveals model neuroimaging and clinical signatures of frailty in HIV (Jaids; August 2020)
Frailty is now an important clinical concern for people living with HIV (PLWH) but the underlying mechanisms are not known. We utilized ensemble machine learning analysis to identify novel risk variables of frailty, leveraging diverse array of clinical and neuroimaging predictors. Our analyzes successfully distinguished PLWH according to frailty status using an algorithm comprised of lower CD4, psychomotor performance, and neuroimaging indices of visual and motor brain systems. Alterations in brain networks important for visuomotor function distinguished frail from nonfrail PLWH. Further, novel synergies between suboptimal HIV treatment response (lower CD4 count), female sex, and depressive symptoms with neuroimaging features increased the risk of frailty among individuals receiving cART. Studies are needed to determine if adjunctive interventions aimed at bolstering visuomotor skills and reducing mild to moderate depressive symptoms are effective risk modification strategies to improve health resilience as PLWH reach advanced ages.
Resting-state Neural Signatures of Depressive Symptoms in Acute HIV (Journal of Neurovirology; January 2020)
Depressive symptoms are often elevated in acute and chronic HIV. Previous neuroimaging research identifies abnormalities in emotion-related brain regions in depression without HIV, including the anterior cingulate cortex (ACC) and amygdala. However, no studies have examined the neural signatures of depressive symptoms in acute HIV infection (AHI). Group analyses compared resting-state functional connectivity (rsFC) of ACC and amygdala seed regions between AHI and uninfected control groups. Within the AHI group, voxelwise regression analyses investigated the relationship between depressive symptoms and rsFC for these affective seed regions. We found that depressive symptoms in AHI associate with altered rsFC of ACC and amygdala regions previously implicated in depression. Longitudinal research in this cohort will be necessary to determine whether these early alterations in rsFC of affective network regions are related to persistent depressive symptoms after combination antiretroviral therapy.
A subset of children with perinatal HIV (pHIV) experience long-term neurocognitive difficulties; however, predicting individual neurocognitive outcomes for young children with pHIV is challenging, especially in resource-limited environments where the majority of the global population of pHIV reside. We developed the first predictive model of neurocognitive trajectories in children with pHIV using a machine learning analysis of baseline and longitudinal predictors derived from clinical measures that can be acquired in resource-limited settings. Our findings support the feasibility of machine learning to identify children with pHIV at risk for suboptimal neurocognitive development. Further, results point towards interactions between HIV disease and mental health problems as early antecedents to neurocognitive difficulties in later childhood among individuals with pHIV. These findings have potential to guide the development of intervention strategies, including psychosocial interventions, to maximize neurodevelopmental outcomes in youth exposed to HIV during critical stages of brain development.
Neurocognitive Phenotyping of HIV in the Era of Antiretroviral Therapy (Current HIV/AIDS Reports; June 2019)
The pattern of neurocognitive symptoms associated with HIV has traditionally been referred to as a “subcortical” phenotype. Recent concern has been raised that the neurocognitive phenotype in the post-ART era has changed to reflect the addition of cortical features, suggestive of synergistic age-related neurodegeneration. Empirical evidence reviewed in this paper suggests that, when present, HIV-related neurocognitive impairment in the post-ART era remains subcortical in nature, regardless of advanced age or treatment status. Persistent neurocognitive impairment among virally suppressed individuals may reflect a combination of HIV disease factors, pre-existing risk factors, and/or emergent health comorbidities such as subcortical ischemic vascular disease in older people living with HIV. An entrenchment of the subcortical neurocognitive phenotype of HIV appears to be unfolding in the post-ART era. Whether new neurocognitive subtypes of HIV exist in the current era requires additional research utilizing harmonized test protocols and advanced computational methods capable of deep phenotyping.
Depression and Anxiety are Common in Acute HIV Infection and Associate with Plasma Immune Activation (AIDS and Behavior; November 2017)
This observational study of 123 Thai participants sought to determine the rate and severity of affective symptoms during acute HIV infection (AHI) and possible associations to disease mechanisms. At diagnosis, just prior to starting combination antiretroviral therapy (cART), AHI participants completed assessments of depression and anxiety symptoms that were repeated at 4, 12, and 24 weeks. Blood markers of HIV infection and immune activation were measured at study entry, with optional cerebrospinal fluid measures. A high frequency of participants reported symptoms that exceeded published thresholds supportive of depression and anxiety at diagnosis, with significant reductions after starting cART. Meeting a threshold for clinically relevant depressive symptoms at study entry was associated with higher baseline plasma HIV RNA and higher plasma neopterin, a marker of macrophage. Controlling for plasma HIV RNA and CD4 count, higher baseline plasma neopterin correlated with worse initial depression and anxiety scores. Depression and anxiety symptoms are frequent in acute HIV infection, associate with plasma immune activation, and can improve concurrent with cART.