1
|
O’Connor EE, Sullivan EV, Chang L, Hammoud DA, Wilson TW, Ragin AB, Meade CS, Coughlin J, Ances BM. Imaging of Brain Structural and Functional Effects in People With Human Immunodeficiency Virus. J Infect Dis 2023; 227:S16-S29. [PMID: 36930637 PMCID: PMC10022717 DOI: 10.1093/infdis/jiac387] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/18/2023] Open
Abstract
Before the introduction of antiretroviral therapy, human immunodeficiency virus (HIV) infection was often accompanied by central nervous system (CNS) opportunistic infections and HIV encephalopathy marked by profound structural and functional alterations detectable with neuroimaging. Treatment with antiretroviral therapy nearly eliminated CNS opportunistic infections, while neuropsychiatric impairment and peripheral nerve and organ damage have persisted among virally suppressed people with HIV (PWH), suggesting ongoing brain injury. Neuroimaging research must use methods sensitive for detecting subtle HIV-associated brain structural and functional abnormalities, while allowing for adjustments for potential confounders, such as age, sex, substance use, hepatitis C coinfection, cardiovascular risk, and others. Here, we review existing and emerging neuroimaging tools that demonstrated promise in detecting markers of HIV-associated brain pathology and explore strategies to study the impact of potential confounding factors on these brain measures. We emphasize neuroimaging approaches that may be used in parallel to gather complementary information, allowing efficient detection and interpretation of altered brain structure and function associated with suboptimal clinical outcomes among virally suppressed PWH. We examine the advantages of each imaging modality and systematic approaches in study design and analysis. We also consider advantages of combining experimental and statistical control techniques to improve sensitivity and specificity of biotype identification and explore the costs and benefits of aggregating data from multiple studies to achieve larger sample sizes, enabling use of emerging methods for combining and analyzing large, multifaceted data sets. Many of the topics addressed in this article were discussed at the National Institute of Mental Health meeting "Biotypes of CNS Complications in People Living with HIV," held in October 2021, and are part of ongoing research initiatives to define the role of neuroimaging in emerging alternative approaches to identifying biotypes of CNS complications in PWH. An outcome of these considerations may be the development of a common neuroimaging protocol available for researchers to use in future studies examining neurological changes in the brains of PWH.
Collapse
Affiliation(s)
- Erin E O’Connor
- Department of Diagnostic Radiology & Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Edith V Sullivan
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California, USA
- Center for Health Sciences, SRI International, Menlo Park, California, USA
| | - Linda Chang
- Department of Diagnostic Radiology & Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA
- Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Dima A Hammoud
- Center for Infectious Disease Imaging, Radiology and Imaging Sciences, NIH Clinical Center, Bethesda, Maryland, USA
| | - Tony W Wilson
- Institute for Human Neuroscience, Boys Town National Research Hospital, Boys Town, Nebraska, USA
| | - Ann B Ragin
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, Illinois, USA
| | - Christina S Meade
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, USA
| | - Jennifer Coughlin
- Department of Neurology, Washington University School of Medicine, St Louis, Missouri, USA
| | - Beau M Ances
- Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| |
Collapse
|
2
|
Spies G, Ahmed-Leitao F, Hoddinott G, Seedat S. Effects of unhealthy alcohol use on brain morphometry and neurocognitive function among people with HIV. J Neurovirol 2021; 28:35-45. [PMID: 34882280 DOI: 10.1007/s13365-021-01027-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2021] [Revised: 10/13/2021] [Accepted: 11/02/2021] [Indexed: 10/19/2022]
Abstract
Individual impacts of alcohol misuse and HIV on brain structure and function have been well demonstrated; however, the potential compounded effect of these conditions is seldom considered, despite the high prevalence of alcohol use in HIV infection. We aimed to determine the effects of unhealthy alcohol use on brain morphometry and cognitive function amongst people with HIV (PWH). In 27 (50.9%) HIV-positive users of alcohol and 26 (49.1%) HIV-positive abstainers from alcohol, results revealed significant differences for left and right amygdala (p < 0.01), left and right hippocampus (p = 0.05), left and right posterior cingulate (p < 0.01), left and right precuneus (p < 0.01), left insula (p < 0.01), left and right caudate (p < 0.01), right thalamus (p < 0.01), and corpus callosum (p < 0.05). Mean volume of these regions was significantly smaller in HIV-positive alcohol users compared to HIV-positive abstainers. Homogeneity of slopes ANCOVA revealed significant associations between anterior cingulate cortex, precuneus, amygdala, hippocampus, and insula volumes and cognitive function in the domains of learning and delayed recall, motor function, speed of information processing, executive function, attention/working memory, and language. Among PWH, unhealthy alcohol use is associated with negative effects on brain structure and cognitive function.
Collapse
Affiliation(s)
- Georgina Spies
- DSI/NRF South African Research Chairs Initiative in PTSD, Department of Psychiatry, Faculty of Medicine and Health Sciences, Stellenbosch University, Stellenbosch, South Africa. .,Department of Psychiatry, South African Medical Research Council / Stellenbosch University Genomics of Brain Disorders Research Unit, Stellenbosch University, P.O. Box 241, Cape Town, 8000, South Africa.
| | - Fatima Ahmed-Leitao
- DSI/NRF South African Research Chairs Initiative in PTSD, Department of Psychiatry, Faculty of Medicine and Health Sciences, Stellenbosch University, Stellenbosch, South Africa
| | - Graeme Hoddinott
- Desmond Tutu TB Centre, Department of Paediatrics and Child Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Stellenbosch, South Africa
| | - Soraya Seedat
- DSI/NRF South African Research Chairs Initiative in PTSD, Department of Psychiatry, Faculty of Medicine and Health Sciences, Stellenbosch University, Stellenbosch, South Africa.,Department of Psychiatry, South African Medical Research Council / Stellenbosch University Genomics of Brain Disorders Research Unit, Stellenbosch University, P.O. Box 241, Cape Town, 8000, South Africa
| |
Collapse
|
3
|
Regional brain volumetric changes despite 2 years of treatment initiated during acute HIV infection. AIDS 2020; 34:415-426. [PMID: 31725432 DOI: 10.1097/qad.0000000000002436] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
Abstract
OBJECTIVE To assess changes in regional brain volumes after 24 months among individuals who initiated combination antiretroviral therapy (cART) within weeks of HIV exposure. DESIGN Prospective cohort study of Thai participants in the earliest stages of HIV-1infection. METHODS Thirty-four acutely HIV-infected individuals (AHI; Fiebig I-V) underwent brain magnetic resonance (MR) imaging and MR spectroscopy at 1.5 T and immediately initiated cART. Imaging was repeated at 24 months. Regional brain volumes were quantified using FreeSurfer's longitudinal pipeline. Voxel-wise analyses using tensor-based morphometry (TBM) were conducted to verify regional assessments. Baseline brain metabolite levels, blood and cerebrospinal fluid biomarkers assessed by ELISA, and peripheral blood monocyte phenotypes measured by flow cytometry were examined as predictors of significant volumetric change. RESULTS Participants were 31 ± 8 years old. The estimated mean duration of infection at cART initiation was 15 days. Longitudinal analyses revealed reductions in volumes of putamen (P < 0.001) and caudate (P = 0.006). TBM confirmed significant atrophy in the putamen and caudate, and also in thalamic and hippocampal regions. In exploratory post-hoc analyses, higher baseline frequency of P-selectin glycoprotein ligand-1 (PSGL-1)-expressing total monocytes correlated with greater caudate volumetric decrease (ρ = 0.67, P = 0.017), whereas the baseline density of PSGL-1-expressing inflammatory (CD14CD16) monocytes correlated with putamen atrophy (ρ = 0.65, P = 0.022). CONCLUSION Suppressive cART initiated during AHI may not prevent brain atrophy. Volumetric decrease appears greater than expected age-related decline, although examination of longitudinal change in demographically similar HIV-uninfected Thai individuals is needed. Mechanisms underlying progressive HIV-related atrophy may include early activation and enhanced adhesive and migratory capacity of circulating monocyte populations.
Collapse
|
4
|
Meade CS, Bell RP, Towe SL, Chen N, Hobkirk AL, Huettel SA. Synergistic effects of marijuana abuse and HIV infection on neural activation during a cognitive interference task. Addict Biol 2019; 24:1235-1244. [PMID: 30239074 DOI: 10.1111/adb.12678] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2018] [Revised: 08/06/2018] [Accepted: 08/11/2018] [Indexed: 01/28/2023]
Abstract
Marijuana use, which is disproportionately prevalent among human immunodeficiency virus (HIV)-infected persons, can alter activity in fronto-parietal regions during cognitively demanding tasks. While HIV is also associated with altered neural activation, it is not known how marijuana may further affect brain function in this population. Our study examined the independent and additive effects of HIV infection and regular marijuana use on neural activation during a cognitive interference task. The sample included 93 adults who differed on marijuana (MJ) and HIV statuses (20 MJ+/HIV+, 19 MJ+/HIV-, 29 MJ-/HIV+, 25 MJ-/HIV-). Participants completed a counting Stroop task during a functional magnetic resonance imaging scan. Main and interactive effects on neural activation during interference versus neutral blocks were examined using a mixed-effects analysis. The sample showed the expected Stroop effect for both speed and accuracy. There were main effects of MJ in the right and left inferior parietal lobules, with the left cluster extending into the posterior middle temporal gyrus and a main effect of HIV in the dorsal anterior cingulate cortex. There was an interaction in the left fronto-insular cortex, such that the MJ+/HIV+ group had the largest increase in activation compared with other groups. Among MJ+, signal change in this cluster correlated positively with cumulative years of regular marijuana use. These results suggest that comorbid HIV and marijuana use is associated with complex neural alterations in multiple brain regions during cognitive interference. Follow-up research is needed to determine how marijuana-related characteristics may moderate HIV neurologic disease and impact real-world functioning.
Collapse
Affiliation(s)
- Christina S. Meade
- Department of Psychiatry and Behavioral SciencesDuke University School of Medicine Durham North Carolina USA
- Department of Psychology & NeuroscienceDuke University Durham North Carolina USA
- Brain Imaging and Analysis CenterDuke University Medical Center Durham North Carolina USA
| | - Ryan P. Bell
- Department of Psychiatry and Behavioral SciencesDuke University School of Medicine Durham North Carolina USA
| | - Sheri L. Towe
- Department of Psychiatry and Behavioral SciencesDuke University School of Medicine Durham North Carolina USA
| | - Nan‐kuei Chen
- Brain Imaging and Analysis CenterDuke University Medical Center Durham North Carolina USA
- Department of RadiologyDuke University School of Medicine Durham North Carolina USA
| | - Andrea L. Hobkirk
- Department of Psychiatry and Behavioral SciencesDuke University School of Medicine Durham North Carolina USA
| | - Scott A. Huettel
- Department of Psychology & NeuroscienceDuke University Durham North Carolina USA
- Brain Imaging and Analysis CenterDuke University Medical Center Durham North Carolina USA
- Center for Cognitive NeuroscienceDuke University Durham North Carolina USA
| |
Collapse
|
5
|
Adeli E, Zahr NM, Pfefferbaum A, Sullivan EV, Pohl KM. Novel Machine Learning Identifies Brain Patterns Distinguishing Diagnostic Membership of Human Immunodeficiency Virus, Alcoholism, and Their Comorbidity of Individuals. BIOLOGICAL PSYCHIATRY: COGNITIVE NEUROSCIENCE AND NEUROIMAGING 2019; 4:589-599. [PMID: 30982583 DOI: 10.1016/j.bpsc.2019.02.003] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/05/2018] [Revised: 02/15/2019] [Accepted: 02/15/2019] [Indexed: 12/13/2022]
Abstract
The incidence of alcohol use disorder (AUD) in human immunodeficiency virus (HIV) infection is twice that of the rest of the population. This study documents complex radiologically identified, neuroanatomical effects of AUD+HIV comorbidity by identifying structural brain systems that predicted diagnosis on an individual basis. Applying novel machine learning analysis to 549 participants (199 control subjects, 222 with AUD, 68 with HIV, 60 with AUD+HIV), 298 magnetic resonance imaging brain measurements were automatically reduced to small subsets per group. Significance of each diagnostic pattern was inferred from its accuracy in predicting diagnosis and performance on six cognitive measures. While all three diagnostic patterns predicted the learning and memory score, the AUD+HIV pattern was the largest and had the highest predication accuracy (78.1%). Providing a roadmap for analyzing large, multimodal datasets, the machine learning analysis revealed imaging phenotypes that predicted diagnostic membership of magnetic resonance imaging scans of individuals with AUD, HIV, and their comorbidity.
Collapse
Affiliation(s)
- Ehsan Adeli
- Department of Psychiatry and Behavioral Sciences, Stanford School of Medicine, Stanford, California
| | - Natalie M Zahr
- Department of Psychiatry and Behavioral Sciences, Stanford School of Medicine, Stanford, California; Center for Biomedical Sciences, SRI International, Menlo Park, California
| | - Adolf Pfefferbaum
- Department of Psychiatry and Behavioral Sciences, Stanford School of Medicine, Stanford, California; Center for Biomedical Sciences, SRI International, Menlo Park, California
| | - Edith V Sullivan
- Department of Psychiatry and Behavioral Sciences, Stanford School of Medicine, Stanford, California
| | - Kilian M Pohl
- Department of Psychiatry and Behavioral Sciences, Stanford School of Medicine, Stanford, California; Center for Biomedical Sciences, SRI International, Menlo Park, California.
| |
Collapse
|
6
|
Samboju V, Philippi CL, Chan P, Cobigo Y, Fletcher JLK, Robb M, Hellmuth J, Benjapornpong K, Dumrongpisutikul N, Pothisri M, Paul R, Ananworanich J, Spudich S, Valcour V. Structural and functional brain imaging in acute HIV. NEUROIMAGE-CLINICAL 2018; 20:327-335. [PMID: 30101063 PMCID: PMC6082997 DOI: 10.1016/j.nicl.2018.07.024] [Citation(s) in RCA: 31] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/21/2018] [Revised: 06/30/2018] [Accepted: 07/25/2018] [Indexed: 01/03/2023]
Abstract
Background HIV RNA is identified in cerebrospinal fluid (CSF) within eight days of estimated viral exposure. Neurological findings and impaired neuropsychological testing performance are documented in a subset of individuals with acute HIV infection (AHI). The purpose of this study was to determine whether microstructural white matter and resting-state functional connectivity (rsFC) are disrupted in AHI. Methods We examined 49 AHI (100% male; mean age = 30 ± SD 9.9) and 23 HIV-uninfected Thai participants (78% male; age = 30 ± 5.5) with diffusion tensor imaging (DTI) and rsFC acquired at 3 Tesla, and four neuropsychological tests (summarized as NPZ-4). MRI for the AHI group was performed prior to combination antiretroviral treatment (ART) in 26 participants and on average two days (range:1–5) after ART in 23 participants. Fractional anisotropy (FA), mean (MD), axial (AD), and radial diffusivity (RD) were quantified for DTI. Seed-based voxelwise rsFC analyses were completed for the default mode (DMN), fronto-parietal, and salience and 6 subcortical networks. rsFC and DTI analyses were corrected for family-wise error, with voxelwise comparisons completed using t-tests. Group-specific voxelwise regressions were conducted to examine relationships between imaging indices, HIV disease variables, and treatment status. Results The AHI group had a mean (SD) CD4 count of 421(234) cells/mm3 plasma HIV RNA of 6.07(1.1) log10 copies/mL and estimated duration of infection of 20(5.5) days. Differences between AHI and CO groups did not meet statistical significance for DTI metrics. Within the AHI group, voxelwise analyses revealed associations between brief exposure to ART and higher FA and lower RD and MD bilaterally in the corpus callosum, corona radiata, and superior longitudinal fasciculus (p < 0.05). Diffusion indices were unrelated to clinical variables or NPZ-4. The AHI group had reduced rsFC between left parahippocampal cortex (PHC) of the DMN and left middle frontal gyrus compared to CO (p < 0.002). Within AHI, ART status was unrelated to rsFC. However, higher CD4 cell count associated with increased rsFC for the right lateral parietal and PHC seeds in the DMN. Direct associations were noted between NPZ-4 correspond to higher rsFC of the bilateral caudate seed (p < 0.002). Conclusions Study findings reveal minimal disruption to structural and functional brain integrity in the earliest stages of HIV. Longitudinal studies are needed to determine if treatment with ART initiated in AHI is sufficient to prevent the evolution of brain dysfunction identified in chronically infected individuals. DTI indicates no significant differences between acute HIV and uninfected controls. rsfMRI reflects limited reduced rsFC in acute HIV compared to uninfected controls. Relatively preserved brain integrity identified in acute HIV vs uninfected controls. Cognitive testing and CD4 lymphocyte counts associate with rsFC activity in acute HIV.
Collapse
Affiliation(s)
- Vishal Samboju
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Carissa L Philippi
- University of Missouri St. Louis, Department of Psychological Sciences, St. Louis, MO, USA
| | - Phillip Chan
- SEARCH, Thai Red Cross AIDS Research Centre, Bangkok, Thailand
| | - Yann Cobigo
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | | | - Merlin Robb
- U.S. Military HIV Research Program, Walter Reed Army Institute of Research, Silver Spring, MD, USA; Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD, USA
| | - Joanna Hellmuth
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | | | | | - Mantana Pothisri
- Department of Radiology, Chulalongkorn University Medical Center, Bangkok, Thailand
| | - Robert Paul
- University of Missouri St. Louis, Department of Psychological Sciences, St. Louis, MO, USA
| | - Jintanat Ananworanich
- SEARCH, Thai Red Cross AIDS Research Centre, Bangkok, Thailand; U.S. Military HIV Research Program, Walter Reed Army Institute of Research, Silver Spring, MD, USA; Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD, USA; Department of Global Health, The University of Amsterdam, Amsterdam, The Netherlands
| | - Serena Spudich
- Department of Neurology, Yale University, New Haven, CT, USA
| | - Victor Valcour
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA.
| | | | | |
Collapse
|
7
|
Rahimian P, He JJ. HIV/neuroAIDS biomarkers. Prog Neurobiol 2017; 157:117-132. [PMID: 27084354 PMCID: PMC5705228 DOI: 10.1016/j.pneurobio.2016.04.003] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2015] [Revised: 04/01/2016] [Accepted: 04/08/2016] [Indexed: 12/12/2022]
Abstract
HIV infection often causes neurological symptoms including cognitive and motor dysfunction, which have been collectively termed HIV/neuroAIDS. Neuropsychological assessment and clinical symptoms have been the primary diagnostic criteria for HIV/neuroAIDS, even for the mild cognitive and motor disorder, the most prevalent form of HIV/neuroAIDS in the era of combination antiretroviral therapy. Those performance-based assessments and symptoms are generally descriptive and do not have the sensitivity and specificity to monitor the diagnosis, progression, and treatment response of the disease when compared to objective and quantitative laboratory-based biological markers, or biomarkers. In addition, effects of demographics and comorbidities such as substance abuse, psychiatric disease, nutritional deficiencies, and co-infection on HIV/neuroAIDS could be more readily determined using biomarkers than using neuropsychological assessment and clinical symptoms. Thus, there have been great efforts in identification of HIV/neuroAIDS biomarkers over the past two decades. The need for reliable biomarkers of HIV/neuroAIDS is expected to increase as the HIV-infected population ages and their vulnerability to neurodegenerative diseases, particularly Alzheimer's disease increases. Currently, three classes of HIV/neuroAIDS biomarkers are being pursued to establish objective laboratory-based definitions of HIV-associated neurologic injury: cerebrospinal fluid biomarkers, blood biomarkers, and neuroimaging biomarkers. In this review, we will focus on the current knowledge in the field of HIV/neuroAIDS biomarker discovery.
Collapse
Affiliation(s)
- Pejman Rahimian
- Department of Cell Biology and Immunology, Graduate School of Biomedical Sciences, University of North Texas Health Science Center, Fort Worth, TX 76107, United States
| | - Johnny J He
- Department of Cell Biology and Immunology, Graduate School of Biomedical Sciences, University of North Texas Health Science Center, Fort Worth, TX 76107, United States.
| |
Collapse
|
8
|
Prakash A, Hou J, Liu L, Gao Y, Kettering C, Ragin AB. Cognitive function in early HIV infection. J Neurovirol 2016; 23:273-282. [PMID: 27896574 DOI: 10.1007/s13365-016-0498-4] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2016] [Revised: 10/25/2016] [Accepted: 11/01/2016] [Indexed: 12/11/2022]
Abstract
This study aimed to examine cognitive function in acute/early HIV infection over the subsequent 2 years. Fifty-six HIV+ subjects and 21 seronegative participants of the Chicago Early HIV Infection Study were evaluated using a comprehensive neuropsychological assessment at study enrollment and at 2-year follow-up. Cognitive performance measures were compared in the groups using t tests and mixed-effect models. Patterns of relationship with clinical measures were determined between cognitive function and clinical status markers using Spearman's correlations. At the initial timepoint, the HIV group demonstrated significantly weaker performance on measures of verbal memory, visual memory, psychomotor speed, motor speed, and executive function. A similar pattern was found when cognitive function was examined at follow-up and across both timepoints. The HIV subjects had generally weaker performance on psychomotor speed, executive function, motor speed, visual memory, and verbal memory. The rate of decline in cognitive function across the 2-year follow-up period did not differ between groups. Correlations between clinical status markers and cognitive function at both timepoints showed weaker performance associated with increased disease burden. Neurocognitive difficulty in chronic HIV infection may have very early onset and reflect consequences of initial brain viral invasion and neuroinflammation during the intense, uncontrolled viremia of acute HIV infection. Further characterization of the changes occurring in initial stages of infection and the risk and protective factors for cognitive function could inform new strategies for neuroprotection.
Collapse
Affiliation(s)
- Aanchal Prakash
- Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
| | - Jue Hou
- San Diego Department of Statistics, University of California, La Jolla, CA, USA
| | - Lei Liu
- Department of Preventive Medicine-Biostatistics, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
| | - Yi Gao
- Department of Statistics, Northwestern University, Evanston, IL, USA
| | - Casey Kettering
- Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N Michigan Ave, Suite 1600, Chicago, IL, 60611, USA
| | - Ann B Ragin
- Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N Michigan Ave, Suite 1600, Chicago, IL, 60611, USA.
| |
Collapse
|
9
|
Cao B, Kong X, Zhang J, Yu PS, Ragin AB. Identifying HIV-induced subgraph patterns in brain networks with side information. Brain Inform 2015; 2:211-223. [PMID: 27747563 PMCID: PMC4737668 DOI: 10.1007/s40708-015-0023-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2015] [Accepted: 11/02/2015] [Indexed: 12/04/2022] Open
Abstract
Investigating brain connectivity networks for neurological disorder identification has attracted great interest in recent years, most of which focus on the graph representation alone. However, in addition to brain networks derived from the neuroimaging data, hundreds of clinical, immunologic, serologic, and cognitive measures may also be documented for each subject. These measures compose multiple side views encoding a tremendous amount of supplemental information for diagnostic purposes, yet are often ignored. In this paper, we study the problem of subgraph selection from brain networks with side information guidance and propose a novel solution to find an optimal set of subgraph patterns for graph classification by exploring a plurality of side views. We derive a feature evaluation criterion, named gSide, to estimate the usefulness of subgraph patterns based upon side views. Then we develop a branch-and-bound algorithm, called gMSV, to efficiently search for optimal subgraph patterns by integrating the subgraph mining process and the procedure of discriminative feature selection. Empirical studies on graph classification tasks for neurological disorders using brain networks demonstrate that subgraph patterns selected by the multi-side-view-guided subgraph selection approach can effectively boost graph classification performances and are relevant to disease diagnosis.
Collapse
Affiliation(s)
- Bokai Cao
- Department of Computer Science, University of Illinois at Chicago, Chicago, IL USA
| | - Xiangnan Kong
- Department of Computer Science, Worcester Polytechnic Institute, Worcester, MA USA
| | - Jingyuan Zhang
- Department of Computer Science, University of Illinois at Chicago, Chicago, IL USA
| | - Philip S. Yu
- Department of Computer Science, University of Illinois at Chicago, Chicago, IL USA
- Institute for Data Science, Tsinghua University, Beijing, China
| | - Ann B. Ragin
- Department of Radiology, Northwestern University, Chicago, IL USA
| |
Collapse
|
10
|
Cao B, Kong X, Yu PS. A review of heterogeneous data mining for brain disorder identification. Brain Inform 2015; 2:253-264. [PMID: 27747561 PMCID: PMC4883173 DOI: 10.1007/s40708-015-0021-3] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2015] [Accepted: 09/18/2015] [Indexed: 01/22/2023] Open
Abstract
With rapid advances in neuroimaging techniques, the research on brain disorder identification has become an emerging area in the data mining community. Brain disorder data poses many unique challenges for data mining research. For example, the raw data generated by neuroimaging experiments is in tensor representations, with typical characteristics of high dimensionality, structural complexity, and nonlinear separability. Furthermore, brain connectivity networks can be constructed from the tensor data, embedding subtle interactions between brain regions. Other clinical measures are usually available reflecting the disease status from different perspectives. It is expected that integrating complementary information in the tensor data and the brain network data, and incorporating other clinical parameters will be potentially transformative for investigating disease mechanisms and for informing therapeutic interventions. Many research efforts have been devoted to this area. They have achieved great success in various applications, such as tensor-based modeling, subgraph pattern mining, and multi-view feature analysis. In this paper, we review some recent data mining methods that are used for analyzing brain disorders.
Collapse
Affiliation(s)
- Bokai Cao
- Department of Computer Science, University of Illinois at Chicago, Chicago, IL, 60607, USA.
| | - Xiangnan Kong
- Department of Computer Science, Worcester Polytechnic Institute, Worcester, MA, 01609, USA
| | - Philip S Yu
- Department of Computer Science, University of Illinois at Chicago, Chicago, IL, 60607, USA.,Institute for Data Science, Tsinghua University, Beijing, China
| |
Collapse
|