Subtypes Based on Neuropsychological Performance Predict Incident Dementia: Findings from the Rush Memory and Aging Project

Post-Hoc Assessment of Cognitive Efficacy in Alzheimer's Disease Using a Latent Growth Mixture Model in AMBAR, a Phase 2B Randomized Controlled Trial

BACKGROUND

Disease progression in Alzheimer's Dementia (AD) is typically characterized by accelerated cognitive and functional decline, where heterogeneous trajectories can impact the observed treatment response.

METHODS

We hypothesized that unobserved heterogeneity could obscure treatment benefits in AD. The effect of unobserved heterogeneity was empirically quantified within the Alzheimer's Management By Albumin Replacement (AMBAR) phase 2b trial data. The ADAS-Cog 12 cognition endpoint was reanalyzed in a 2-class latent growth mixture model initially fit to the treatment arm. The model with the best fit was then applied across both treatment arms to a larger (n=1000) simulated dataset that was representative of AMBAR trial cognitive data.

RESULTS

Two classes of patients were observed: a stable cognitive trajectory class and a highly variable class. Removal of the latter (n=48, 22%) from the analysis and refitting efficacy models comparing the stable class to full placebo yielded significant treatment efficacy on cognition (p=0.007, Cohen's D=-0.4). Comparison of the stable class of each arm within the simulated dataset revealed a significant difference in treatment efficacy favoring the simulated stable treatment arm.

CONCLUSION

This post hoc exploratory analysis suggests that prespecified strategies for addressing unobserved heterogeneity may yield improved effect detection in AD trials. The generalizability of the analytic strategy is limited by latent stratification in only the treatment arm, a requirement given the small placebo arm in AMBAR. This limitation was partially addressed by the simulation modeling.

The Influence of Cerebrovascular Pathology on Cluster Analysis of Neuropsychological Scores in Patients With Mild Cognitive Impairment

OBJECTIVES

The diagnostic entity of mild cognitive impairment (MCI) is heterogeneous, highlighting the need for data-driven classification approaches to identify patient subgroups. However, these approaches can be strongly determined by sample characteristics and selected measures. Here, we applied a cluster analysis to an MCI patient database from a neuropsychology clinic to determine whether the inclusion of patients with MCI with vascular pathology would result in a different classification of subgroups.

METHODS

Participants diagnosed with MCI (n = 166), vascular cognitive impairment-no dementia (n = 26), and a group of older adults with subjective cognitive concerns but no objective impairment (n = 144) were assessed using a full neuropsychological battery and other clinical measures. Cognitive measures were analyzed using a hierarchical cluster analysis and then a k-means approach, with resulting clusters compared on a range of demographic and clinical variables.

RESULTS

We found a 4-factor solution: a cognitively intact cluster, a globally impaired cluster, an amnestic/visuospatial impairment cluster, and a mild, mixed-domain cluster. Interestingly, group differences in self-reported multilingualism emerged in the derived clusters that were not observed when comparing diagnostic groups.

CONCLUSIONS

Our results were generally consistent with previous studies using cluster analysis in MCI. Including patients with primarily cerebrovascular disease resulted in subtle differences in the derived clusters and revealed new insights into shared cognitive profiles of patients beyond diagnostic categories. These profiles should be further explored to develop individualized assessment and treatment approaches.

Comparing Performance of Different Predictive Models in Estimating Disease Progression in Alzheimer Disease

BACKGROUND

Automatic classification techniques provide tools to analyze complex data and predict disease progression.

METHODS

A total of 305 cognitively normal; 475 patients with amnestic mild cognitive impairment (aMCI); and 162 patients with dementia were included in this study. We compared the performance of 3 different methods in predicting progression from aMCI to dementia: (1) index-based model; (2) logistic regression (LR); and (3) ensemble linear discriminant (ELD) machine learning models. LR and ELD models were trained using data from cognitively normal and dementia subgroups, and subsequently were applied to aMCI subgroup to predict their disease progression.

RESULTS

Performance of ELD models were better than LR models in prediction of conversion from aMCI to Alzheimer dementia at all time frames. ELD models performed better when a larger number of features were used for prediction.

CONCLUSION

Machine learning models have substantial potential to improve the predictive ability for cognitive outcomes.

Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials

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 would also respond to the therapeutic intervention.

Objective

To investigate if predictive models can be an effective tool for identifying and excluding people unlikely to show cognitive decline as an enrichment strategy in AD trials.

Method

We used data from the placebo arms of two phase 3, double-blind trials, EXPEDITION and EXPEDITION2. Patients had 18 months of follow-up. Based on the longitudinal data from the placebo arm, we classified participants into two groups: one showed cognitive decline (any negative slope) and the other showed no cognitive decline (slope is zero or positive) on the Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-cog). We used baseline data for EXPEDITION to train regression-based classifiers and machine learning classifiers to estimate probability of cognitive decline. Models were applied to EXPEDITION2 data to assess predicted performance in an independent sample. Features used in predictive models included baseline demographics, apolipoprotein E ε4 genotype, neuropsychological scores, functional scores, and volumetric magnetic resonance imaging.

Result

In EXPEDITION, 46.3% of placebo-treated patients showed no cognitive decline and the proportion was similar in EXPEDITION2 (45.6%). Models had high sensitivity and modest specificity in both the training (EXPEDITION) and replication samples (EXPEDITION2) for detecting the stable group. Positive predictive value of models was higher than the base prevalence of cognitive decline, and negative predictive value of models were higher than the base rate of participants who had stable cognition.

Conclusion

Excluding persons with AD unlikely to decline from the active and placebo arms of clinical trials using predictive models may boost the power of AD trials through selective inclusion of participants expected to decline.

Diagnosing Mild Cognitive Impairment Among Racially Diverse Older Adults: Comparison of Consensus, Actuarial, and Statistical Methods

BACKGROUND

Actuarial and statistical methods have been proposed as alternatives to conventional methods of diagnosing mild cognitive impairment (MCI), with the aim of enhancing diagnostic and prognostic validity, but have not been compared in racially diverse samples.

OBJECTIVE

We compared the agreement of consensus, actuarial, and statistical MCI diagnostic methods, and their relationship to race and prognostic indicators among diverse older adults.

METHODS

Participants (N = 354; M age = 71; 68% White, 29% Black) were diagnosed with MCI or normal cognition (NC) according to clinical consensus, actuarial neuropsychological criteria (Jak/Bondi), and latent class analysis (LCA). We examined associations with race/ethnicity, longitudinal cognitive and functional change, and incident dementia.

RESULTS

MCI rates by consensus, actuarial criteria, and LCA were 44%, 53%, and 41%, respectively. LCA identified three MCI subtypes (memory; memory/language; memory/executive) and two NC classes (low normal; high normal). Diagnostic agreement was substantial, but agreement of the actuarial method with consensus and LCA was weaker than the agreement between consensus and LCA. Among cases classified as MCI by actuarial criteria only, Black participants were over-represented, and outcomes were generally similar to those of NC participants. Consensus diagnoses best predicted longitudinal outcomes overall, whereas actuarial diagnoses best predicted longitudinal functional change among Black participants.

CONCLUSION

Consensus diagnoses optimize specificity in predicting dementia, but among Black older adults, actuarial diagnoses may be more sensitive to early signs of decline. Results highlight the need for cross-cultural validity in MCI diagnosis and should be explored in community- and population-based samples.

Latent Cognitive Class at Enrollment Predicts Future Cognitive Trajectories of Decline in a Community Sample of Older Adults

BACKGROUND

Methods that can identify subgroups with different trajectories of cognitive decline are crucial for isolating the biologic mechanisms which underlie these groupings.

OBJECTIVE

This study grouped older adults based on their baseline cognitive profiles using a latent variable approach and tested the hypothesis that these groups would differ in their subsequent trajectories of cognitive change.

METHODS

In this study we applied time-varying effects models (TVEMs) to examine the longitudinal trajectories of cognitive decline across different subgroups of older adults in the Rush Memory and Aging Project.

RESULTS

A total of 1,662 individuals (mean age = 79.6 years, SD = 7.4, 75.4%female) participated in the study; these were categorized into five previously identified classes of older adults differing in their baseline cognitive profiles: Superior Cognition (n = 328, 19.7%), Average Cognition (n = 767, 46.1%), Mixed-Domains Impairment (n = 71, 4.3%), Memory-Specific Impairment (n = 274, 16.5%), and Frontal Impairment (n = 222, 13.4%). Differences in the trajectories of cognition for these five classes persisted during 8 years of follow-up. Compared with the Average Cognition class, The Mixed-Domains and Memory-Specific Impairment classes showed steeper rates of decline, while other classes showed moderate declines.

CONCLUSION

Baseline cognitive classes of older adults derived through the use of latent variable methods were associated with distinct longitudinal trajectories of cognitive decline that did not converge during an average of 8 years of follow-up.

Using Mixture Modeling to Construct Subgroups of Cognitive Aging in the Wisconsin Longitudinal Study

OBJECTIVES

Longitudinal surveys of older adults increasingly incorporate assessments of cognitive performance. However, very few studies have used mixture modeling techniques to describe cognitive aging, identifying subgroups of people who display similar patterns of performance across discrete cognitive functions. We employ this approach to advance empirical evidence concerning interindividual variability and intraindividual change in patterns of cognitive aging.

METHOD

We drew upon data from 3,713 participants in the Wisconsin Longitudinal Study (WLS). We used latent class analysis to generate subgroups of cognitive aging based on assessments of verbal fluency and episodic memory at ages 65 and 72. We also employed latent transition analysis to identify how individual participants moved between subgroups over the 7-year period.

RESULTS

There were 4 subgroups at each point in time. Approximately 3 quarters of the sample demonstrated continuity in the qualitative type of profile between ages 65 and 72, with 17.9% of the sample in a profile with sustained overall low performance at both ages 65 and 72. An additional 18.7% of participants made subgroup transitions indicating marked decline in episodic memory.

DISCUSSION

Results demonstrate the utility of using mixture modeling to identify qualitatively and quantitatively distinct subgroups of cognitive aging among older adults. We discuss the implications of these results for the continued use of population health data to advance research on cognitive aging.

A Latent Transition Analysis Model to Assess Change in Cognitive States over Three Occasions: Results from the Rush Memory and Aging Project

BACKGROUND

Conceptualizing cognitive aging as a step-sequential process is useful in identifying particular stages of cognitive function and impairment.

OBJECTIVE

We applied latent transition analysis (LTA) to determine 1) whether the underlying structure of cognitive profiles found at every measurement occasion are uniform across three waves of assessment, 2) whether class-instability is predictive of distal outcomes, and 3) whether class-reversions from impaired to non-impaired using latent modelling is lower than when using clinical criteria of mild cognitive impairment (MCI).

METHODS

A mover-stayer LTA model with dementia as a distal outcome was specified to model transitions of ten neuropsychological measures over three annual waves in the Rush Memory and Aging Project (n = 1,661). The predictive validity of the mover-stayer status for incident Alzheimer's disease (AD) was then assessed.

RESULTS

We identified a five-class model across the three time-points: Mixed-Domain Impairment, Memory-Specific Impairment, Frontal Impairment, Average, and Superior Cognition. None of the individuals in the Impairment classes reverted to the Average or Superior classes. Conventional MCI classification identified 26.4% and 14.1% at Times 1 and 2 as false-positive cases. "Movers" had 87% increased risk of developing dementia compared to those classified as "Stayers".

CONCLUSION

Our findings support the use of latent variable modelling that incorporates comprehensive neuropsychological assessment to identify and classify cognitive impairment.

Detecting biological heterogeneity patterns in ADNI amnestic mild cognitive impairment based on volumetric MRI

There is substantial biological heterogeneity among older adults with amnestic mild cognitive impairment (aMCI). We hypothesized that this heterogeneity can be detected solely based on volumetric MRI measures, which potentially have clinical implications and can improve our ability to predict clinical outcomes. We used latent class analysis (LCA) to identify subgroups among persons with aMCI (n = 696) enrolled in the Alzheimer's Disease Neuroimaging Initiative (ADNI), based on baseline volumetric MRI measures. We used volumetric measures of 10 different brain regions. The subgroups were validated with respect to demographics, cognitive performance, and other AD biomarkers. The subgroups were compared with each other and with normal and Alzheimer's disease (AD) groups with respect to baseline cognitive function and longitudinal rate of conversion. Four aMCI subgroups emerged with distinct MRI patterns: The first subgroup (n = 404), most similar to normal controls in volumetric characteristics and cognitive function, had the lowest incidence of AD. The second subgroup (n = 230) had the most similar MRI profile to early AD, along with poor performance in memory and executive function domains. The third subgroup (n = 36) had the highest global atrophy, very small hippocampus and worst overall cognitive performance. The fourth subgroup (n = 26) had the least amount of atrophy, however still had poor cognitive function specifically in in the executive function domain. Individuals with aMCI who were clinically categorized within one group other showed substantial heterogeneity based on MRI volumetric measures.

Associations Between Air Pollution Exposure and Empirically Derived Profiles of Cognitive Performance in Older Women

BACKGROUND

Elucidating associations between exposures to ambient air pollutants and profiles of cognitive performance may provide insight into neurotoxic effects on the aging brain.

OBJECTIVE

We examined associations between empirically derived profiles of cognitive performance and residential concentrations of particulate matter of aerodynamic diameter < 2.5 (PM2.5) and nitrogen dioxide (NO2) in older women.

METHOD

Women (N = 2,142) from the Women's Health Initiative Study of Cognitive Aging completed a neuropsychological assessment measuring attention, visuospatial, language, and episodic memory abilities. Average yearly concentrations of PM2.5 and NO2 were estimated at the participant's addresses for the 3 years prior to the assessment. Latent profile structural equation models identified subgroups of women exhibiting similar profiles across tests. Multinomial regressions examined associations between exposures and latent profile classification, controlling for covariates.

RESULT

Five latent profiles were identified: low performance across multiple domains (poor multi-domain; n = 282;13%), relatively poor verbal episodic memory (poor memory; n = 216; 10%), average performance across all domains (average multi-domain; n = 974; 45%), superior memory (n = 381; 18%), and superior attention (n = 332; 15%). Using women with average cognitive ability as the referent, higher PM2.5 (per interquartile range [IQR] = 3.64μg/m3) was associated with greater odds of being classified in the poor memory (OR = 1.29; 95% Confidence Interval [CI] = 1.10-1.52) or superior attention (OR = 1.30; 95% CI = 1.10-1.53) profiles. NO2 (per IQR = 9.86 ppb) was associated with higher odds of being classified in the poor memory (OR = 1.38; 95% CI = 1.17-1.63) and lower odds of being classified with superior memory (OR = 0.81; 95% CI = 0.67-0.97).

CONCLUSION

Exposure to PM2.5 and NO2 are associated with patterns of cognitive performance characterized by worse verbal episodic memory relative to performance in other domains.

Extensive memory testing improves prediction of progression to MCI in late middle age

INTRODUCTION

Predicting risk for Alzheimer's disease when most people are likely still biomarker negative would aid earlier identification. We hypothesized that combining multiple memory tests and scores in middle-aged adults would provide useful, and non-invasive, prediction of 6-year progression to MCI.

METHODS

We examined 849 men who were cognitively normal at baseline (mean age ± SD = 55.69 ± 2.45).

RESULTS

California Verbal Learning Test learning trials was the best individual predictor of amnestic MCI (OR = 4.75). A latent factor incorporating seven measures across three memory tests provided much stronger prediction (OR = 9.88). This compared favorably with biomarker-based prediction in a study of much older adults.

DISCUSSION

Neuropsychological tests are sensitive and early indicators of MCI risk at an age when few individuals are likely to have yet become biomarker positive. The single best measures may appear time- and cost-effective, but 30 additional minutes of testing and use of multiple scores within tests provide substantially improved prediction.

Machine Learning Predictive Models Can Improve Efficacy of Clinical Trials for Alzheimer's Disease

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.

Neuropsychological latent classes at enrollment and postmortem neuropathology

INTRODUCTION

We classified individuals based on their baseline performance on cognitive measures and investigated the association between cognitive classifications and neuropathological findings ∼7 years later, as an external validator.

METHODS

Brain autopsies of 779 decedents were examined. Baseline latent class analysis on 10 neuropsychological measures was previously assigned: mixed-domains impairment (n = 39, 5%), memory-specific impairment (n = 210, 27%), frontal impairment (n = 113, 14.5%), average cognition (n = 360, 46.2%), and superior cognition (n = 57, 7.3%). Linear regressions and risks ratios were used to examine the relation of latent class assignment at enrollment with neuropathological indices.

RESULTS

Amyloid β, tau, and transactive response DNA-binding protein 43 were associated with mixed-domains impairment and memory-specific impairment classes ∼7 years before death. Moderate arteriolosclerosis was associated with membership in the frontal impairment class.

DISCUSSION

Our findings support the use of latent class models that incorporate more comprehensive neuropsychological measures to classify cognitive impairment.