Search

Background: Blood-based biomarkers (BBMs) are of growing interest in the field of Alzheimer's disease (AD) and related dementias. Objective: This study aimed to assess the ability of plasma biomarkers to 1) predict disease progression from mild cognitive impairment (MCI) to dementia and 2) improve the predictive ability of magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) measures when combined. Methods: We used data from the Alzheimer's Disease Neuroimaging Initiative. Machine learning models were trained using the data from participants who remained cognitively stable (CN-s) and with Dementia diagnosis at 2-year follow-up visit. The models were used to predict progression to dementia in MCI individuals. We assessed the performance of models with plasma biomarkers against those with CSF and MRI measures, and also in combination with them. Results: Our models with plasma biomarkers classified CN-s individuals from AD with an AUC of 0.75±0.03 and could predict conversion to dementia in MCI individuals with an AUC of 0.64±0.03 (17.1% BP, base prevalence). Models with plasma biomarkers performed better when combined with CSF and MRI measures (CN versus AD: AUC of 0.89±0.02; MCI-to-AD: AUC of 0.76±0.03, 21.5% BP). Conclusions: Our results highlight the potential of plasma biomarkers in predicting conversion to dementia in MCI individuals. While plasma biomarkers could improve the predictive ability of CSF and MRI measures when combined, they also show the potential to predict non-progression to AD when considered alone. The predictive ability of plasma biomarkers is crucially linked to reducing the costly and effortful collection of CSF and MRI measures. [ABSTRACT FROM AUTHOR]

Background: Depression is a late-life risk factor for cognitive decline. Evidence suggests an association between Alzheimer's disease (AD) associated pathologic changes and depressive symptoms.Objective: To investigate the influence of AT(N) biomarker profile (amyloid-β [A], p-tau [T], and neurodegeneration [N]) and gender on cross-sectional associations between subclinical depressive symptoms and cognitive function among older adults without dementia.Methods: Participants included 868 individuals without dementia from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Depressive symptoms were measured using the Geriatric Depression Scale (GDS). ADNI neuropsychological composite scores assessed memory and executive function (EF). PET, cerebrospinal fluid, and MRI modalities classified the study sample into biomarker profiles: normal biomarkers (A-T-N-), AD continuum (A+T±N±), and suspect non-AD pathology (SNAP; A-T±N-or A-T-N±). Multivariate regression models were used to investigate associations between GDS and cognitive domains.Results: GDS was negatively associated with memory (β= -0.156, p < 0.001) and EF (β= -0.147, p < 0.001) in the whole sample. When classified by biomarker profile, GDS was negatively associated with memory and EF in AD continuum (memory: β= -0.174, p < 0.001; EF: β= -0.129 p = 0.003) and SNAP (memory: β= -0.172, p = 0.005; EF: β= -0.197, p = 0.001) subgroups. When stratified by sex, GDS was negatively associated with memory (β= -0.227, p < 0.001) and EF (β= -0.205, p < 0.001) in men only.Conclusion: The association between subclinical depressive symptoms and cognitive function is highly influenced by the AT(N) biomarker profile. [ABSTRACT FROM AUTHOR]

Background: The ideal participants for Alzheimer's disease (AD) clinical trials would show cognitive decline in the absence of treatment (i.e., placebo arm) and also would be responsive to the therapeutic intervention being studied (i.e., drug arm). One strategy to boost the power of trials is to enroll individuals who are more likely to progress targeted using data-driven predictive models.Objective: To investigate if machine learning (ML) models can effectively predict clinical disease progression (cognitive decline) in mild-to-moderate AD patients during the timeframe of a phase III clinical trial.Methods: Data from 202 participants with a diagnosis of AD at baseline from the Alzheimer's Disease Neuroimaging Initiative (ADNI) was used to train ML classifiers that can differentiate between individuals who had declining cognitive function (DC) and individuals with stable cognitive function (SC). DC was defined as any downward change in the Alzheimer's Disease Assessment Scale cognitive subscale (ADAS-cog) score over 12 months of follow-up. SC was defined by the absence of decline in ADAS-cog. Trained models were applied to data from 77 participants from the placebo arm of the phase III trial of Semagacestat (LFAN study) to identify subgroups of SC versus DC.Results: Only 74.8% of ADNI participants and 63.6% of LFAN participants had cognitive decline after one year of follow up. K-nearest neighbors (kNN) classifier had an accuracy of 68.3%, sensitivity of 80.1%, and specificity of 33.3% for identifying decliners in ADNI (training sample). In LFAN (validation sample), the model showed an overall accuracy of 61.3%, sensitivity of 65.5%, and specificity of 47.0% in identifying decliners at the 12 months of follow-up. The model had a positive predictive value of 80.8%, which was 17.2% more than the base prevalence of decliners.Conclusions: Machine learning predictive models can be effectively used to boost the power of clinical trials by reducing the sample size. [ABSTRACT FROM AUTHOR]

Background: Amyloid-β positivity (Aβ+) based on PET imaging is part of the enrollment criteria for many of the clinical trials of Alzheimer's disease (AD), particularly in trials for amyloid-targeted therapy. Predicting Aβ positivity prior to PET imaging can decrease unnecessary patient burden and costs of running these trials.Objective: The aim of this study was to evaluate the performance of a machine learning model in estimating the individual risk of Aβ+ based on gold-standard of PET imaging.Methods: We used data from an amnestic mild cognitive impairment (aMCI) subset of the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to develop and validate the models. The predictors of Aβ status included demographic and ApoE4 status in all models plus a combination of neuropsychological tests (NP), MRI volumetrics, and cerebrospinal fluid (CSF) biomarkers.Results: The models that included NP and MRI measures separately showed an area under the receiver operating characteristics (AUC) of 0.74 and 0.72, respectively. However, using NP and MRI measures jointly in the model did not improve prediction. The models including CSF biomarkers significantly outperformed other models with AUCs between 0.89 to 0.92.Conclusions: Predictive models can be effectively used to identify persons with aMCI likely to be amyloid positive on a subsequent PET scan. [ABSTRACT FROM AUTHOR]

Background: Predicting clinical course of cognitive decline can boost clinical trials' power and improve our clinical decision-making. Machine learning (ML) algorithms are specifically designed for the purpose of prediction; however. identifying optimal features or algorithms is still a challenge.Objective: To investigate the accuracy of different ML methods and different features to classify cognitively normal (CN) individuals from Alzheimer's disease (AD) and to predict longitudinal outcome in participants with mild cognitive impairment (MCI).Methods: A total of 1,329 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were included: 424 CN, 656 MCI, and 249 AD individuals. Four feature-sets at baseline (hippocampal volume and volume of 47 cortical and subcortical regions with and without demographics and APOE4) and six machine learning methods (decision trees, support vector machines, K-nearest neighbor, ensemble linear discriminant, boosted trees, and random forests) were used to classify participants with normal cognition from participants with AD. Subsequently the model with best classification performance was used for predicting clinical outcome of MCI participants.Results: Ensemble linear discriminant models using demographics and all volumetric magnetic resonance imaging measures as feature-set showed the best performance in classification of CN versus AD participants (accuracy = 92.8%, sensitivity = 95.8%, and specificity = 88.3%). Prediction accuracy of future conversion from MCI to AD for this ensemble linear discriminant at 6, 12, 24, 36, and 48 months was 63.8% (sensitivity = 74.4, specificity = 63.1), 68.9% (sensitivity = 75.9, specificity = 67.8), 74.9% (sensitivity = 71.5, specificity = 76.3), 75.3%, (sensitivity = 65.2, specificity = 79.7), and 77.0% (sensitivity = 59.6, specificity = 86.1), respectively.Conclusions: Machine learning models trained for classification of CN versus AD can improve our prediction ability of MCI conversion to AD. [ABSTRACT FROM AUTHOR]

Background: In a previous report, we used latent class analysis (LCA) to identify natural subgroups of older adults in the Einstein Aging Study (EAS) based on neuropsychological performance. These subgroups differed in demographics, genetic profile, and prognosis. Herein, we assess the generalizability of these findings to an independent sample, the Rush Memory and Aging Project (MAP), which used an overlapping, but distinct neuropsychological battery.Objective: Our aim was to identify the association of natural subgroups based on neuropsychological performance in the MAP cohort with incident dementia and compare them with the associations identified in the EAS.Methods: MAP is a community-dwelling cohort of older adults living in the northeastern Illinois, Chicago. Latent class models were applied to baseline scores of 10 neuropsychological measures across 1,662 dementia-free MAP participants. Results were compared to prior findings from the EAS.Results: LCA resulted in a 5-class model: Mixed-Domain Impairment (n = 71, 4.3%), Memory-specific-Impairment (n = 274, 16.5%), Average (n = 767, 46.1%), Frontal Impairment (n = 222, 13.4%), and a class of Superior Cognition (n = 328, 19.7%). Similar to the EAS, the Mixed-Domain Impairment, the Memory-Specific Impairment, and the Frontal Impairment classes had higher risk of incident Alzheimer's disease when compared to the Average class. By contrast, the Superior Cognition had a lower risk of Alzheimer's disease when compared to the Average class.Conclusions: Natural cognitive subgroups in MAP are similar to those identified in EAS. These similarities, despite study differences in geography, sampling strategy, and cognitive tests, suggest that LCA is capable of identifying classes that are not limited to a single sample or a set of cognitive tests. [ABSTRACT FROM AUTHOR]

There is a growing recognition of sex differences in Alzheimer's disease (AD). Females show an advantage over males on tests of verbal memory, which are used to diagnose AD and its precursor, amnestic mild cognitive impairment (aMCI). Women retain this advantage in aMCI despite reduced hippocampal volume and temporal lobe glucose metabolism. Here we examined whether this female advantage endures despite evidence of AD-specific pathology, cortical amyloid-β (Aβ) deposition measured with [18F]AV45 (florbetapir) positron emission tomography. Participants with normal cognition (N = 304), aMCI (N = 515), and AD dementia (N = 175) were drawn from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Across and within diagnostic groups, we conducted linear regressions to examine the interaction of sex with cortical Aβ burden on immediate and delayed recall on the Rey Auditory Verbal Learning Test (RAVLT) adjusting for age, education, and APOE4. In the overall group, sex by cortical Aβ interaction was significant for delayed recall only. Overall, delayed recall performance was significantly better in women versus men among those with low to moderate Aβ burden, but women and men performed similarly among those with high Aβ burden. In diagnosis-stratified analyses, a significant sex by cortical Aβ interaction was observed for delayed recall in the aMCI group, but not in the normal or AD dementia groups. Thus, women maintain a verbal memory advantage over men in aMCI despite similar levels of AD pathology. Although this advantage may benefit women by delaying verbal memory impairment until more advanced pathology, it may also delay diagnosis of aMCI and treatment intervention. [ABSTRACT FROM AUTHOR]

Background: Education and occupational complexity are main sources of mental engagement during early life and adulthood respectively, but research findings are not conclusive regarding protective effects of these factors against late-life dementia., Objective: This project aimed to examine the unique contributions of education and occupational complexity to incident dementia, and to assess the mediating effects of occupational complexity on the association between education and dementia across diverse cohorts., Method: We used data from 10,195 participants (median baseline age = 74.1, range = 58∼103), representing 9 international datasets from 6 countries over 4 continents. Using a coordinated analysis approach, the accelerated failure time model was applied to each dataset, followed by meta-analysis. In addition, causal mediation analyses were performed., Result: The meta-analytic results indicated that both education and occupational complexity were independently associated with increased dementia-free survival time, with 28%of the effect of education mediated by occupational complexity. There was evidence of threshold effects for education, with increased dementia-free survival time associated with 'high school completion' or 'above high school' compared to 'middle school completion or below'., Conclusion: Using datasets from a wide range of geographical regions, we found that both early life education and adulthood occupational complexity were independently predictive of dementia. Education and occupational experiences occur during early life and adulthood respectively, and dementia prevention efforts could thus be made at different stages of the life course.

There is a growing recognition of sex differences in Alzheimer's disease (AD). Females show an advantage over males on tests of verbal memory, which are used to diagnose AD and its precursor, amnestic mild cognitive impairment (aMCI). Women retain this advantage in aMCI despite reduced hippocampal volume and temporal lobe glucose metabolism. Here we examined whether this female advantage endures despite evidence of AD-specific pathology, cortical amyloid-β (Aβ) deposition measured with [18F]AV45 (florbetapir) positron emission tomography. Participants with normal cognition (N = 304), aMCI (N = 515), and AD dementia (N = 175) were drawn from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Across and within diagnostic groups, we conducted linear regressions to examine the interaction of sex with cortical Aβ burden on immediate and delayed recall on the Rey Auditory Verbal Learning Test (RAVLT) adjusting for age, education, and APOE4. In the overall group, sex by cortical Aβ interaction was significant for delayed recall only. Overall, delayed recall performance was significantly better in women versus men among those with low to moderate Aβ burden, but women and men performed similarly among those with high Aβ burden. In diagnosis-stratified analyses, a significant sex by cortical Aβ interaction was observed for delayed recall in the aMCI group, but not in the normal or AD dementia groups. Thus, women maintain a verbal memory advantage over men in aMCI despite similar levels of AD pathology. Although this advantage may benefit women by delaying verbal memory impairment until more advanced pathology, it may also delay diagnosis of aMCI and treatment intervention.

Research increasingly suggests that subjective cognitive decline (SCD) in older adults, in the absence of objective cognitive dysfunction or depression, may be a harbinger of non-normative cognitive decline and eventual progression to dementia. Little is known, however, about the key features of self-report measures currently used to assess SCD. The Subjective Cognitive Decline Initiative (SCD-I) Working Group is an international consortium established to develop a conceptual framework and research criteria for SCD (Jessen et al., 2014, Alzheimers Dement 10, 844-852). In the current study we systematically compared cognitive self-report items used by 19 SCD-I Working Group studies, representing 8 countries and 5 languages. We identified 34 self-report measures comprising 640 cognitive self-report items. There was little overlap among measures- approximately 75% of measures were used by only one study. Wide variation existed in response options and item content. Items pertaining to the memory domain predominated, accounting for about 60% of items surveyed, followed by executive function and attention, with 16% and 11% of the items, respectively. Items relating to memory for the names of people and the placement of common objects were represented on the greatest percentage of measures (56% each). Working group members reported that instrument selection decisions were often based on practical considerations beyond the study of SCD specifically, such as availability and brevity of measures. Results document the heterogeneity of approaches across studies to the emerging construct of SCD. We offer preliminary recommendations for instrument selection and future research directions including identifying items and measure formats associated with important clinical outcomes.