Machine Learning Driven Profiling of Cerebrospinal Fluid Core Biomarkers in Alzheimer’s Disease and Other Neurological Disorders

Amyloid-beta (Aβ) 42/40 ratio, tau phosphorylated at threonine-181 (p-tau), and total-tau (t-tau) are considered core biomarkers for the diagnosis of Alzheimer’s disease (AD). The use of fully automated biomarker assays has been shown to reduce the intra- and inter-laboratory variability, which is a critical factor when defining cut-off values. The calculation of cut-off values is often influenced by the composition of AD and control groups. Indeed, the clinically defined AD group may include patients affected by other forms of dementia, while the control group is often very heterogeneous due to the inclusion of subjects diagnosed with other neurological diseases (OND). In this context, unsupervised machine learning approaches may overcome these issues providing unbiased cut-off values and data-driven patient stratification according to the sole distribution of biomarkers. In this work, we took advantage of the reproducibility of automated determination of the CSF core AD biomarkers to compare two large cohorts of patients diagnosed with different neurological disorders and enrolled in two centers with established expertise in AD biomarkers. We applied an unsupervised Gaussian mixture model clustering algorithm and found that our large series of patients could be classified in six clusters according to their CSF biomarker profile, some presenting a typical AD-like profile and some a non-AD profile. By considering the frequencies of clinically defined OND and AD subjects in clusters, we subsequently computed cluster-based cut-off values for Aβ42/Aβ40, p-tau, and t-tau. This approach promises to be useful for large-scale biomarker studies aimed at providing efficient biochemical phenotyping of neurological diseases.

Download Full-text

Machine learning prediction of incidence of Alzheimer’s disease using large-scale administrative health data

npj Digital Medicine ◽

10.1038/s41746-020-0256-0 ◽

2020 ◽

Vol 3 (1) ◽

Cited By ~ 7

Author(s):

Ji Hwan Park ◽

Han Eol Cho ◽

Jong Hun Kim ◽

Melanie M. Wall ◽

Yaakov Stern ◽

...

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Large Scale ◽

Health Data ◽

Administrative Health Data

Download Full-text

Computational Methods Dedicated for Neurological Disorder Detection through Epistasis Analysis: A Review

Current Chinese Engineering Science ◽

10.2174/1573411016999201110101039 ◽

2020 ◽

Vol 01 ◽

Author(s):

Sridharan Priya ◽

Radhakrishnan Manavalana

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Neurological Disorders ◽

Neurological Disorder ◽

Disease Risk ◽

Neurological Diseases ◽

Association Studies ◽

Genetic Interactions ◽

Computational Techniques ◽

Genome Wide Association Studies

Background: Neurological disorders diseases such as ALS, Alzheimer’s, epilepsy, Parkinson’s Disease, Autism, Atrial Fibrillation, and Sclerosis affect the central nervous system, including the brain, nerves, spinal cords, muscles, and Neuromuscular joint. These disorders are investigated by detecting the genetic variations in Single Nucleotide Polymorphism (SNP) in Genome-Wide Association Studies (GWAS). In the human genome sequence, one SNP influence the effects of another SNP. These SNP-SNP interactions or Gene-Gene interaction (Epistasis) significantly increases the risk of disease susceptibility to neurological disorders. Objective: The manual analyzes of various genetic interactions related to Neurological diseases are cumbersome. Hence, the computational system is effective for the discovery of Epistasis effects in Neurological syndromes. This study aims to explore various techniques of statistical, machine learning, optimization, so far applied to find the epistasis effect for neurological-disorder. Conclusion: This study finds several genetic interactions models involving different loci, various candidate genes, and SNP interactions involved in numerous neurological diseases. The gene APOE and its polymorphism increase Alzheimer's disease pathology. The gene GAB2 and its SNPs play a vital role in Alzheimer’s disease. The genes GABRA4, ITGB3, and SLC64A highly influence the genetic interactions for Autism disorder. In schizophrenia, the SNPs of NRG1 increases the disease risk. The benefits, limitations, and issues of the various computational techniques implemented for epistasis evaluation of neurological disease are deeply discussed.

Download Full-text

Neuroinflammation and Alzheimer’s Disease: A Machine Learning Approach to CSF Proteomics

Cells ◽

10.3390/cells10081930 ◽

2021 ◽

Vol 10 (8) ◽

pp. 1930

Author(s):

Lorenzo Gaetani ◽

Giovanni Bellomo ◽

Lucilla Parnetti ◽

Kaj Blennow ◽

Henrik Zetterberg ◽

...

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Biomarker Discovery ◽

Neurological Diseases ◽

Univariate Analysis ◽

Learning Approach ◽

Barrier Dysfunction ◽

Csf Analysis ◽

Machine Learning Approach

In Alzheimer’s disease (AD), the contribution of pathophysiological mechanisms other than amyloidosis and tauopathy is now widely recognized, although not clearly quantifiable by means of fluid biomarkers. We aimed to identify quantifiable protein biomarkers reflecting neuroinflammation in AD using multiplex proximity extension assay (PEA) testing. Cerebrospinal fluid (CSF) samples from patients with mild cognitive impairment due to AD (AD-MCI) and from controls, i.e., patients with other neurological diseases (OND), were analyzed with the Olink Inflammation PEA biomarker panel. A machine-learning approach was then used to identify biomarkers discriminating AD-MCI (n: 34) from OND (n: 25). On univariate analysis, SIRT2, HGF, MMP-10, and CXCL5 showed high discriminatory performance (AUC 0.809, p = 5.2 × 10−4, AUC 0.802, p = 6.4 × 10−4, AUC 0.793, p = 3.2 × 10−3, AUC 0.761, p = 2.3 × 10−3, respectively), with higher CSF levels in AD-MCI patients as compared to controls. These same proteins were the best contributors to the penalized logistic regression model discriminating AD-MCI from controls (AUC of the model 0.906, p = 2.97 × 10−7). The biological processes regulated by these proteins include astrocyte and microglia activation, amyloid, and tau misfolding modulation, and blood-brain barrier dysfunction. Using a high-throughput multiplex CSF analysis coupled with a machine-learning statistical approach, we identified novel biomarkers reflecting neuroinflammation in AD. Studies confirming these results by means of different assays are needed to validate PEA as a multiplex technique for CSF analysis and biomarker discovery in the field of neurological diseases.

Download Full-text

The Implication of STEP in Synaptic Plasticity and Cognitive Impairments in Alzheimer’s Disease and Other Neurological Disorders

Frontiers in Cell and Developmental Biology ◽

10.3389/fcell.2021.680118 ◽

2021 ◽

Vol 9 ◽

Author(s):

Yacoubou Abdoul Razak Mahaman ◽

Fang Huang ◽

Kidane Siele Embaye ◽

Xiaochuan Wang ◽

Feiqi Zhu

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Synaptic Plasticity ◽

Ampa Receptor ◽

Neurological Disorders ◽

Neurological Diseases ◽

Cognitive Impairments ◽

Tyrosine Phosphatase ◽

Receptor Complexes ◽

Related Proteins

STriatal-Enriched protein tyrosine Phosphatase (STEP) is a tyrosine phosphatase that has been implicated in Alzheimer’s disease (AD), the most common form of dementia, and many other neurological diseases. The protein level and activity of STEP have been found to be elevated in most of these disorders, and specifically in AD as a result of dysregulation of different pathways including PP2B/DARPP32/PP1, PKA as well as impairments of both proteasomal and lysosomal systems. The upregulation in STEP leads to increased binding to, and dephosphorylation of, its substrates which are mainly found to be synaptic plasticity and thus learning and memory related proteins. These proteins include kinases like Fyn, Pyk2, ERK1/2 and both NMDA and AMPA receptor subunits GluN2B and GluA2. The dephosphorylation of these molecules results in inactivation of these kinases and internalization of NMDA and AMPA receptor complexes leading to synapse loss and cognitive impairments. In this study, we aim to review STEP regulation and its implications in AD as well as other neurological disorders and then summarize data on targeting STEP as therapeutic strategy in these diseases.

Download Full-text

Alzheimer's Disease Risk Assessment Using Large-Scale Machine Learning Methods

PLoS ONE ◽

10.1371/journal.pone.0077949 ◽

2013 ◽

Vol 8 (11) ◽

pp. e77949 ◽

Cited By ~ 54

Author(s):

Ramon Casanova ◽

Fang-Chi Hsu ◽

Kaycee M. Sink ◽

Stephen R. Rapp ◽

Jeff D. Williamson ◽

...

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Risk Assessment ◽

Alzheimer's Disease ◽

Large Scale ◽

Disease Risk ◽

Learning Methods ◽

Machine Learning Methods

Download Full-text

Cerebral Responses to Acupuncture at GV24 and Bilateral GB13 in Rat Models of Alzheimer’s Disease

Behavioural Neurology ◽

10.1155/2018/8740284 ◽

2018 ◽

Vol 2018 ◽

pp. 1-10 ◽

Cited By ~ 4

Author(s):

Shaoyang Cui ◽

Mingzhu Xu ◽

Jianting Huang ◽

Qing Mei Wang ◽

Xinsheng Lai ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Neurological Diseases ◽

Statistical Parametric Mapping ◽

Insular Cortex ◽

Retrosplenial Cortex ◽

Association Cortex ◽

Control Group ◽

Cerebral Peduncle ◽

Positron Emission

Acupuncture has been widely used in China to treat neurological diseases including Alzheimer’s disease (AD). However, its mechanism remains unclear. In the present study, eighty healthy Wistar rats were divided into a normal control group (n=15) and premodel group (n=65). Forty-five rats that met the criteria for the AD model were then randomly divided into the model group (MG), the nonacupoint group (NG), and the acupoint group (AG). All rats received positron emission tomography (PET) scanning, and the images were analyzed with Statistical Parametric Mapping 8.0. MG exhibited hypometabolism in the olfactory bulb, insular cortex, orbital cortex, prelimbic cortex, striatum, parietal association cortex, visual cortex, cingulate gyrus, and retrosplenial cortex. AG exhibited prominent and extensive hypermetabolism in the thalamus, hypothalamus, bed nucleus of the stria terminalis, cerebral peduncle, midbrain tegmentum, and pontine tegmentum compared to NG. These results demonstrated that acupuncturing at GV24 and bilateral GB13 acupoints may improve the learning and memory abilities of the AD rats, probably via altering cerebral glucose metabolism (CGM) in the hypothalamus, thalamus, and brain stem. The observed effects of acupuncture may be caused by regulating the distribution of certain kinds of neurotransmitters and enhancing synaptic plasticity.

Download Full-text

CSF biomarker profiles in CNS infection associated with HSV and VZV mimic pattern in Alzheimer’s disease.

10.21203/rs.3.rs-66188/v1 ◽

2020 ◽

Author(s):

Makiko Shinomoto ◽

TAKASHI KASAI ◽

Harutsugu Tatebe ◽

Fukiko Kitani-Morii ◽

Takuma Ohmichi ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Disease Severity ◽

Amyloid Β ◽

Cns Infection ◽

Control Group ◽

Neurofilament Light Chain ◽

Cns Infections ◽

Csf Biomarker ◽

T Tau

Abstract Background: Central nervous system (CNS) infections have been reported to have a certain etiological relevance to Alzheimer’s disease (AD). In particular, herpes simplex virus (HSV) and varicella zoster virus (VZV) infections has been reported as risk factors for AD. The aim of this study was to determine whether or not AD-related biomarkers were changed in patients with HSV or VZV CNS infections.Methods: Nine patients with HSV infection of the CNS, eight patients with VZV complicated by CNS involvement, and eighteen age-matched controls were enrolled. Amyloid β (Aβ)1-42, Aβ1-40, total-tau (t-tau), tau phosphorylated at threonine 181 (p-tau), neurofilament light chain (NfL), phosphorylated neurofilament heavy chain (p-NfH), glial fibrillary acidic protein (GFAP), and soluble triggering receptor expressed on myeloid cells 2 (sTREM2) in were measured in cerebrospinal fluid (CSF), and NfL in serum.Results: Compared with the control group, CSF Aβ1-42, Aβ1-40, and the Aβ1-42/ Aβ1-40 ratio were significantly decreased, and CSF t-tau, p-tau, sTREM2, and GFAP were significantly increased in the HSV and VZV combined group, in which biomarker changes were similar to those reported in AD. CSF NfL levels measured on admission were significantly correlated with the disease severity and a poor outcome after age adjustment. Serum NfL on admission was also associated with disease severity after age adjustment.Conclusions: The fact that the biomarker profile in patients with CNS HSV and VZV infections mimicked that in AD patients should be paid attention to as a potential confounding factor in CSF biomarker-based diagnosis of AD, and it suggests an etiological similarity between herpetic virus infection and AD. The CSF NfL concentration on admission may be useful as a predictive marker of severity and prognosis in patients with CNS HSV and VZV infections.

Download Full-text

The Feasibility of Using Virtual Reality and Eye Tracking in Research With Older Adults With and Without Alzheimer's Disease

Frontiers in Aging Neuroscience ◽

10.3389/fnagi.2021.607219 ◽

2021 ◽

Vol 13 ◽

Author(s):

Rebecca Davis

Keyword(s):

Alzheimer’S Disease ◽

Older Adults ◽

Alzheimer's Disease ◽

Virtual Reality ◽

Eye Tracking ◽

Large Scale ◽

Early Stage ◽

Retirement Community ◽

Control Group ◽

Reality Testing

Aim: To examine the feasibility of using large scale spatial, self-mobile, virtual reality, and eye tracking in older adults with and without Alzheimer's disease (AD).Methods: Older adults with early stage AD (n = 38) and a control group without AD (n = 50) were asked to find their way in a large, projected VR simulation of a retirement community repeatedly over 10 trials for each of 2 days, while wearing eye tracking glasses. Feasibility measures, including tolerance, side effects, and ability to complete the VR and eye tracking were collected. This study reports the analysis of the feasibility data for the VR and eye tracking and comparison of findings between the groups.Results: Over 80% of the subjects were able to complete the VR portion of the study. Only four subjects, all in the AD group, could not use the joystick and were excluded. Withdrawal rate (18%) was similar between the groups [X2(2) = 2.82, N = 88, p = 0.245] with most withdrawals occurring after the fourth trial. Simulation sickness was not significantly different between the groups. Only 60% of the subjects had completed eye tracking videos; more subjects in the AD group had complete eye tracking videos than the control group; X2(1) = 7.411, N = 88, p = 0.006. Eye tracking incompletion was primarily due to inability to calibration issues.Conclusion: Virtual reality testing and eye tracking can be used in older adults with and without AD in a large-scale way-finding task, but that there are some limitations.

Download Full-text

Association of serum apolipoprotein B with cerebrospinal fluid Alzheimer’s disease biomarkers in patients with subjective cognitive decline

10.21203/rs.2.19696/v2 ◽

2020 ◽

Author(s):

Hao Hu ◽

Lan Tan ◽

Yan-Lin Bi ◽

Wei Xu ◽

Lin Tan ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Cerebrospinal Fluid ◽

Cognitive Decline ◽

Apolipoprotein B ◽

Subjective Cognitive Decline ◽

Control Group ◽

Elderly Adults ◽

Preclinical Stage ◽

T Tau

Abstract Background The preclinical stage of Alzheimer's disease (AD) has become a key target stage for future AD prevention trials. Serum apolipoprotein, an important lipid-related factor, has been found to be involved in the pathogenesis of AD. This study was to examine whether apolipoprotein B (ApoB), apolipoprotein A-1 (ApoA1) or the ratio of ApoB and ApoA1 (ApoB/A1) were associated with early changes of cerebrospinal fluid (CSF) AD biomarkers in elderly adults with subjective cognitive decline. Methods This study included 201 cognitive normal (CN) elderly adults and 101 participants with subjective cognitive decline (SCD) from the Chinese Alzheimer’s Biomarker and LifestylE (CABLE) database. The Kruskall-Wallis test and Chisquare test were applied in the intergroup comparisons. Multiple linear regression models were used to examine the cross-sectional associations of serum ApoB, ApoA1 and ApoB/A1 levels with CSF AD-related biomarkers. Results Compared with the control group, SCD participants with significant AD biological characteristics had lower ApoB levels. In the total participants, higher level of serum ApoB was associated with increases in CSF Aβ42 (p = 0.0009) and Aβ42/40 (p = 0.0038) as well as decreases in CSF t-tau/Aβ42 (p < 0.0001) and p-tau/Aβ42 (p < 0.0001), independent of APOEɛ4 status. In the further subgroup analysis, these associations were much more significant in the SCD participants. In addition, higher levels of serum ApoB were also found associated with decreases in CSF t-tau (p = 0.0224), p-tau (p = 0.0086) and Aβ40 (p = 0.0297) in the SCD subgroup. Furthermore, we found that these protective associations between serum ApoB and CSF AD core biomarkers were much more significant in the overweight participants. Results showed no association between ApoA1 and all CSF biomarkers in either total participants or subgroups. Conclusions This study is the first to find protective associations of serum ApoB, but not ApoA1, with CSF AD core biomarkers in elderly adults, and these associations were more significant in SCD individuals. This finding indicated that ApoB may play a protective role in the preclinical stage of AD. Identifying the underlying mechanisms may contribute to the discovery of new pathogenic mechanisms and therapeutic targets.

Download Full-text

Neuroprotective Effects of Cistanches Herba Therapy on Patients with Moderate Alzheimer’s Disease

Evidence-based Complementary and Alternative Medicine ◽

10.1155/2015/103985 ◽

2015 ◽

Vol 2015 ◽

pp. 1-12 ◽

Cited By ~ 11

Author(s):

Nan Li ◽

Jianping Wang ◽

Jun Ma ◽

Zhiqiang Gu ◽

Chao Jiang ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Independent Living ◽

Control Group ◽

Mrna Levels ◽

Volume Changes ◽

Neuroprotective Effects ◽

Mri Scans ◽

And Control ◽

T Tau

Cistanches Herba (CH) is thought to be a “Yang-invigorating” material in traditional Chinese medicine. We evaluated neuroprotective effects of Cistanches Herba on Alzheimer’s disease (AD) patients. Moderate AD participants were divided into 3 groups: Cistanches Herba capsule (CH,n=10), Donepezil tablet (DON,n=8), and control group without treatmentn=6. We assessed efficacy by MMSE and ADAS-cog, and investigated the volume changes of hippocampus by 1.5 T MRI scans. Protein, mRNA levels, and secretions of total-tau (T-tau), tumor necrosis factor-α(TNF-α), and interleukin- (IL) 1β(IL-1β) in cerebrospinal fluid (CSF) were detected by Western blot, RT-PCR, and ELISA. The scores showed statistical difference after 48 weeks of treatment compared to control group. Meanwhile, volume changes of hippocampus were slight in drug treatment groups but distinct in control group; the levels of T-tau, TNF-α, and IL-1βwere decreased compared to those in control group. Cistanches Herba could improve cognitive and independent living ability of moderate AD patients, slow down volume changes of hippocampus, and reduce the levels of T-tau, TNF-α, and IL-1β. It suggested that Cistanches Herba had potential neuroprotective effects for moderate AD.

Download Full-text