A 'Framingham-like' Algorithm for Predicting 4-Year Risk of Progression to Amnestic Mild Cognitive Impairment or Alzheimer's Disease Using Multidomain Information

Risk Models Based on Non-Cognitive Measures May Identify Presymptomatic Alzheimer's Disease

BACKGROUND

Alzheimer's disease (AD) is a progressive disorder without a cure. Develop risk prediction models for detecting presymptomatic AD using non-cognitive measures is necessary to enable early interventions.

OBJECTIVE

Examine if non-cognitive metrics alone can be used to construct risk models to identify adults at risk for AD dementia and cognitive impairment.

METHODS

Clinical data from older adults without dementia from the Memory and Aging Project (MAP, n = 1,179) and Religious Orders Study (ROS, n = 1,103) were analyzed using Cox proportional hazard models to develop risk prediction models for AD dementia and cognitive impairment. Models using only non-cognitive covariates were compared to models that added cognitive covariates. All models were trained in MAP, tested in ROS, and evaluated by the AUC of ROC curve.

RESULTS

Models based on non-cognitive covariates alone achieved AUC (0.800,0.785) for predicting AD dementia (3.5) years from baseline. Including additional cognitive covariates improved AUC to (0.916,0.881). A model with a single covariate of composite cognition score achieved AUC (0.905,0.863). Models based on non-cognitive covariates alone achieved AUC (0.717,0.714) for predicting cognitive impairment (3.5) years from baseline. Including additional cognitive covariates improved AUC to (0.783,0.770). A model with a single covariate of composite cognition score achieved AUC (0.754,0.730).

CONCLUSION

Risk models based on non-cognitive metrics predict both AD dementia and cognitive impairment. However, non-cognitive covariates do not provide incremental predictivity for models that include cognitive metrics in predicting AD dementia, but do in models predicting cognitive impairment. Further improved risk prediction models for cognitive impairment are needed.

Categorical predictive and disease progression modeling in the early stage of Alzheimer's disease

BACKGROUND

A preclinical stage of Alzheimer's disease (AD) precedes the symptomatic phases of mild cognitive impairment (MCI) and dementia, which constitutes a window of opportunities for preventive therapies or delaying dementia onset.

NEW METHOD

We propose to use categorical predictive models based on survival analysis with longitudinal data which are capable of determining subsets of markers to classify cognitively unimpaired (CU) subjects who progress into MCI/dementia or not. Subsequently, the proposed combination of markers was used to construct disease progression models (DPMs), which reveal long-term pathological trajectories from short-term clinical data. The proposed methodology was applied to a population recruited by the ADNI.

RESULTS

A very small subset of standard MRI-based data, CSF markers and cognitive measures was used to predict CU-to-MCI/dementia progression. The longitudinal data of these selected markers were used to construct DPMs using the algorithms of growth models by alternating conditional expectation (GRACE) and the latent time joint mixed effects model (LTJMM). The results show that the natural history of the proposed cognitive decline classifies the subjects well according to the clinical groups and shows a moderate correlation between the conversion times and their estimates by the algorithms.

COMPARISON WITH EXISTING METHODS

Unlike the training of the DPM algorithms without preselection of the markers, here, it is proposed to construct and evaluate the DPMs using the subsets of markers defined by the categorical predictive models.

CONCLUSIONS

The estimates of the natural history of the proposed cognitive decline from GRACE were more robust than those using LTJMM. The transition from normal to cognitive decline is mostly associated with an increase in temporal atrophy, worsening of clinical scores and pTAU/Aβ. Furthermore, pTAU/Aβ, Everyday Cognition score and the normalized volume of the entorhinal cortex show alterations of more than 20% fifteen years before the onset of cognitive decline.

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.

Alzheimer’s Disease: Epidemiology and Clinical Progression

Alzheimer’s disease (AD) is prevalent throughout the world and is the leading cause of dementia in older individuals (aged ≥ 65 years). To gain a deeper understanding of the recent literature on the epidemiology of AD and its progression, we conducted a review of the PubMed-indexed literature (2014–2021) in North America, Europe, and Asia. The worldwide toll of AD is evidenced by rising prevalence, incidence, and mortality due to AD—estimates which are low because of underdiagnosis of AD. Mild cognitive impairment (MCI) due to AD can ultimately progress to AD dementia; estimates of AD dementia etiology among patients with MCI range from 40% to 75% depending on the populations studied and whether the MCI diagnosis was made clinically or in combination with biomarkers. The risk of AD dementia increases with progression from normal cognition with no amyloid-beta (Aβ) accumulation to early neurodegeneration and subsequently to MCI. For patients with Aβ accumulation and neurodegeneration, lifetime risk of AD dementia has been estimated to be 41.9% among women and 33.6% among men. Data on progression from preclinical AD to MCI are sparse, but an analysis of progression across the three preclinical National Institute on Aging and Alzheimer’s Association (NIA-AA) stages suggests that NIA-AA stage 3 (subtle cognitive decline with AD biomarker positivity) could be useful in combination with other tools for treatment decision-making. Factors shown to increase risk include lower Mini-Mental State Examination (MMSE) score, higher Alzheimer’s Disease Assessment Scale (ADAS-cog) score, positive APOE4 status, white matter hyperintensities volume, entorhinal cortex atrophy, cerebrospinal fluid (CSF) total tau, CSF neurogranin levels, dependency in instrumental activities of daily living (IADL), and being female. Results suggest that use of biomarkers alongside neurocognitive tests will become an important part of clinical practice as new disease-modifying therapies are introduced.

Development of a Sex-Specific Risk Scoring System for the Prediction of Cognitively Normal People to Patients With Mild Cognitive Impairment (SRSS-CNMCI)

OBJECTIVE

We aimed to develop a sex-specific risk scoring system, abbreviated as SRSS-CNMCI, for the prediction of the conversion of cognitively normal (CN) people into patients with Mild Cognitive Impairment (MCI) to provide a reliable tool for the prevention of MCI.

METHODS

CN at baseline participants 61-90 years of age were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with at least one follow-up. Multivariable Cox proportional hazards models were used to identify the major risk factors associated with the conversion from CN to MCI and to develop the SRSS-CNMCI. Receiver operating characteristic (ROC) curve analysis was used to determine risk cutoff points corresponding to an optimal prediction. The results were externally validated, including evaluation of the discrimination and calibration in the Harvard Aging Brain Study (HABS) database.

RESULTS

A total of 471 participants, including 240 female (51%) and 231 male participants (49%) aged from 61 to 90 years, were included in the study cohort. The final multivariable models and the SRSS-CNMCI included age, APOE e4, mini mental state examination (MMSE) and clinical dementia rating (CDR). The C-statistics of the SRSS-CNMCI were 0.902 in the female subgroup and 0.911 in the male subgroup. The cutoff point of high and low risks was 33% in the female subgroup, indicating that more than 33% female participants were considered to have a high risk, and more than 9% participants were considered to have a high risk in the male subgroup. The SRSS-CNMCI performed well in the external cohort: the C-statistics were 0.950 in the female subgroup and 0.965 in the male subgroup.

CONCLUSION

The SRSS-CNMCI performs well in various cohorts and provides an accurate prediction and a generalization.

Comparison of the predictive accuracy of multiple definitions of cognitive impairment for incident dementia: a 20-year follow-up of the Whitehall II cohort study

BACKGROUND

Studies generally use cognitive assessment done at one timepoint to define cognitive impairment in order to examine conversion to dementia. Our objective was to examine the predictive accuracy and conversion rate of seven alternate definitions of cognitive impairment for dementia.

METHODS

In this prospective study, we included participants from the Whitehall II cohort study who were assessed for cognitive impairment in 2007-09 and were followed up for clinically diagnosed dementia. Algorithms based on poor cognitive performance (defined using age-specific and sex-specific thresholds, and subsequently thresholds by education or occupation levels) and objective cognitive decline (using data from cognitive assessments in 1997-99, 2002-04, and 2007-09) were used to generate seven alternate definitions of cognitive impairment. We compared predictive accuracy using Royston's R 2, the Akaike information criterion (AIC), sensitivity, specificity, and Harrell's C-statistic.

FINDINGS

5687 participants, with a mean age of 65·7 years (SD 5·9) in 2007-09, were included and followed up for a median of 10·5 years (IQR 10·1-10·9). Over follow-up, 270 (4·7%) participants were clinically diagnosed with dementia. Cognitive impairment defined using both cognitive performance and decline had higher hazard ratios (from 5·08 [95% CI 3·82-6·76] to 5·48 [4·13-7·26]) for dementia than did definitions based on cognitive performance alone (from 3·25 [2·52-4·17] to 3·39 [2·64-4·36]) and cognitive decline alone (3·01 [2·37-3·82]). However, all definitions had poor predictive performance (C-statistic ranged from 0·591 [0·565-0·616] to 0·631 [0·601-0·660]), primarily due to low sensitivity (21·6-48·4%). A predictive model containing age, sex, and education without measures of cognitive impairment had better predictive performance (C-statistic 0·783 [0·758-0·809], sensitivity 74·2%, specificity 72·2%) than all seven definitions of cognitive impairment (all p<0·0001).

INTERPRETATION

These findings suggest that cognitive impairment in early old age might not be useful for dementia prediction, even when it is defined using longitudinal data on cognitive decline and thresholds of poor cognitive performance additionally defined by education or occupation.

FUNDING

National Institutes of Health, UK Medical Research Council.

2020 update on the clinical validity of cerebrospinal fluid amyloid, tau, and phospho-tau as biomarkers for Alzheimer's disease in the context of a structured 5-phase development framework

Purpose

In the last decade, the research community has focused on defining reliable biomarkers for the early detection of Alzheimer’s disease (AD) pathology. In 2017, the Geneva AD Biomarker Roadmap Initiative adapted a framework for the systematic validation of oncological biomarkers to cerebrospinal fluid (CSF) AD biomarkers—encompassing the 42 amino-acid isoform of amyloid-β (Aβ42), phosphorylated-tau (P-tau), and Total-tau (T-tau)—with the aim to accelerate their development and clinical implementation. The aim of this work is to update the current validation status of CSF AD biomarkers based on the Biomarker Roadmap methodology.

Methods

A panel of experts in AD biomarkers convened in November 2019 at a 2-day workshop in Geneva. The level of maturity (fully achieved, partly achieved, preliminary evidence, not achieved, unsuccessful) of CSF AD biomarkers was assessed based on the Biomarker Roadmap methodology before the meeting and presented and discussed during the workshop.

Results

By comparison to the previous 2017 Geneva Roadmap meeting, the primary advances in CSF AD biomarkers have been in the area of a unified protocol for CSF sampling, handling and storage, the introduction of certified reference methods and materials for Aβ42, and the introduction of fully automated assays. Additional advances have occurred in the form of defining thresholds for biomarker positivity and assessing the impact of covariates on their discriminatory ability.

Conclusions

Though much has been achieved for phases one through three, much work remains in phases four (real world performance) and five (assessment of impact/cost). To a large degree, this will depend on the availability of disease-modifying treatments for AD, given these will make accurate and generally available diagnostic tools key to initiate therapy.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05258-7.

Sleep Quality and Health-Related Quality of Life in Older People With Subjective Cognitive Decline, Mild Cognitive Impairment, and Alzheimer Disease

We aimed to investigate sleep quality and health-related quality of life (HRQOL) in older adults with subjective cognitive decline (SCD), mild cognitive impairment (MCI), and Alzheimer disease (AD). A total of 221 participants were divided into the following five groups: normal controls (NCs), SCD without memory concerns (SCD-0), SCD with memory concerns (SCD-1), MCI, and AD according to their cognitive status. Compared with NC, individuals with SCD-0, SCD-1, MCI, and AD had more sleep problems and reduced HRQOL. Participants with poor sleep quality had an increased risk of cognitive impairment compared with participants with good sleep quality. Within all five subgroups, individuals with poor sleep quality reported more difficulties in HRQOL than individuals with good sleep quality. Future studies employing a longitudinal design, larger samples, and objective evaluation tools are needed.