Assessment of the Correlation and Diagnostic Accuracy between Cerebrospinal Fluid and Plasma Alzheimer's Disease Biomarkers: A Comparison of the Lumipulse and Simoa Platforms.

We compared the clinical and analytical performance of Alzheimer's disease (AD) plasma biomarkers measured using the single-molecule array (Simoa) and Lumipulse platforms. We quantified the plasma levels of amyloid beta 42 (Aß42), Aß40, phosphorylated tau (Ptau181), and total tau biomarkers in 81 patients with mild cognitive impairment (MCI), 30 with AD, and 16 with non-AD dementia. We found a strong correlation between the Simoa and Lumipulse methods. Concerning the clinical diagnosis, Simoa Ptau181/Aß42 (AUC 0.739, 95% CI 0.592-0.887) and Lumipulse Aß42 and Ptau181/Aß42 (AUC 0.735, 95% CI 0.589-0.882 and AUC 0.733, 95% CI 0.567-0.900) had the highest discriminating power. However, their power was significantly lower than that of CSF Aß42/Aß40, as measured by Lumipulse (AUC 0.879, 95% CI 0.766-0.992). Simoa Ptau181 and Lumipulse Ptau181/Aß42 were the markers most consistent with the CSF Aß42/Aß40 status (AUC 0.801, 95% CI 0.712-0.890 vs. AUC 0.870, 95% CI 0.806-0.934, respectively) at the ≥2.127 and ≥0.084 cut-offs, respectively. The performance of the Simoa and Lumipulse plasma AD assays is weaker than that of CSF AD biomarkers. At present, the analysed AD plasma biomarkers may be useful for screening to reduce the number of lumbar punctures in the clinical setting.

The interaction of global small vessel disease burden and Alzheimer's disease pathologies do not change the independent association of amyloid-beta with hippocampal volume: A longitudinal study on mild cognitive impairment subjects.

The purpose of this study was to investigate whether the co-existence of global small vessel disease (SVD) burdens and Alzheimer's disease (AD) pathologies change hippocampal volume (HV) and cognitive function of mild cognitive impairment (MCI) subjects. We obtained MRI images, cerebrospinal fluid biomarkers (Aß1-42 and p-tau), and neuropsychological tests of 310 MCI subjects from ADNI. The global SVD score was assessed. We used linear regression and linear mixing effect to analyze the effects of global SVD burdens, AD pathologies, and their interactions (SVD*AD) on baseline and longitudinal HV and cognition respectively. We used simple mediation effect to analyze the influencing pathways. After adjusting for global SVD and SVD*AD, Aß remained independently correlated with baseline and longitudinal HV (std ß = 0.294, p = .007; std ß = 0.292, p < .001), indicating that global SVD did not affect the correlation between Aß and HV. Global SVD score was correlated with longitudinal but not baseline HV (std ß = 0.470, p = .050), suggesting that global SVD may be more representative of long-term permanent impairment. Global SVD, AD pathologies, and SVD*AD were independently correlated with baseline and longitudinal cognitions, in which the association of Aß (B = 0.005, 95% CI: 0.005; 0.024) and p-tau (B = -0.002, 95% CI: -0.004; -0.000) with cognition were mediated by HV, suggesting that HV is more likely to explain the progression caused by AD pathology than SVD. The co-existence of global SVD and AD pathologies did not affect the individual association of Aß on HV; HV played a more important role in the influence of AD pathology on cognition than in SVD.

Exploratory Assessment of Proteomic Network Changes in Cerebrospinal Fluid of Mild Cognitive Impairment Patients: A Pilot Study.

(1) Background: Despite the existence of well-established, CSF-based biomarkers such as amyloid-ß and phosphorylated-tau, the pathways involved in the pathophysiology of Alzheimer's disease (AD) remain an active area of research. (2) Methods: We measured 3072 proteins in CSF samples of AD-biomarker positive mild cognitive impairment (MCI) participants (n = 38) and controls (n = 48), using the Explore panel of the Olink proximity extension assay (PEA). We performed group comparisons, association studies with diagnosis, age, and APOE ε4 status, overrepresentation analysis (ORA), and gene set enrichment analysis (GSEA) to determine differentially expressed proteins and dysregulated pathways. (3) Results: GSEA results demonstrated an enrichment of granulocyte-related and chemotactic pathways (core enrichment proteins: ITGB2, ITGAM, ICAM1, SELL, SELP, C5, IL1A). Moreover, some of the well-replicated, differentially expressed proteins in CSF included: ITGAM, ITGB2, C1QA, TREM2, GFAP, NEFL, MMP-10, and a novel tau-related marker, SCRN1. (4) Conclusion: Our results highlight the upregulation of neuroinflammatory pathways, especially chemotactic and granulocyte recruitment in CSF of early AD patients.

Decision tree-based classification as a support to diagnosis in the Alzheimer's disease continuum using cerebrospinal fluid biomarkers: insights from automated analysis.

OBJECTIVE: Cerebrospinal fluid (CSF) biomarkers add accuracy to the diagnostic workup of cognitive impairment by illustrating Alzheimer's disease (AD) pathology. However, there are no universally accepted cutoff values for the interpretation of AD biomarkers. The aim of this study is to determine the viability of a decision-tree method to analyse CSF biomarkers of AD as a support for clinical diagnosis. METHODS: A decision-tree method (automated classification analysis) was applied to concentrations of AD biomarkers in CSF as a support for clinical diagnosis in older adults with or without cognitive impairment in a Brazilian cohort. In brief, 272 older adults (68 with AD, 122 with mild cognitive impairment [MCI], and 82 healthy controls) were assessed for CSF concentrations of Aß1-42, total-tau, and phosphorylated-tau using multiplexed Luminex assays; biomarker values were used to generate decision-tree algorithms (classification and regression tree) in the R statistical software environment. RESULTS: The best decision tree model had an accuracy of 74.65% to differentiate the three groups. Cluster analysis supported the combination of CSF biomarkers to differentiate AD and MCI vs. controls, suggesting the best cutoff values for each clinical condition. CONCLUSION: Automated analyses of AD biomarkers provide valuable information to support the clinical diagnosis of MCI and AD in research settings.

Multivariate Assessment of Lipoxidative Metabolites, Trace Biometals, and Antioxidant and Detoxifying Activities in the Cerebrospinal Fluid Define a Fingerprint of Preclinical Stages of Alzheimer's Disease.

BACKGROUND: There exists considerable interest in the identification of molecular traits during early stages of Alzheimer's disease (AD). Mild cognitive impairment (MCI) is considered the closest prodromal stage of AD, and to develop gradually from earlier stages although not always progresses to AD. Classical cerebrospinal fluid (CSF) AD biomarkers, amyloid-ß peptides and tau/p-tau proteins, have been measured in prodromal stages yet results are heterogeneous and far from conclusive. Therefore, there exists a pressing need to identify a neurochemical signature for prodromal stages and to predict which cases might progress to AD. OBJECTIVE: Exploring potential CSF biomarkers related to brain oxidative and inorganic biochemistry during prodromal stages of the disease. METHODS: We have analyzed CSF levels of lipoxidative markers (MDA and 8-isoF2α), biometals (Cu, Zn, Se, Mn, and Fe), iron-transport protein transferrin (TFER), antioxidant enzymes (SOD and GPx4), detoxifying enzymes (GST and BuChE), as well as classical amyloid-ß and total and phosphorylated tau, in cognitively healthy controls, patients with MCI, and subjects exhibiting subjective memory complaints (SMC). RESULTS: Inter-group differences for several variables exhibit differentiable trends along the HC ⟶ SMC ⟶ MCI sequence. More interestingly, the combination of Se, Cu, Zn, SOD, TFER, and GST variables allow differentiable fingerprints for control subjects and each prodromal stage. Further, multivariate scores correlate positively with neurocognitive In-Out test, hence with both episodic memory decline and prediction to dementia. CONCLUSION: We conclude that changes in the CSF biochemistry related to brain oxidative defense and neurometallomics might provide more powerful and accurate diagnostic tools in preclinical stages of AD.

Racial Disparity in Cerebrospinal Fluid Amyloid and Tau Biomarkers and Associated Cutoffs for Mild Cognitive Impairment.

Importance: Prior evidence suggests that racial differences exist in tau biomarkers in mild cognitive impairment (MCI) and Alzheimer disease (AD). Whether this reported disparity is associated with a differential level of neurodegeneration and disease stage or with underlying mechanisms separate from amyloid or tau is unclear. Objectives: To compare cerebrospinal fluid (CSF) biomarkers in African American and white individuals with normal cognition and MCI, to estimate race-based cutoffs for these biomarkers that maximize diagnostic discrimination between normal cognition and MCI, and to study the association of demographic characteristics, cognitive performance, and common vascular risk factors with these differences. Design, Setting, and Participants: This case-control study conducted from March 1, 2016, through January 31, 2019, included participants in the Brain Stress Hypertension and Aging Research Program cohort undergoing baseline assessment. Participants were 50 years or older and recruited from the Atlanta, Georgia, area. Exposures: Self-reported race and cognitive status categorized using modified Petersen criteria and clinical consensus diagnosis. Main Outcomes and Measures: Levels of ß-amyloid 1-42 (Aß1-42), tau, and phosphorylated tau 181 (pTau181), the ratio of tau or pTau181 to Aß1-42, and hippocampal volume on magnetic resonance imaging of the brain. Results: Data from 362 study participants were analyzed (mean [SD] age, 65.6 [7.9] years), of whom 152 (42.0%) were African American, 230 (63.5%) were women, and 189 (52.2%) had MCI. After adjustment for demographic characteristics and cognitive performance, lower mean (SE) levels were observed in African American vs white individuals with MCI for tau (52.40 [5.90] vs 78.98 [5.02] pg/mL; P = .001) and pTau181 (15.42 [2.06] vs 25.24 [1.75] pg/mL; P = .001) and a lower pTau181 to Aß1-42 ratio (0.07 [0.02] vs 0.14 [0.01]; P = .003). There were no racial differences in the normal cognition group or in hippocampal volumes in the MCI group. Cutoffs for CSF biomarkers were higher for Aß1-42 in African American relative to white individuals (208 [95% CI, 126-321] vs 197 [95% CI, 183-245] pg/mL) and lower for tau (51 [95% CI, 31-59] vs 59 [95% CI, 56-92] pg/mL) and pTau181 (12 [95% CI, 12-19] vs 20 [95% CI, 12-27] pg/mL) levels. Cutoffs for the pTau181 to Aß1-42 ratio were 0.05 (95% CI, 0.03-0.12) for African American participants and 0.05 (95% CI, 0.05-0.13) for white participants. Conclusions and Relevance: This study found that African American individuals had lower levels of tau-based biomarkers that were not likely explained by the degree of disease stage or neurodegeneration reflected by hippocampal volumes. This study suggests that race is an important factor when interpreting CSF biomarkers, especially in the clinical diagnosis of prodromal AD. It appears that using the pTau181 to Aß1-42 ratio may ameliorate these differences.

Neuronal injury biomarkers for assessment of the individual cognitive reserve in clinically suspected Alzheimer's disease.

OBJECTIVES: Many predictive or influencing factors have emerged in investigations of the cognitive reserve model of patients with Alzheimer's disease (AD). For example, neuronal injury, which correlates with cognitive decline in AD, can be assessed by [18F]-fluorodeoxyglucose positron-emission-tomography (FDG-PET), structural magnetic resonance imaging (MRI) and total tau in cerebrospinal fluid (CSFt-tau), all according to the A/T/N-classification. The aim of this study was to calculate residual cognitive performance based on neuronal injury biomarkers as a surrogate of cognitive reserve, and to test the predictive value of this index for the individual clinical course. METHODS: 110 initially mild cognitive impaired and demented subjects (age 71 ±â€¯8 years) with a final diagnosis of AD dementia were assessed at baseline by clinical mini-mental-state-examination (MMSE), FDG-PET, MRI and CSFt-tau. All neuronal injury markers were tested for an association with clinical MMSE and the resulting residuals were correlated with years of education. We used multiple regression analysis to calculate the expected MMSE score based on neuronal injury biomarkers and covariates. The residuals of the partial correlation for each biomarker and the predicted residualized memory function were correlated with individual cognitive changes measured during clinical follow-up (27 ±â€¯13 months). RESULTS: FDG-PET correlated highly with clinical MMSE (R = -0.49, p < .01), whereas hippocampal atrophy to MRI (R = -0.15, p = .14) and CSFt-tau (R = -0.12, p = .22) showed only weak correlations. Residuals of all neuronal injury biomarker regressions correlated significantly with education level, indicating them to be surrogates of cognitive reserve. A positive residual was associated with faster cognitive deterioration at follow-up for the residuals of stand-alone FDG-PET (R = -0.36, p = .01) and the combined residualized memory function model (R = -0.35, p = .02). CONCLUSIONS: These findings suggest that subjects with higher cognitive reserve had accumulated more pathology, which subsequently caused a faster cognitive decline over time. Together with previous findings suggesting that higher reserve is associated with slower cognitive decline, we propose a biphasic reserve effect, with an initially protective phase followed by more rapid decompensation once the protection is overwhelmed.

Concordance between the assessment of Aß42, T-tau, and P-T181-tau in peripheral blood neuronal-derived exosomes and cerebrospinal fluid.

INTRODUCTION: Neuronal-derived exosomal Aß42, T-tau, and P-T181-tau have been demonstrated to be biomarkers of Alzheimer's disease (AD). However, no study has assessed the association of Aß42, T-tau, and P-T181-tau between exosomes and CSF. METHODS: This was a multicenter study with two-stage design. The subjects included 28 AD patients, 25 aMCI patients, and 29 controls in the discovery stage; the results of which were confirmed in the validation stage (73 AD, 71 aMCI, and 72 controls). RESULTS: The exosomal concentrations of Aß42, T-tau, and P-T181-tau in AD group were higher than those in aMCI and control groups (all P < .001). The level of each exosomal biomarker was highly correlated with that in CSF. DISCUSSION: This study verified the agreement between CSF and blood exosomal biomarkers and confirmed that exosomal Aß42, T-tau, and P-T181-tau have the same capacity as those in CSF for the diagnosis of AD and aMCI.

In Brief Neuropsychological Assessment, Amnestic Mild Cognitive Impairment (MCI) Is associated with Cerebrospinal Fluid Biomarkers for Cognitive Decline in Contrast to the Prevailing NIA-AA MCI Criterion.

BACKGROUND: In the care of persons with cognitive problems, it is important to use a valid mild cognitive impairment (MCI) criterion that discriminates well between normal and pathological aging. OBJECTIVE: To find the brief neuropsychological screening criterion that best correlates with cerebrospinal fluid (CSF) biomarkers for cognitive decline and dementia in persons seeking help for cognitive problems. METHODS: 452 consecutively recruited patients (age 40-80 years) from memory-clinics in the Norwegian national multicentre longitudinal study Dementia Disease Initiation were included. CSF data as well as full data from brief neuropsychological screening were available for all patients. RESULTS: Amnestic MCI, including at least one memory test below T-score 40, outperformed the conventional US National Institute on Aging-Alzheimer's Association (NIA-AA) MCI criterion. Only amnestic MCI was significantly associated with biomarker pattern of NIA-AA stage 2 (low CSF Aß42 concentrations and elevated tau) in multivariate regression analysis. CONCLUSIONS: The finding that amnestic MCI based on brief neuropsychological assessment is significantly associated with CSF biomarkers for cognitive decline and Alzheimer's disease is in accordance with longitudinal studies that find memory impairment; both in itself and especially in combination with other cognitive deficit to constitute a risk factor for subsequent cognitive decline and dementia. The prevalence of pathological biomarkers for Alzheimer's disease is common in the elderly and the clinical significance of present findings depend on longitudinal validation.

Concordance Between Different Amyloid Immunoassays and Visual Amyloid Positron Emission Tomographic Assessment.

Importance: Visual assessment of amyloid positron emission tomographic (PET) images has been approved by regulatory authorities for clinical use. Several immunoassays have been developed to measure ß-amyloid (Aß) 42 in cerebrospinal fluid (CSF). The agreement between CSF Aß42 measures from different immunoassays and visual PET readings may influence the use of CSF biomarkers and/or amyloid PET assessment in clinical practice and trials. Objective: To determine the concordance between CSF Aß42 levels measured using 5 different immunoassays and visual amyloid PET analysis. Design, Setting, and Participants: The study included 262 patients with mild cognitive impairment or subjective cognitive decline from the Swedish BioFINDER (Biomarkers for Identifying Neurodegenerative Disorders Early and Reliably) cohort (recruited from September 1, 2010, through December 31, 2014) who had undergone flutemetamol F 18 ([18F]flutemetamol)-labeled PET. Levels of CSF Aß42 were analyzed using the classic INNOTEST and the newer modified INNOTEST, fully automated Lumipulse (FL), EUROIMMUN (EI), and Meso Scale Discovery (MSD) assays. Concentrations of CSF Aß were assessed using an antibody-independent mass spectrometry-based reference measurement procedure. Main Outcomes and Measures: The concordance of CSF Aß42 levels and Aß42:Aß40 and Aß42:tau ratios with visual [18F]flutemetamol PET status. Results: Of 262 participants (mean [SD] age, 70.9 [5.5] years), 108 were women (41.2%) and 154 were men (58.8%). The mass spectrometry-derived Aß42 values showed higher correlations with the modified Aß42-INNOTEST (r = 0.97), Aß42-FL (r = 0.93), Aß42-EI (r = 0.93), and Aß42-MSD (r = 0.95) assays compared with the classic Aß42-INNOTEST assay (r = 0.88; P ≤ .01). The signal in the classic Aß42-INNOTEST assay was partly quenched by recombinant Aß1-40 peptide. However, the classic Aß42-INNOTEST assay showed better concordance with visual [18F]flutemetamol PET status (area under the receiver operating characteristic curve [AUC], 0.92) compared with the newer assays (AUCs, 0.87-0.89; P ≤ .01). The accuracies of the newer assays improved significantly when Aß42:Aß40 (AUCs, 0.93-0.95; P ≤ .01), Aß42 to total tau (T-tau) (AUCs, 0.94; P ≤ .05), or Aß42 to phosphorylated tau (P-tau) (AUCs, 0.94-0.95; P ≤ .001) ratios were used. A combination of the Aß42:Aß40 ratio and T-tau or P-tau level did not improve the accuracy compared with the ratio alone. Conclusions and Relevance: Concentrations of CSF Aß42 derived from the new immunoassays (modified INNOTEST, FL, EI, and MSD) may correlate better with the antibody-independent mass spectrometry-based reference measurement procedure and may show improved agreement with visual [18F]flutemetamol PET assessment when using the Aß42:Aß40 or Aß42:tau ratios. These findings suggest the benefit of implementing the CSF Aß42:Aß40 or Aß42:tau ratios as a biomarker of amyloid deposition in clinical practice and trials.

Cost-Utility of Using Alzheimer's Disease Biomarkers in Cerebrospinal Fluid to Predict Progression from Mild Cognitive Impairment to Dementia.

BACKGROUND: Diagnostic research criteria for Alzheimer's disease support the use of biomarkers in the cerebrospinal fluid (CSF) to improve the accuracy of the prognosis regarding progression to dementia for people with mild cognitive impairment (MCI). OBJECTIVE: The aim of this study was to estimate the potential incremental cost-effectiveness ratio of adding CSF biomarker testing to the standard diagnostic workup to determine the prognosis for patients with MCI. METHODS: In an early technology assessment, a mathematical simulation model was built, using available evidence on added prognostic value as well as expert opinion to estimate the incremental costs and quality-adjusted life years (QALYs) of 20,000 virtual MCI patients with (intervention strategy) and without (control strategy) relying on CSF, from a health-care sector perspective and with a 5-year time horizon. RESULTS: Adding the CSF test improved the accuracy of prognosis by 11%. This resulted in an average QALY gain of 0.046 and € 432 additional costs per patient, representing an incremental cost-effectiveness ratio of € 9,416. CONCLUSION: The results show the potential of CSF biomarkers in current practice from a health-economics perspective. This result was, however, marked by a high degree of uncertainty, and empirical research is required into the impact of a prognosis on worrying, false-positive/negative prognosis, and stigmatization.

Combining Cerebrospinal Fluid Biomarkers and Neuropsychological Assessment: A Simple and Cost-Effective Algorithm to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease Dementia.

BACKGROUND: Correctly diagnosing Alzheimer's disease (AD) in prodromal phases would allow the adoption of experimental therapeutic strategies that could selectively interrupt the pathogenetic process before neuronal damage becomes irreversible. Therefore, great efforts have been aimed at finding early reliable disease markers. OBJECTIVE: The aim of this study was to identify a simple, cost effective, and reliable diagnostic algorithm to predict conversion from mild cognitive impairment (MCI) to AD. METHODS: 96 consecutive MCI patients admitted to the Neurology department of San Raffaele Hospital in Milan between January 2009 and January 2015 were included. All patients underwent neuropsychological assessment and lumbar puncture with CSF analysis of amyloid-ß 42 (Aß42), total tau (t-tau), and phosphorylated tau (p-tau) levels. Each patient underwent clinical and neuropsychological follow-up, in order to identify a possible progression from MCI to AD. The mean follow up time was 36.73 months. RESULTS: 37 out of 96 MCI converted to AD during follow up. CSF analysis and neuropsychological assessment reliably detected MCI patients who developed AD. In a subsample of 43 subjects, a Composite Cognitive Score (CCS) was calculated including episodic memory, executive function, and verbal fluency tests. Combining together CSF biomarkers and CCS increased the accuracy of the single predictors, correctly classifying 86% of patients with a specificity of 96% and a Positive Predictive Value of 93%. DISCUSSION: Even if preliminary, our data seem to suggest that CSF analysis and neuropsychological assessment could detect MCI patients who will convert to AD with high confidence. Their relative low cost and availability could make them worldwide essential tools in future clinical trials.

Alzheimer's Disease Assessment Scale-Cognitive subscale variants in mild cognitive impairment and mild Alzheimer's disease: change over time and the effect of enrichment strategies.

BACKGROUND: Development of new treatments for Alzheimer's disease (AD) has broadened into early interventions in individuals with modest cognitive impairment and a slow decline. The 11-item version of the Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog) was originally developed to measure cognition in patients with mild to moderate AD. Attempts to improve its properties for early AD by removing items prone to ceiling and/or by adding cognitive measures known to be impaired early have yielded a number of ADAS-Cog variants. Using Alzheimer's Disease Neuroimaging Initiative data, we compared the performance of the 3-, 5-, 11- and 13-item ADAS-Cog variants in subjects with early AD. Given the interest in enrichment strategies, we also examined this aspect with a focus on cerebrospinal fluid (CSF) markers. METHODS: Subjects with mild cognitive impairment (MCI) and mild AD with available ADAS-Cog 13 and CSF data were analysed. The decline over time was defined by change from baseline. Direct cross-comparison of the ADAS-Cog variants was performed using the signal-to-noise ratio (SNR), with higher values reflecting increased sensitivity to detect change over time. RESULTS: The decline over time on any of the ADAS-Cog variants was minimal in subjects with MCI. Approximately half of subjects with MCI fulfilled enrichment criteria for positive AD pathology. The impact of enrichment was detectable but subtle in MCI. The annual decline in mild AD was more pronounced but still modest. More than 90 % of subjects with mild AD had positive AD pathology. SNRs were low in MCI but greater in mild AD. The numerically largest SNRs were seen for the ADAS-Cog 5 in MCI and for both the 5- and 13-item ADAS-Cog variants in mild AD, although associated confidence intervals were large. CONCLUSIONS: The possible value of ADAS-Cog expansion or reduction is less than compelling, particularly in MCI. In mild AD, adding items known to be impaired at early stages seems to provide more benefit than removing items on which subjects score close to ceiling.

Assessment of CSF Aß42 as an aid to discriminating Alzheimer's disease from other dementias and mild cognitive impairment: a meta-analysis of 50 studies.

Mild Alzheimer's disease (AD) is usually difficult to differentiate from other dementias or mild cognitive impairment (MCI). The aim of our study is to evaluate the clinical importance of cerebrospinal fluid (CSF) ß-amyloid 42 (Aß42) in MCI, AD and other dementias, more specifically: frontotemporal dementia (FTD), dementia with Lewy bodies (DLB), Parkinson's disease (PD) with dementia (PDD) and vascular dementia (VaD). Fifty eligible articles were identified by search of databases including PubMed, EMBASE, Elsevier, Springer Link and the Cochrane Library, from January 1990 to May 2014. The random effects model was used to calculate the standardized mean difference (SMD) with corresponding 95% CI by STATA 9.0 software. The subgroup analyses were made on the method (ELISA, xMAP). We found that CSF Aß42 concentrations were significantly lower in AD compared to MCI (SMD: -0.68, 95% CI: [-0.80, -0.56], z=11.34, P<0.001), FTD (SMD: -1.09, 95% CI: [-1.41, -0.76], z=6.62, P<0.001), PDD (SMD: -0.75, 95% CI: [-1.39, -0.10], z=2.27, P=0.023), VaD (SMD: -0.95, 95% CI: [-1.30, -0.61], z=5.43, P<0.001). In addition, compared to DLB, Aß42 concentrations are moderately lower in AD (SMD: -0.27, 95% CI: [-0.51, -0.03], z=2.20, P=0.028). Results from this meta-analysis hinted that CSF Aß42 is a good biomarker for discriminating Alzheimer's disease from other dementias and MCI.

Monte Carlo feature selection and rule-based models to predict Alzheimer's disease in mild cognitive impairment.

The objective of the present study was to evaluate a Monte Carlo feature selection (MCFS) and rough set Rosetta pipeline for generating rule-based models as a tool for comprehensive risk estimates for future Alzheimer's disease (AD) in individual patients with mild cognitive impairment (MCI). Risk estimates were generated on the basis of age, gender, Mini-Mental State Examination scores, apolipoprotein E (APOE) genotype and the cerebrospinal fluid (CSF) biomarkers total tau (T-tau), phospho-tau(181) (P-tau) and the 42 amino acid form of amyloid ß (Aß42) in two sets of longitudinally followed MCI patients (n = 217 in total). The predictive model was created in Rosetta, evaluated with the standard tenfold cross-validation approach and tested on an external set. Features were ranked and selected by the MCFS algorithm. Using the combined pipeline of MCFS and Rosetta, it was possible to predict AD among patients with MCI with an area under the receiver operating characteristics curve of 0.92. Risk estimates were produced for the individual patients and showed good correlation with actual diagnosis in cross validation, and on an external dataset from a new study. Analysis of the importance of attributes showed that the biochemical CSF markers contributed the most to the predictions, and that added value was gained by combining several biochemical markers. Despite a correlation with the biochemical markers, the genetic marker APOE ε4 did not contribute to the predictive power of the model.