Deep Learning Analysis of Cerebral Blood Flow to Identify Cognitive Impairment and Frailty in Persons Living With HIV

Machine Learning Approaches to Understand Cognitive Phenotypes in People With HIV

Cognitive disorders are prevalent in people with HIV (PWH) despite antiretroviral therapy. Given the heterogeneity of cognitive disorders in PWH in the current era and evidence that these disorders have different etiologies and risk factors, scientific rationale is growing for using data-driven models to identify biologically defined subtypes (biotypes) of these disorders. Here, we discuss the state of science using machine learning to understand cognitive phenotypes in PWH and their associated comorbidities, biological mechanisms, and risk factors. We also discuss methods, example applications, challenges, and what will be required from the field to successfully incorporate machine learning in research on cognitive disorders in PWH. These topics were discussed at the National Institute of Mental Health meeting on "Biotypes of CNS Complications in People Living with HIV" held in October 2021. These ongoing research initiatives seek to explain the heterogeneity of cognitive phenotypes in PWH and their associated biological mechanisms to facilitate clinical management and tailored interventions.

The Structural and Functional Correlates of Frailty in Persons With Human Immunodeficiency Virus

BACKGROUND

Persons with HIV (PWH) are at increased risk of frailty, a clinically recognizable state of increased vulnerability resulting from aging-associated decline in multiple physiologic systems. Frailty is often defined by the Fried criteria, which includes subjective and objective standards concerning health resiliency. However, these frailty metrics do not incorporate cognitive performance or neuroimaging measures.

METHODS

We compared structural (diffusion tensor imaging [DTI]) and functional (cerebral blood flow [CBF]) neuroimaging markers in PWH with frailty and cognitive performance. Virologically controlled PWH were dichotomized as either frail (≥3) or nonfrail (<3) using the Fried criteria. Cognitive Z-scores, both domain (executive, psychomotor speed, language, and memory) and global, were derived from a battery of tests. We identified three regions of reduced CBF, based on a voxel-wise comparison of frail PWH compared with nonfrail PWH. These clusters (bilateral frontal and posterior cingulate) were subsequently used as seed regions of interest (ROIs) for DTI probabilistic white matter tractography.

RESULTS

White matter integrity connecting the ROIs was significantly decreased in frail compared with nonfrail PWH. No differences in cognition were observed between frail and nonfrail PWH. However, reductions in white matter integrity among these ROIs was significantly associated with worse psychomotor speed and executive function across the entire cohort.

CONCLUSIONS

We conclude that frailty in PWH can lead to structural and functional brain changes, including subtle changes that are not detectable by standard neuropsychological tests. Multimodal neuroimaging in conjunction with frailty assessment could identify pathological brain changes observed in PWH.

Co-Infection and Cancer: Host–Pathogen Interaction between Dendritic Cells and HIV-1, HTLV-1, and Other Oncogenic Viruses

Dendritic cells (DCs) function as a link between innate and adaptive immune responses. Retroviruses HIV-1 and HTLV-1 modulate DCs to their advantage and utilize them to propagate infection. Coinfection of HTLV-1 and HIV-1 has implications for cancer malignancies. Both viruses initially infect DCs and propagate the infection to CD4+ T cells through cell-to-cell transmission using mechanisms including the formation of virologic synapses, viral biofilms, and conduits. These retroviruses are both neurotrophic with neurovirulence determinants. The neuropathogenesis of HIV-1 and HTLV-1 results in neurodegenerative diseases such as HIV-associated neurocognitive disorders (HAND) and HTLV-1-associated myelopathy/tropical spastic paraparesis (HAM/TSP). Infected DCs are known to traffic to the brain (CNS) and periphery (PNS, lymphatics) to induce neurodegeneration in HAND and HAM/TSP patients. Elevated levels of neuroinflammation have been correlated with cognitive decline and impairment of motor control performance. Current vaccinations and therapeutics for HIV-1 and HTLV-1 are assessed and can be applied to patients with HIV-1-associated cancers and adult T cell leukemia/lymphoma (ATL). These diseases caused by co-infections can result in both neurodegeneration and cancer. There are associations with cancer malignancies and HIV-1 and HTLV-1 as well as other human oncogenic viruses (EBV, HBV, HCV, HDV, and HPV). This review contains current knowledge on DC sensing of HIV-1 and HTLV-1 including DC-SIGN, Tat, Tax, and current viral therapies. An overview of DC interaction with oncogenic viruses including EBV, Hepatitis viruses, and HPV is also provided. Vaccines and therapeutics targeting host–pathogen interactions can provide a solution to co-infections, neurodegeneration, and cancer.

Effects of Framingham 10-Year Cardiovascular Risk Score and Viral Load on Brain Integrity in Persons With HIV

BACKGROUND

Combination antiretroviral therapy (cART) has allowed for viral load (VL) suppression and increased life expectancy for persons with HIV (PWH). Altered brain integrity, measured by neuropsychological (NP) performance and neuroimaging, is still prevalent among virally suppressed PWH. Age-related conditions such as cardiovascular disease may also affect brain integrity. This study investigated the effects of cardiovascular risk, VL, and HIV serostatus on cerebral blood flow (CBF), brain volumetrics, and cognitive function in PWH and persons without HIV (PWoH).

METHODS

Ten-year cardiovascular risk, using the Framingham Heart Study criteria, was calculated in PWH (n = 164) on cART with undetectable (≤20 copies/mL; n = 134) or detectable (>20 copies/mL; n = 30) VL and PWoH (n = 66). The effects of cardiovascular risk on brain integrity (CBF, volume, and cognition) were compared for PWH (undetectable and detectable VL) and PWoH.

RESULTS

PWH had smaller brain volumes and worse NP scores than PWoH. PWH with detectable and undetectable VL had similar brain integrity measures. Higher cardiovascular risk was associated with smaller volumes and lower CBF in multiple brain regions for PWH and PWoH. Significant interactions between HIV serostatus and cardiovascular risk on brain volumes were observed in frontal, orbitofrontal, and motor regions. Cardiovascular risk was not associated with cognition for PWH or PWoH.

CONCLUSIONS

Neuroimaging, but not cognitive measures, was associated with elevated cardiovascular risk. HIV serostatus was associated with diminished brain volumes and worse cognition while CBF remained unchanged, reflecting potential protective effects of cART. Neuroimaging measures of structure (volume) and function (CBF) may identify contributions of comorbidities, but future longitudinal studies are needed.

Modeling the Effects of HIV and Aging on Resting-State Networks Using Machine Learning

BACKGROUND

The relationship between HIV infection, the functional organization of the brain, cognitive impairment, and aging remains poorly understood. Understanding disease progression over the life span is vital for the care of people living with HIV (PLWH).

SETTING

Virologically suppressed PLWH (n = 297) on combination antiretroviral therapy and 1509 HIV-uninfected healthy controls were evaluated. PLWH were further classified as cognitively normal (CN) or cognitively impaired (CI) based on neuropsychological testing.

METHODS

Feature selection identified resting-state networks (RSNs) that predicted HIV status and cognitive status within specific age bins (younger than 35 years, 35-55 years, and older than 55 years). Deep learning models generated voxelwise maps of RSNs to identify regional differences.

RESULTS

Salience (SAL) and parietal memory networks (PMNs) differentiated individuals by HIV status. When comparing controls with PLWH CN, the PMN and SAL had the strongest predictive strength across all ages. When comparing controls with PLWH CI, the SAL, PMN, and frontal parietal network (FPN) were the best predictors. When comparing PLWH CN with PLWH CI, the SAL, FPN, basal ganglia, and ventral attention were the strongest predictors. Only minor variability in predictive strength was observed with aging. Anatomically, differences in RSN topology occurred primarily in the dorsal and rostral lateral prefrontal cortex, cingulate, and caudate.

CONCLUSION

Machine learning identified RSNs that classified individuals by HIV status and cognitive status. The PMN and SAL were sensitive for discriminating HIV status, with involvement of FPN occurring with cognitive impairment. Minor differences in RSN predictive strength were observed by age. These results suggest that specific RSNs are affected by HIV, aging, and HIV-associated cognitive impairment.

Neuroimaging the Neuropathogenesis of HIV

PURPOSE OF REVIEW

This review highlights neuroimaging studies of HIV conducted over the last 2 years and discusses how relevant findings further our knowledge of the neuropathology of HIV. Three major avenues of neuroimaging research are covered with a particular emphasis on inflammation, aging, and substance use in persons living with HIV (PLWH).

RECENT FINDINGS

Neuroimaging has been a critical tool for understanding the neuropathological underpinnings observed in HIV. Recent studies comparing levels of neuroinflammation in PLWH and HIV-negative controls show inconsistent results but report an association between elevated neuroinflammation and poorer cognition in PLWH. Other recent neuroimaging studies suggest that older PLWH are at increased risk for brain and cognitive compromise compared to their younger counterparts. Finally, recent findings also suggest that the effects of HIV may be exacerbated by alcohol and drug abuse. These neuroimaging studies provide insight into the structural, functional, and molecular changes occurring in the brain due to HIV. HIV triggers a strong neuroimmune response and may lead to a cascade of events including increased chronic inflammation and cognitive decline. These outcomes are further exacerbated by age and age-related comorbidities, as well as lifestyle factors such as drug use/abuse.

Machine Learning Analysis Reveals Novel Neuroimaging and Clinical Signatures of Frailty in HIV

BACKGROUND

Frailty is an important clinical concern for the aging population of people living with HIV (PLWH). The objective of this study was to identify the combination of risk features that distinguish frail from nonfrail individuals.

SETTING

Machine learning analysis of highly dimensional risk features was performed on a clinical cohort of PLWH.

METHODS

Participants included 105 older (average age = 55.6) PLWH, with at least a 3-month history of combination antiretroviral therapy (median CD4 = 546). Predictors included demographics, HIV clinical markers, comorbid health conditions, cognition, and neuroimaging (ie, volumetrics, resting-state functional connectivity, and cerebral blood flow). Gradient-boosted multivariate regressions were implemented to establish linear and interactive classification models. Model performance was determined by sensitivity/specificity (F1 score) with 5-fold cross validation.

RESULTS

The linear gradient-boosted multivariate regression classifier included lower current CD4 count, lower psychomotor performance, and multiple neuroimaging indices (volumes, network connectivity, and blood flow) in visual and motor brain systems (F1 score = 71%; precision = 84%; and sensitivity = 66%). The interactive model identified novel synergies between neuroimaging features, female sex, symptoms of depression, and current CD4 count.

CONCLUSIONS

Data-driven algorithms built from highly dimensional clinical and brain imaging features implicate disruption to the visuomotor system in older PLWH designated as frail individuals. Interactions between lower CD4 count, female sex, depressive symptoms, and neuroimaging features suggest potentiation of risk mechanisms. Longitudinal data-driven studies are needed to guide clinical strategies capable of preventing the development of frailty as PLWH reach advanced age.