1
|
Dong A, Li Z, Wang M, Shen D, Liu M. High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis. Front Neurosci 2021; 15:634124. [PMID: 33776639 PMCID: PMC7994898 DOI: 10.3389/fnins.2021.634124] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2020] [Accepted: 01/25/2021] [Indexed: 11/15/2022] Open
Abstract
Multimodal heterogeneous data, such as structural magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF), are effective in improving the performance of automated dementia diagnosis by providing complementary information on degenerated brain disorders, such as Alzheimer's prodromal stage, i.e., mild cognitive impairment. Effectively integrating multimodal data has remained a challenging problem, especially when these heterogeneous data are incomplete due to poor data quality and patient dropout. Besides, multimodal data usually contain noise information caused by different scanners or imaging protocols. The existing methods usually fail to well handle these heterogeneous and noisy multimodal data for automated brain dementia diagnosis. To this end, we propose a high-order Laplacian regularized low-rank representation method for dementia diagnosis using block-wise missing multimodal data. The proposed method was evaluated on 805 subjects (with incomplete MRI, PET, and CSF data) from the real Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Experimental results suggest the effectiveness of our method in three tasks of brain disease classification, compared with the state-of-the-art methods.
Collapse
Affiliation(s)
- Aimei Dong
- School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Science), Jinan, China
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States
| | - Zhigang Li
- School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Science), Jinan, China
| | - Mingliang Wang
- College of Computer Science and Technology, Nanjing University of Aeronautics & Astronautics, Nanjing, China
| | - Dinggang Shen
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
- Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
- Department of Artificial Intelligence, Korea University, Seoul, South Korea
| | - Mingxia Liu
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States
| |
Collapse
|
2
|
McKeown A, Turner A, Angehrn Z, Gove D, Ly A, Nordon C, Nelson M, Tochel C, Mittelstadt B, Keenan A, Smith M, Singh I. Health Outcome Prioritization in Alzheimer's Disease: Understanding the Ethical Landscape. J Alzheimers Dis 2020; 77:339-353. [PMID: 32716354 PMCID: PMC7592677 DOI: 10.3233/jad-191300] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/08/2020] [Indexed: 11/28/2022]
Abstract
BACKGROUND Dementia has been described as the greatest global health challenge in the 21st Century on account of longevity gains increasing its incidence, escalating health and social care pressures. These pressures highlight ethical, social, and political challenges about healthcare resource allocation, what health improvements matter to patients, and how they are measured. This study highlights the complexity of the ethical landscape, relating particularly to the balances that need to be struck when allocating resources; when measuring and prioritizing outcomes; and when individual preferences are sought. OBJECTIVE Health outcome prioritization is the ranking in order of desirability or importance of a set of disease-related objectives and their associated cost or risk. We analyze the complex ethical landscape in which this takes place in the most common dementia, Alzheimer's disease. METHODS Narrative review of literature published since 2007, incorporating snowball sampling where necessary. We identified, thematized, and discussed key issues of ethical salience. RESULTS Eight areas of ethical salience for outcome prioritization emerged: 1) Public health and distributive justice, 2) Scarcity of resources, 3) Heterogeneity and changing circumstances, 4) Knowledge of treatment, 5) Values and circumstances, 6) Conflicting priorities, 7) Communication, autonomy and caregiver issues, and 8) Disclosure of risk. CONCLUSION These areas highlight the difficult balance to be struck when allocating resources, when measuring and prioritizing outcomes, and when individual preferences are sought. We conclude by reflecting on how tools in social sciences and ethics can help address challenges posed by resource allocation, measuring and prioritizing outcomes, and eliciting stakeholder preferences.
Collapse
Affiliation(s)
- Alex McKeown
- Department of Psychiatry and Wellcome Centre for Ethics and Humanities, University of Oxford, Oxford, UK
| | - Andrew Turner
- The National Institute for Health Research Applied Research Collaboration West [NIHR ARC West] at University Hospitals Bristol NHS Foundation Trust, University of Bristol, Bristol, UK
| | | | | | - Amanda Ly
- MRC Integrative Epidemiology Unit & Centre for Academic Mental Health, University of Bristol, Bristol, UK
| | | | - Mia Nelson
- Usher Institute of Population Health Sciences and Informatics, University of Edinburgh, Edinburgh, UK
| | - Claire Tochel
- Usher Institute of Population Health Sciences and Informatics, University of Edinburgh, Edinburgh, UK
| | | | - Alex Keenan
- Janssen Pharmaceutica NV, Titusville, NJ, USA
| | - Michael Smith
- Alzheimer Scotland Centre for Policy and Practice, University of the West of Scotland, Paisley, Scotland, UK
| | - Ilina Singh
- Department of Psychiatry and Wellcome Centre for Ethics and Humanities, University of Oxford, Oxford, UK
| |
Collapse
|
3
|
Foster PP. How does dancing promote brain reconditioning in the elderly? Front Aging Neurosci 2013; 5:4. [PMID: 23447744 PMCID: PMC3581818 DOI: 10.3389/fnagi.2013.00004] [Citation(s) in RCA: 26] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2013] [Accepted: 02/02/2013] [Indexed: 12/02/2022] Open
Affiliation(s)
- Philip P Foster
- The Brown Foundation, Department of NanoMedicine and Biomedical Engineering, Institute of Molecular Medicine for the Prevention of Human Diseases, The University of Texas Health Science Center at Houston Houston, TX, USA ; Division of Pulmonary, Sleep Medicine, and Critical Care, Department of Internal Medicine, The University of Texas Health Science Center at Houston Houston, TX, USA
| |
Collapse
|
4
|
Kuljiš RO, Colom LV, Rojo LE. Biological basis for cerebral dysfunction in schizophrenia in contrast with Alzheimer's disease. Front Psychiatry 2013; 4:119. [PMID: 24550846 PMCID: PMC3909944 DOI: 10.3389/fpsyt.2013.00119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/02/2013] [Accepted: 09/12/2013] [Indexed: 11/30/2022] Open
Abstract
Schizophrenia and Alzheimer's disease are two disorders that, while conceptualized as pathophysiologically and clinically distinct, cause substantial cognitive and behavioral impairment worldwide, and target apparently similar - or nearby - circuitry in regions such as the temporal and frontal lobes. We review the salient differences and similarities from selected historical, nosological, and putative mechanistic viewpoints, as a means to help both clinicians and researchers gain a better insight into these intriguing disorders, for which over a century of research and decades of translational development was needed to begin yielding treatments that are objectively effective, but still very far from entirely satisfactory. Ongoing comparison and "cross-pollination" among these approaches to disorders that produce similar deficits is likely to continue improving both our insight into the mechanisms at play, and the development of biotechnological approaches to tackle both conditions - and related disorders - more rapidly and efficaciously.
Collapse
Affiliation(s)
- Rodrigo O Kuljiš
- Brain-Mind Project, Inc. , Galveston, TX , USA ; Institute of Ethnopharmacology, Universidad Arturo Prat , Iquique , Chile ; The University of Texas Medical Branch at Galveston , Galveston, TX , USA ; Instituto Neurogeriátrico , Santiago , Chile ; Zdrav Mozak Limitada , Santiago , Chile ; Clínica Las Condes, University of Chile , Santiago , Chile ; Encephalogistics, Inc. , Miami, FL , USA
| | - Luis V Colom
- Brain-Mind Project, Inc. , Galveston, TX , USA ; The University of Texas at Brownsville , Brownsville, TX , USA
| | - Leonel E Rojo
- Brain-Mind Project, Inc. , Galveston, TX , USA ; Institute of Ethnopharmacology, Universidad Arturo Prat , Iquique , Chile ; Instituto Neurogeriátrico , Santiago , Chile ; Encephalogistics, Inc. , Miami, FL , USA
| |
Collapse
|
5
|
Yuan L, Wang Y, Thompson PM, Narayan VA, Ye J. Multi-source feature learning for joint analysis of incomplete multiple heterogeneous neuroimaging data. Neuroimage 2012; 61:622-32. [PMID: 22498655 DOI: 10.1016/j.neuroimage.2012.03.059] [Citation(s) in RCA: 109] [Impact Index Per Article: 9.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2011] [Revised: 03/15/2012] [Accepted: 03/20/2012] [Indexed: 11/29/2022] Open
Abstract
Analysis of incomplete data is a big challenge when integrating large-scale brain imaging datasets from different imaging modalities. In the Alzheimer's Disease Neuroimaging Initiative (ADNI), for example, over half of the subjects lack cerebrospinal fluid (CSF) measurements; an independent half of the subjects do not have fluorodeoxyglucose positron emission tomography (FDG-PET) scans; many lack proteomics measurements. Traditionally, subjects with missing measures are discarded, resulting in a severe loss of available information. In this paper, we address this problem by proposing an incomplete Multi-Source Feature (iMSF) learning method where all the samples (with at least one available data source) can be used. To illustrate the proposed approach, we classify patients from the ADNI study into groups with Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal controls, based on the multi-modality data. At baseline, ADNI's 780 participants (172AD, 397 MCI, 211 NC), have at least one of four data types: magnetic resonance imaging (MRI), FDG-PET, CSF and proteomics. These data are used to test our algorithm. Depending on the problem being solved, we divide our samples according to the availability of data sources, and we learn shared sets of features with state-of-the-art sparse learning methods. To build a practical and robust system, we construct a classifier ensemble by combining our method with four other methods for missing value estimation. Comprehensive experiments with various parameters show that our proposed iMSF method and the ensemble model yield stable and promising results.
Collapse
Affiliation(s)
- Lei Yuan
- School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ 85287, USA
| | | | | | | | | | | |
Collapse
|
6
|
Yuan L, Wang Y, Thompson PM, Narayan VA, Ye J. Multi-Source Learning for Joint Analysis of Incomplete Multi-Modality Neuroimaging Data. KDD : PROCEEDINGS. INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING 2012:1149-1157. [PMID: 24014189 PMCID: PMC3763848 DOI: 10.1145/2339530.2339710] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/27/2023]
Abstract
Incomplete data present serious problems when integrating largescale brain imaging data sets from different imaging modalities. In the Alzheimer's Disease Neuroimaging Initiative (ADNI), for example, over half of the subjects lack cerebrospinal fluid (CSF) measurements; an independent half of the subjects do not have fluorodeoxyglucose positron emission tomography (FDG-PET) scans; many lack proteomics measurements. Traditionally, subjects with missing measures are discarded, resulting in a severe loss of available information. We address this problem by proposing two novel learning methods where all the samples (with at least one available data source) can be used. In the first method, we divide our samples according to the availability of data sources, and we learn shared sets of features with state-of-the-art sparse learning methods. Our second method learns a base classifier for each data source independently, based on which we represent each source using a single column of prediction scores; we then estimate the missing prediction scores, which, combined with the existing prediction scores, are used to build a multi-source fusion model. To illustrate the proposed approaches, we classify patients from the ADNI study into groups with Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal controls, based on the multi-modality data. At baseline, ADNI's 780 participants (172 AD, 397 MCI, 211 Normal), have at least one of four data types: magnetic resonance imaging (MRI), FDG-PET, CSF and proteomics. These data are used to test our algorithms. Comprehensive experiments show that our proposed methods yield stable and promising results.
Collapse
Affiliation(s)
- Lei Yuan
- Center for Evolutionary Medicine and Informatics, The Biodesign Institute, ASU, Tempe, AZ ; Department of Computer Science and Engineering, ASU, Tempe, AZ
| | | | | | | | | |
Collapse
|
7
|
Foster PP, Rosenblatt KP, Kuljiš RO. Exercise-induced cognitive plasticity, implications for mild cognitive impairment and Alzheimer's disease. Front Neurol 2011; 2:28. [PMID: 21602910 PMCID: PMC3092070 DOI: 10.3389/fneur.2011.00028] [Citation(s) in RCA: 110] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2011] [Accepted: 04/18/2011] [Indexed: 12/17/2022] Open
Abstract
Lifestyle factors such as intellectual stimulation, cognitive and social engagement, nutrition, and various types of exercise appear to reduce the risk for common age-associated disorders such as Alzheimer’s disease (AD) and vascular dementia. In fact, many studies have suggested that promoting physical activity can have a protective effect against cognitive deterioration later in life. Slowing or a deterioration of walking speed is associated with a poor performance in tests assessing psychomotor speed and verbal fluency in elderly individuals. Fitness training influences a wide range of cognitive processes, and the largest positive impact observed is for executive (a.k.a. frontal lobe) functions. Studies show that exercise improves additional cognitive functions such as tasks mediated by the hippocampus, and result in major changes in plasticity in the hippocampus. Interestingly, this exercise-induced plasticity is also pronounced in APOE ε4 carriers who express a risk factor for late-onset AD that may modulate the effect of treatments. Based on AD staging by Braak and Braak (1991) and Braak et al. (1993) we propose that the effects of exercise occur in two temporo-spatial continua of events. The “inward” continuum from isocortex (neocortex) to entorhinal cortex/hippocampus for amyloidosis and a reciprocal “outward” continuum for neurofibrillary alterations. The exercise-induced hypertrophy of the hippocampus at the core of these continua is evaluated in terms of potential for prevention to stave off neuronal degeneration. Exercise-induced production of growth factors such as the brain-derived neurotrophic factor (BDNF) has been shown to enhance neurogenesis and to play a key role in positive cognitive effects. Insulin-like growth factor (IGF-1) may mediate the exercise-induced response to exercise on BDNF, neurogenesis, and cognitive performance. It is also postulated to regulate brain amyloid β (Aβ) levels by increased clearance via the choroid plexus. Growth factors, specifically fibroblast growth factor and IGF-1 receptors and/or their downstream signaling pathways may interact with the Klotho gene which functions as an aging suppressor gene. Neurons may not be the only cells affected by exercise. Glia (astrocytes and microglia), neurovascular units and the Fourth Element may also be affected in a differential fashion by the AD process. Analyses of these factors, as suggested by the multi-dimensional matrix approach, are needed to improve our understanding of this complex multi-factorial process, which is increasingly relevant to conquering the escalating and intersecting world-wide epidemics of dementia, diabetes, and sarcopenia that threaten the global healthcare system. Physical activity and interventions aimed at enhancing and/or mimicking the effects of exercise are likely to play a significant role in mitigating these epidemics, together with the embryonic efforts to develop cognitive rehabilitation for neurodegenerative disorders.
Collapse
Affiliation(s)
- Philip P Foster
- Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Texas Medical Branch Galveston, TX, USA
| | | | | |
Collapse
|
8
|
Kuljiš RO. The fourth element targeting hypothesis of Alzheimer's disease pathogenesis and pathophysiology. Front Neurol 2010; 1:144. [PMID: 21188267 PMCID: PMC3008923 DOI: 10.3389/fneur.2010.00144] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2010] [Accepted: 10/22/2010] [Indexed: 12/20/2022] Open
Abstract
Despite well over a century of research on all forms of the disorder known as Alzheimer's disease (AD), it is still not known whether the condition targets initially neurons, glial cells, other cellular elements in the brain, or components of cells, such as synapses, or molecules independently of their cellular compartmentalization, or otherwise (e.g., specific neuronal circuits). Multiple lines of highly suggestive but as yet insufficient experimental evidence are discussed here to formulate the hypothesis that AD results from primary (i.e., direct and initial) or secondary targeting of what we designate as the Fourth Element Cell (4EC): a relatively recently identified type of brain cell that exhibits features in common with neurons (e.g., synapses, participation in glutamatergic, and GABAergic neurotransmission), astrocytes, oligodendrocytes, and their precursors, but is in other respects clearly distinct from all of them. The 4EC is proposed to be the main target of both: (1) converging insults (i.e., not true "causes") that over time cause sporadic forms of AD as postulated by the Danger Signal Hypothesis - which was not formulated with 4EC in mind - as well as (2) the causes of inherited (i.e., familial) forms of neurodegeneration that resemble certain aspects of the clinical manifestations of sporadic AD.
Collapse
Affiliation(s)
- Rodrigo O. Kuljiš
- The Brain-Mind Project, Inc. and Encephalogistics, Inc. Galveston, TX, USA
| |
Collapse
|
9
|
Kuljiš RO. Integrative Understanding of Emergent Brain Properties, Quantum Brain Hypotheses, and Connectome Alterations in Dementia are Key Challenges to Conquer Alzheimer's Disease. Front Neurol 2010; 1:15. [PMID: 21188254 PMCID: PMC3008926 DOI: 10.3389/fneur.2010.00015] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2010] [Accepted: 06/17/2010] [Indexed: 11/24/2022] Open
Abstract
The biological substrate for cognition remains a challenge as much as defining this function of living beings. Here, we examine some of the difficulties to understand normal and disordered cognition in humans. We use aspects of Alzheimer's disease and related disorders to illustrate how the wealth of information at many conceptually separate, even intellectually decoupled, physical scales - in particular at the Molecular Neuroscience versus Systems Neuroscience/Neuropsychology levels - presents a challenge in terms of true interdisciplinary integration towards a coherent understanding. These unresolved dilemmas include critically the as yet untested quantum brain hypothesis, and the embryonic attempts to develop and define the so-called connectome in humans and in non-human models of disease. To mitigate these challenges, we propose a scheme incorporating the vast array of scales of the space and time (space-time) manifold from at least the subatomic through cognitive-behavioral dimensions of inquiry, to achieve a new understanding of both normal and disordered cognition, that is essential for a new era of progress in the Generative Sciences and its application to translational efforts for disease prevention and treatment.
Collapse
Affiliation(s)
- Rodrigo O. Kuljiš
- The Brain-Mind Project, Inc, Encephalogistics, Inc, University of MiamiMiami, FL, USA
- Departments of Neurology, Neuroscience and Cell Biology, and Pathology, The University of Texas Medical BranchGalveston, TX, USA
- Mitchell Center for Neurodegenerative Disease, The University of Texas Medical BranchGalveston, TX, USA
| |
Collapse
|