Browse
Submit Data
Databases
API
Help

Dataset Information

28 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Predicting MCI outcome with clinically available MRI and CSF biomarkers.

ABSTRACT:

Objective

To determine the ability of clinically available volumetric MRI (vMRI) and CSF biomarkers, alone or in combination with a quantitative learning measure, to predict conversion to Alzheimer disease (AD) in patients with mild cognitive impairment (MCI).

Methods

We stratified 192 MCI participants into positive and negative risk groups on the basis of 1) degree of learning impairment on the Rey Auditory Verbal Learning Test; 2) medial temporal atrophy, quantified from Food and Drug Administration-approved software for automated vMRI analysis; and 3) CSF biomarker levels(.) We also stratified participants based on combinations of risk factors. We computed Cox proportional hazards models, controlling for age, to assess 3-year risk of converting to AD as a function of risk group and used Kaplan-Meier analyses to determine median survival times.

Results

When risk factors were examined separately, individuals testing positive showed significantly higher risk of converting to AD than individuals testing negative (hazard ratios [HR] 1.8-4.1). The joint presence of any 2 risk factors substantially increased risk, with the combination of greater learning impairment and increased atrophy associated with highest risk (HR 29.0): 85% of patients with both risk factors converted to AD within 3 years, vs 5% of those with neither. The presence of medial temporal atrophy was associated with shortest median dementia-free survival (15 months).

Conclusions

Incorporating quantitative assessment of learning ability along with vMRI or CSF biomarkers in the clinical workup of MCI can provide critical information on risk of imminent conversion to AD.

SUBMITTER: Heister D

PROVIDER: S-EPMC3198979 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

MRI and CSF biomarkers in normal, MCI, and AD subjects: predicting future clinical change.

Project description:ObjectiveTo investigate the relationship between baseline MRI and CSF biomarkers and subsequent change in continuous measures of cognitive and functional abilities in cognitively normal (CN) subjects and patients with amnestic mild cognitive impairment (aMCI) and Alzheimer disease (AD) and to examine the ability of these biomarkers to predict time to conversion from aMCI to AD.MethodsData from the Alzheimer's Disease Neuroimaging Initiative, which consists of CN, aMCI, and AD cohorts with both CSF and MRI, were used. Baseline CSF (t-tau, Abeta(1-42), and p-tau(181P)) and MRI scans were obtained in 399 subjects (109 CN, 192 aMCI, 98 AD). Structural Abnormality Index (STAND) scores, which reflect the degree of AD-like features in MRI, were computed for each subject.ResultsChange on continuous measures of cognitive and functional performance was modeled as average Clinical Dementia Rating-sum of boxes and Mini-Mental State Examination scores over a 2-year period. STAND was a better predictor of subsequent cognitive/functional change than CSF biomarkers. Single-predictor Cox proportional hazard models for time to conversion from aMCI to AD showed that STAND and log (t-tau/Abeta(1-42)) were both predictive of future conversion. The age-adjusted hazard ratio for an interquartile change (95% confidence interval) of STAND was 2.6 (1.7, 4.2) and log (t-tau/Abeta(1-42)) was 2.0 (1.1, 3.4). Both MRI and CSF provided information about future cognitive change even after adjusting for baseline cognitive performance.ConclusionsMRI and CSF provide complimentary predictive information about time to conversion from amnestic mild cognitive impairment to Alzheimer disease and combination of the 2 provides better prediction than either source alone. However, we found that MRI was a slightly better predictor of future clinical/functional decline than the CSF biomarkers tested.

| S-EPMC2715214 | biostudies-literature

Serial MRI and CSF biomarkers in normal aging, MCI, and AD.

Project description:ObjectiveTo compare the annual change in MRI and CSF biomarkers in cognitively normal (CN), amnestic mild cognitive impairment (aMCI), and Alzheimer disease (AD). Comparisons were based on intergroup discrimination, correlation with concurrent cognitive/functional changes, relationships to APOE genotype, and sample sizes for clinical trials.MethodsWe used data from the Alzheimer's Disease Neuroimaging Initiative study consisting of CN, aMCI, and AD cohorts with both baseline and 12-month follow-up CSF and MRI. The annual change in CSF (total-tau [t-tau], Abeta(1-42)) and MRI (change in ventricular volume) was obtained in 312 subjects (92 CN, 149 aMCI, 71 AD).ResultsThere was no significant average annual change in either CSF biomarker in any clinical group except t-tau in CN; moreover, the annual change did not differ by clinical group in pairwise comparisons. In contrast, annual increase in ventricular volume increased in the following order, AD > aMCI > CN, and differences were significant between all clinical groups in pairwise comparisons. Ventricular volume increase correlated with concurrent worsening on cognitive/functional indices in aMCI and AD whereas evidence of a similar correlation with change in CSF measures was unclear. The annual changes in MRI differed by APOE epsilon4 status overall and among aMCI while annual changes in CSF biomarkers did not. Estimated sample sizes for clinical trials are notably less for MRI than the CSF or clinical measures.ConclusionsUnlike the CSF biomarkers evaluated, changes in serial structural MRI are correlated with concurrent change on general cognitive and functional indices in impaired subjects, track with clinical disease stage, and are influenced by APOE genotype.

| S-EPMC2905929 | biostudies-literature

MRI and CSF biomarkers in normal, MCI, and AD subjects: diagnostic discrimination and cognitive correlations.

Project description:ObjectiveTo assess the correlations of both MRI and CSF biomarkers with clinical diagnosis and with cognitive performance in cognitively normal (CN) subjects and patients with amnestic mild cognitive impairment (aMCI) and Alzheimer disease (AD).MethodsThis is a cross-sectional study with data from the Alzheimer's Disease Neuroimaging Initiative, which consists of CN subjects, subjects with aMCI, and subjects with AD with both CSF and MRI. Baseline CSF (t-tau, Abeta(1-42), and p-tau(181P)) and MRI scans were obtained in 399 subjects (109 CN, 192 aMCI, 98 AD). Structural Abnormality Index (STAND) scores, which reflect the degree of AD-like anatomic features on MRI, were computed for each subject.ResultsWe found no significant correlation between CSF biomarkers and cognitive scores in any of the 3 clinical groups individually. Conversely, STAND scores correlated with both Clinical Dementia Rating-sum of boxes and Mini-Mental State Examination in aMCI and AD (p < or = 0.01). While STAND and all CSF biomarkers were predictors of clinical group membership (CN, aMCI, or AD) univariately (p < 0.001), STAND was more predictive than CSF both univariately and in combined models.ConclusionsCSF and MRI biomarkers independently contribute to intergroup diagnostic discrimination and the combination of CSF and MRI provides better prediction than either source of data alone. However, MRI provides greater power to effect cross-sectional groupwise discrimination and better correlation with general cognition and functional status cross-sectionally. We therefore conclude that although MRI and CSF provide complementary information, MRI reflects clinically defined disease stage better than the CSF biomarkers tested.

| S-EPMC2715210 | biostudies-literature

Alzheimer Disease Biomarkers as Outcome Measures for Clinical Trials in MCI.

Project description:The aim of this study was to compare the performance and power of the best-established diagnostic biological markers as outcome measures for clinical trials in patients with mild cognitive impairment (MCI).Magnetic resonance imaging, F-18 fluorodeoxyglucose positron emission tomography markers, and Alzheimer's Disease Assessment Scale-cognitive subscale were compared in terms of effect size and statistical power over different follow-up periods in 2 MCI groups, selected from Alzheimer's Disease Neuroimaging Initiative data set based on cerebrospinal fluid (abnormal cerebrospinal fluid A?1-42 concentration-ABETA+) or magnetic resonance imaging evidence of Alzheimer disease (positivity to hippocampal atrophy-HIPPO+). Biomarkers progression was modeled through mixed effect models. Scaled slope was chosen as measure of effect size. Biomarkers power was estimated using simulation algorithms.Seventy-four ABETA+ and 51 HIPPO+ MCI patients were included in the study. Imaging biomarkers of neurodegeneration, especially MR measurements, showed highest performance. For all biomarkers and both MCI groups, power increased with increasing follow-up time, irrespective of biomarker assessment frequency.These findings provide information about biomarker enrichment and outcome measurements that could be employed to reduce MCI patient samples and treatment duration in future clinical trials.

| S-EPMC4437812 | biostudies-literature

Can MRI screen for CSF biomarkers in neurodegenerative disease?

Project description:ObjectiveAlzheimer disease (AD) and frontotemporal lobar degeneration (FTLD) may have overlapping clinical presentations despite distinct underlying neuropathologies, thus making in vivo diagnosis challenging. In this study, we evaluate the utility of MRI as a noninvasive screening procedure for the differential diagnosis of AD and FTLD.MethodsWe recruited 185 patients with a clinically diagnosed neurodegenerative disease consistent with AD or FTLD who had a lumbar puncture and a volumetric MRI. A subset of 32 patients had genetic or autopsy-confirmed AD or FTLD. We used singular value decomposition to decompose MRI volumes and linear regression and cross-validation to predict CSF total tau (tt) and β-amyloid (Aβ(1-42)) ratio (tt/Aβ) in patients with AD and patients with FTLD. We then evaluated accuracy of MRI-based predicted tt/Aβ using 4 converging sources including neuroanatomic visualization and categorization of a subset of patients with genetic or autopsy-confirmed AD or FTLD.ResultsRegression analyses showed that MRI-predicted tt/Aβ is highly related to actual CSF tt/Aβ. In each group, both predicted and actual CSF tt/Aβ have extensively overlapping neuroanatomic correlates: low tt/Aβ consistent with FTLD is related to ventromedial prefrontal regions while high tt/Aβ consistent with AD is related to posterior cortical regions. MRI-predicted tt/Aβ is 75% accurate at identifying underlying diagnosis in patients with known pathology and in clinically diagnosed patients with known CSF tt/Aβ levels.ConclusionMRI may serve as a noninvasive procedure that can screen for AD and FTLD pathology as a surrogate for CSF biomarkers.

| S-EPMC3589187 | biostudies-literature

CSF protein biomarkers predicting longitudinal reduction of CSF ?-amyloid42 in cognitively healthy elders.

Project description:?-amyloid (A?) plaque accumulation is a hallmark of Alzheimer's disease (AD). It is believed to start many years prior to symptoms and is reflected by reduced cerebrospinal fluid (CSF) levels of the peptide A?1-42 (A?42). Here we tested the hypothesis that baseline levels of CSF proteins involved in microglia activity, synaptic function and A? metabolism predict the development of A? plaques, assessed by longitudinal CSF A?42 decrease in cognitively healthy people. Forty-six healthy people with three to four serial CSF samples were included (mean follow-up 3 years, range 2-4 years). There was an overall reduction in A?42 from a mean concentration of 211-195 pg ml(-1) after 4 years. Linear mixed-effects models using longitudinal A?42 as the response variable, and baseline proteins as explanatory variables (n=69 proteins potentially relevant for A? metabolism, microglia or synaptic/neuronal function), identified 10 proteins with significant effects on longitudinal A?42. The most significant proteins were angiotensin-converting enzyme (ACE, P=0.009), Chromogranin A (CgA, P=0.009) and Axl receptor tyrosine kinase (AXL, P=0.009). Receiver-operating characteristic analysis identified 11 proteins with significant effects on longitudinal A?42 (largely overlapping with the proteins identified by linear mixed-effects models). Several proteins (including ACE, CgA and AXL) were associated with A?42 reduction only in subjects with normal baseline A?42, and not in subjects with reduced baseline A?42. We conclude that baseline CSF proteins related to A? metabolism, microglia activity or synapses predict longitudinal A?42 reduction in cognitively healthy elders. The finding that some proteins only predict A?42 reduction in subjects with normal baseline A?42 suggest that they predict future development of the brain A? pathology at the earliest stages of AD, prior to widespread development of A? plaques.

| S-EPMC3756294 | biostudies-literature

Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma

Project description:Abstract Background Glioblastoma is the most common primary brain malignancy, yet treatment options are limited, and prognosis remains guarded. Individualized tumor genetic assessment has become important for accurate prognosis and for guiding emerging targeted therapies. However, challenges remain for widespread tumor genetic testing due to costs and the need for tissue sampling. The aim of this study is to evaluate a novel artificial intelligence method for predicting clinically relevant genetic biomarkers from preoperative brain MRI in patients with glioblastoma. Methods We retrospectively analyzed preoperative MRI data from 400 patients with glioblastoma, IDH-wildtype or WHO grade 4 astrocytoma, IDH mutant who underwent resection and genetic testing. Nine genetic biomarkers were assessed: hotspot mutations of IDH1 or TERT promoter, pathogenic mutations of TP53, PTEN, ATRX, or CDKN2A/B, MGMT promoter methylation, EGFR amplification, and combined aneuploidy of chromosomes 7 and 10. Models were developed to predict biomarker status from MRI data using radiomics features, convolutional neural network (CNN) features, and a combination of both. Results Combined model performance was good for IDH1 and TERT promoter hotspot mutations, pathogenic mutations of ATRX and CDKN2A/B, and combined aneuploidy of chromosomes 7 and 10, with receiver operating characteristic area under the curve (ROC AUC) >0.85 and was fair for all other tested biomarkers with ROC AUC >0.7. Combined model performance was statistically superior to individual radiomics and CNN feature models for prediction chromosome 7 and 10 aneuploidy, MGMT promoter methylation, and PTEN mutation. Conclusions Combining radiomics and CNN features from preoperative MRI yields improved noninvasive genetic biomarker prediction performance in patients with WHO grade 4 diffuse astrocytic gliomas.

| S-EPMC9122791 | biostudies-literature

Predicting clinically significant prostate cancer using DCE-MRI habitat descriptors.

Project description:Prostate cancer diagnosis and treatment continues to be a major public health challenge. The heterogeneity of the disease is one of the major factors leading to imprecise diagnosis and suboptimal disease management. The improved resolution of functional multi-parametric magnetic resonance imaging (mpMRI) has shown promise to improve detection and characterization of the disease. Regions that subdivide the tumor based on Dynamic Contrast Enhancement (DCE) of mpMRI are referred to as DCE-Habitats in this study. The DCE defined perfusion curve patterns on the identified tumor habitat region are used to assess clinical significance. These perfusion curves were systematically quantified using seven features in association with the patient biopsy outcome and classifier models were built to find the best discriminating characteristics between clinically significant and insignificant prostate lesions defined by Gleason score (GS). Multivariable analysis was performed independently on one institution and validated on the other, using a multi-parametric feature model, based on DCE characteristics and ADC features. The models had an intra institution Area under the Receiver Operating Characteristic (AUC) of 0.82. Trained on Institution I and validated on the cohort from Institution II, the AUC was also 0.82 (sensitivity 0.68, specificity 0.95).

| S-EPMC6324677 | biostudies-literature

Predicting outcome in clinically isolated syndrome using machine learning.

Project description:We aim to determine if machine learning techniques, such as support vector machines (SVMs), can predict the occurrence of a second clinical attack, which leads to the diagnosis of clinically-definite Multiple Sclerosis (CDMS) in patients with a clinically isolated syndrome (CIS), on the basis of single patient's lesion features and clinical/demographic characteristics. Seventy-four patients at onset of CIS were scanned and clinically reviewed after one and three years. CDMS was used as the gold standard against which SVM classification accuracy was tested. Radiological features related to lesional characteristics on conventional MRI were defined a priori and used in combination with clinical/demographic features in an SVM. Forward recursive feature elimination with 100 bootstraps and a leave-one-out cross-validation was used to find the most predictive feature combinations. 30 % and 44 % of patients developed CDMS within one and three years, respectively. The SVMs correctly predicted the presence (or the absence) of CDMS in 71.4 % of patients (sensitivity/specificity: 77 %/66 %) at 1 year, and in 68 % (60 %/76 %) at 3 years on average over all bootstraps. Combinations of features consistently gave a higher accuracy in predicting outcome than any single feature. Machine-learning-based classifications can be used to provide an "individualised" prediction of conversion to MS from subjects' baseline scans and clinical characteristics, with potential to be incorporated into routine clinical practice.

| S-EPMC4297887 | biostudies-literature

Synaptic biomarkers in CSF aid in diagnosis, correlate with cognition and predict progression in MCI and Alzheimer's disease.

Project description:IntroductionAmyloid, Tau, and neurodegeneration biomarkers can stage Alzheimer's Disease (AD). Synaptic biomarkers may help track cognition.MethodsIn cognitively normal controls, Mild Cognitive Impairment (MCI) and AD, we investigated CSF biomarkers in relation to cognitive measures and as predictors of cognitive and global decline.ResultsThere were 90 normal controls (mean age 73.0, 58% women), 57 MCI (mean age 74.3, 35% women), and 46 AD (mean age 70.7, 41% women). CSF Aβ1-42 and Neuronal Pentraxin 2 (NPTX2) were decreased, and CSF Tau, neurogranin, and SNAP25 increased in AD versus controls. Aβ1-42/Tau or NPTX2/Tau discriminated AD and controls best. NPTX2/Tau correlated strongly with cognition in AD and MCI and predicted a 2-3-year decline. We replicated findings in the ADNI cohort.DiscussionCSF synaptic biomarkers, particularly NPTX2, which regulates synaptic homeostasis, relate to cognition and predict progression in AD beyond Aβ1-42 and Tau. This is relevant for prognosis and clinical trials.

| S-EPMC6911971 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data