Assessing risk for preclinical β-amyloid pathology with APOE, cognitive, and demographic information

Predicting amyloid beta accumulation in cognitively unimpaired older adults: Cognitive assessments provide no additional utility beyond demographic and genetic factors

BACKGROUND

Integrating non-invasive measures to estimate abnormal amyloid beta accumulation (Aβ+) is key to developing a screening tool for preclinical Alzheimer's disease (AD). The predictive capability of standard neuropsychological tests in estimating Aβ+ has not been quantified.

METHODS

We constructed machine learning models using six cognitive measurements alongside demographic and genetic risk factors to predict Aβ status. Data were drawn from three cohorts: Anti-Amyloid Treatment in Asymptomatic Alzheimer's Disease (A4), Alzheimer's Disease Neuroimaging Initiative (ADNI), and Australian Imaging, Biomarker & Lifestyle (AIBL) study. Internal validation was conducted within A4 with external validations in ADNI and AIBL to assess model generalizability.

RESULTS

The highest area under the curve (AUC) for predicting Aβ+ was observed with demographic, genetic, and cognitive variables in A4 (median AUC = 0.745), but this was not significantly different from models without cognitive variables. External validation showed no improvement in ADNI and a slight decrease in AIBL.

DISCUSSION

Standard neuropsychological tests do not significantly enhance Aβ+ prediction in cognitively unimpaired adults beyond demographic and genetic information.

HIGHLIGHTS

Standard neuropsychological tests do not significantly improve the prediction of amyloid beta positivity (Aβ+) in cognitively unimpaired older adults beyond demographic and genetic information alone. Across three well-characterized cohorts, machine learning models incorporating cognitive measures failed to significantly improve Aβ+ prediction, indicating the limited relationship between cognitive performance on these tests and the risk of pre-clinical Alzheimer's disease (AD). These findings challenge assumptions about cognitive symptoms preceding Aβ+ screening and emphasize the need for developing more sensitive cognitive tests for early AD detection.

Predicting amyloid-PET and clinical conversion in apolipoprotein E ε3/ε3 non-demented individuals with multidimensional factors

The apolipoprotein E (APOE) ε4 is a well-established risk factor of amyloid-β (Aβ) in Alzheimer's disease (AD). However, because of the high prevalence of APOE ε3, there may be a large number of people with APOE ε3/ε3 who are non-demented and have Aβ pathology. There are limited studies on assessing Aβ status and clinical conversion in the APOE ε3/ε3 non-demented population. Two hundred and ninety-three non-demented individuals with APOE ε3/ε3 from ADNI database were divided into Aβ-positron emission tomography (Aβ-PET) positivity (+) and Aβ-PET negativity (-) groups using cut-off value of >1.11. Stepwise regression searched for a single or multidimensional clinical variables for predicting Aβ-PET (+), and the receiver operating characteristic curve (ROC) assessed the accuracy of the predictive models. The Cox regression model explored the risk factors associated with clinical conversion to mild cognitive impairment (MCI) or AD. The results showed that the combination of sex, education, ventricle and white matter hyperintensity (WMH) volume can accurately predict Aβ-PET status in cognitively normal (CN), and the combination of everyday cognition study partner total (EcogSPTotal) score, age, plasma p-tau 181 and WMH can accurately predict Aβ-PET status in MCI individuals. EcogSPTotal score were independent predictors of clinical conversion to MCI or AD. The findings may provide a non-invasive and effective tool to improve the efficiency of screening Aβ-PET (+), accelerate and reduce costs of AD trial recruitment in future secondary prevention trials or help to select patients at high risk of disease progression in clinical trials.

Machine learning prediction of future amyloid beta positivity in amyloid-negative individuals

BACKGROUND

The pathophysiology of Alzheimer's disease (AD) involves β -amyloid (A β ) accumulation. Early identification of individuals with abnormal β -amyloid levels is crucial, but A β quantification with positron emission tomography (PET) and cerebrospinal fluid (CSF) is invasive and expensive.

METHODS

We propose a machine learning framework using standard non-invasive (MRI, demographics, APOE, neuropsychology) measures to predict future A β -positivity in A β -negative individuals. We separately study A β -positivity defined by PET and CSF.

RESULTS

Cross-validated AUC for 4-year A β conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based A β definitions. Although not trained for the clinical status-change prediction, the CSF-based model excelled in predicting future mild cognitive impairment (MCI)/dementia conversion in cognitively normal/MCI individuals (AUCs, respectively, 0.76 and 0.89 with a separate dataset).

CONCLUSION

Standard measures have potential in detecting future A β -positivity and assessing conversion risk, even in cognitively normal individuals. The CSF-based definition led to better predictions than the PET-based definition.

Detecting Amyloid Positivity Using Morphometric Magnetic Resonance Imaging

Background

Early detection of amyloid-β (Aβ) positivity is essential for an accurate diagnosis and treatment of Alzheimer's disease (AD), but it is currently costly and/or invasive.

Objective

We aimed to classify Aβ positivity (Aβ+) using morphometric features from magnetic resonance imaging (MRI), a more accessible and non-invasive technique, in two clinical population scenarios: one containing AD, mild cognitive impairment (MCI) and cognitively normal (CN) subjects, and another only cognitively impaired subjects (AD and MCI).

Methods

Demographic, cognitive (Mini-Mental State Examination [MMSE] scores), regional morphometry MRI (volumes, areas, and thicknesses), and derived morphometric graph theory (GT) features from all subjects (302 Aβ+, age: 73.3±7.2, 150 male; 246 Aβ-, age: 71.1±7.1, 131 male) were combined in different feature sets. We implemented a machine learning workflow to find the best Aβ+ classification model.

Results

In an AD+MCI+CN population scenario, the best-performing model selected 120 features (107 GT features, 12 regional morphometric features and the MMSE total score) and achieved a negative predictive value (NPVadj) of 68.4%, and a balanced accuracy (BAC) of 66.9%. In a AD+MCI scenario, the best model obtained NPVadj of 71.6%, and BAC of 70.7%, using 180 regional morphometric features (98 volumes, 52 areas and 29 thicknesses from temporal, parietal, and frontal brain regions).

Conclusions

Although with currently limited clinical applicability, regional MRI morphometric features have clinical usefulness potential for detecting Aβ status, which may be augmented by a combination with cognitive data when cognitively normal subjects make up a substantial part of the population presenting for diagnosis.

Predicting positron emission tomography brain amyloid positivity using interpretable machine learning models with wearable sensor data and lifestyle factors

BACKGROUND

Developing a screening method for identifying individuals at higher risk of elevated brain amyloid burden is important to reduce costs and burden to patients in clinical trials on Alzheimer's disease or the clinical setting. We developed machine learning models using objectively measured lifestyle factors to predict elevated brain amyloid burden on positron emission tomography.

METHODS

Our prospective cohort study of non-demented, community-dwelling older adults aged ≥ 65 years was conducted from August 2015 to September 2019 in Usuki, Oita Prefecture, Japan. One hundred and twenty-two individuals with mild cognitive impairment or subjective memory complaints (54 men and 68 women, median age: 75.50 years) wore wearable sensors and completed self-reported questionnaires, cognitive test, and positron emission tomography imaging at baseline. Moreover, 99 individuals in the second year and 61 individuals in the third year were followed up. In total, 282 eligible records with valid wearable sensors, cognitive test results, and amyloid imaging and data on demographic characteristics, living environments, and health behaviors were used in the machine learning models. Amyloid positivity was defined as a standardized uptake value ratio of ≥ 1.4. Models were constructed using kernel support vector machine, Elastic Net, and logistic regression for predicting amyloid positivity. The mean score among 10 times fivefold cross-validation repeats was utilized for evaluation.

RESULTS

In Elastic Net, the mean area under the receiver operating characteristic curve of the model using objectively measured lifestyle factors alone was 0.70, whereas that of the models using wearable sensors in combination with demographic characteristics and health and life environment questionnaires was 0.79. Moreover, 22 variables were common to all machine learning models.

CONCLUSION

Our machine learning models are useful for predicting elevated brain amyloid burden using readily-available and noninvasive variables without the need to visit a hospital.

TRIAL REGISTRATION

This prospective study was conducted in accordance with the Declaration of Helsinki and was approved by the local ethics committee of Oita University Hospital (UMIN000017442). A written informed consent was obtained from all participants. This research was performed based on the Strengthening the Reporting of Observational Studies in Epidemiology reporting guideline.

Predicting amyloid-beta pathology in the general population

INTRODUCTION

Reliable models to predict amyloid beta (Aβ) positivity in the general aging population are lacking but could become cost-efficient tools to identify individuals at risk of developing Alzheimer's disease.

METHODS

We developed Aβ prediction models in the clinical Anti-Amyloid Treatment in Asymptomatic Alzheimer's (A4) Study (n = 4,119) including a broad range of easily ascertainable predictors (demographics, cognition and daily functioning, health and lifestyle factors). Importantly, we determined the generalizability of our models in the population-based Rotterdam Study (n = 500).

RESULTS

The best performing model in the A4 Study (area under the curve [AUC] = 0.73 [0.69-0.76]), including age, apolipoprotein E (APOE) ε4 genotype, family history of dementia, and subjective and objective measures of cognition, walking duration and sleep behavior, was validated in the independent Rotterdam Study with higher accuracy (AUC = 0.85 [0.81-0.89]). Yet, the improvement relative to a model including only age and APOE ε4 was marginal.

DISCUSSION

Aβ prediction models including inexpensive and non-invasive measures were successfully applied to a general population-derived sample more representative of typical older non-demented adults.

Brain health registry updates: An online longitudinal neuroscience platform

INTRODUCTION

Remote, internet-based methods for recruitment, screening, and longitudinally assessing older adults have the potential to facilitate Alzheimer's disease (AD) clinical trials and observational studies.

METHODS

The Brain Health Registry (BHR) is an online registry that includes longitudinal assessments including self- and study partner-report questionnaires and neuropsychological tests. New initiatives aim to increase inclusion and engagement of commonly underincluded communities using digital, community-engaged research strategies. New features include multilingual support and biofluid collection capabilities.

RESULTS

BHR includes > 100,000 participants. BHR has made over 259,000 referrals resulting in 25,997 participants enrolled in 30 aging and AD studies. In addition, 28,278 participants are coenrolled in BHR and other studies with data linkage among studies. Data have been shared with 28 investigators. Recent efforts have facilitated the enrollment and engagement of underincluded ethnocultural communities.

DISCUSSION

The major advantages of the BHR approach are scalability and accessibility. Challenges include compliance, retention, cohort diversity, and generalizability.

HIGHLIGHTS

Brain Health Registry (BHR) is an online, longitudinal platform of > 100,000 members. BHR made > 259,000 referrals, which enrolled 25,997 participants in 32 studies. New efforts increased enrollment and engagement of underincluded communities in BHR. The major advantages of the BHR approach are scalability and accessibility. BHR provides a unique adjunct for clinical neuroscience research.

Integrated algorithm combining plasma biomarkers and cognitive assessments accurately predicts brain β-amyloid pathology

BACKGROUND

Accurate prediction of cerebral amyloidosis with easily available indicators is urgently needed for diagnosis and treatment of Alzheimer's disease (AD).

METHODS

We examined plasma Aβ42, Aβ40, T-tau, P-tau181, and NfL, with APOE genotypes, cognitive test scores and key demographics in a large Chinese cohort (N = 609, aged 40 to 84 years) covering full AD spectrum. Data-driven integrated computational models were developed to predict brain β-amyloid (Aβ) pathology.

RESULTS

Our computational models accurately predict brain Aβ positivity (area under the ROC curves (AUC) = 0.94). The results are validated in Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Particularly, the models have the highest prediction power (AUC = 0.97) in mild cognitive impairment (MCI) participants. Three levels of models are designed with different accuracies and complexities. The model which only consists of plasma biomarkers can predict Aβ positivity in amnestic MCI (aMCI) patients with AUC = 0.89. Generally the models perform better in participants without comorbidities or family histories.

CONCLUSIONS

The innovative integrated models provide opportunity to assess Aβ pathology in a non-invasive and cost-effective way, which might facilitate AD-drug development, early screening, clinical diagnosis and prognosis evaluation.

Predicting conversion of brain β-amyloid positivity in amyloid-negative individuals

Background

Cortical deposition of β-amyloid (Aβ) plaque is one of the main hallmarks of Alzheimer’s disease (AD). While Aβ positivity has been the main concern so far, predicting whether Aβ (−) individuals will convert to Aβ (+) has become crucial in clinical and research aspects. In this study, we aimed to develop a classifier that predicts the conversion from Aβ (−) to Aβ (+) using artificial intelligence.

Methods

Data were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort regarding patients who were initially Aβ (−). We developed an artificial neural network-based classifier with baseline age, gender, APOE ε4 genotype, and global and regional standardized uptake value ratios (SUVRs) from positron emission tomography. Ten times repeated 10-fold cross-validation was performed for model measurement, and the feature importance was assessed. To validate the prediction model, we recruited subjects at the Samsung Medical Center (SMC).

Results

A total of 229 participants (53 converters) from the ADNI dataset and a total of 40 subjects (10 converters) from the SMC dataset were included. The average area under the receiver operating characteristic values of three developed models are as follows: Model 1 (age, gender, APOE ε4) of 0.674, Model 2 (age, gender, APOE ε4, global SUVR) of 0.814, and Model 3 (age, gender, APOE ε4, global and regional SUVR) of 0.841. External validation result showed an AUROC of 0.900.

Conclusion

We developed prediction models regarding Aβ positivity conversion. With the growing recognition of the need for earlier intervention in AD, the results of this study are expected to contribute to the screening of early treatment candidates.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13195-022-01067-8.

Initial Data and a Clinical Diagnosis Transition for the Aiginition Longitudinal Biomarker Investigation of Neurodegeneration (ALBION) Study

Background and Objectives: This article presents data from the ongoing Aiginition Longitudinal Biomarker Investigation of Neurodegeneration study (ALBION) regarding baseline clinical characterizations and CSF biomarker profiles, as well as preliminary longitudinal data on clinical progression. Materials and Methods: As of March 2022, 138 participants who either were cognitively normal (CN, n = 99) or had a diagnosis of mild cognitive impairment (MCI, n = 39) had been recruited at the specialist cognitive disorders outpatient clinic at Aiginition Hospital. Clinical characteristics at baseline were provided. These patients were followed annually to determine progression from CN to MCI or even dementia. CSF biomarker data (amyloid β1-42, phosphorylated tau at threonine 181, and total tau) collected using automated Elecsys® assays (Roche Diagnostics) were available for 74 patients. These patients were further sorted based on the AT(N) classification model, as determined by CSF Aβ42 (A), CSF pTau (T), and CSF tTau (N). Results: Of the 49 CN patients with CSF biomarker data, 21 (43%) were classified as exhibiting “Alzheimer’s pathologic change” (A+Τ− (Ν)−) and 6 (12%) as having “Alzheimer’s disease” (A+T−(N)+, A+T+(N)−, or A+T+(N)+). Of the 25 MCI patients, 8 (32%) displayed “Alzheimer’s pathologic change”, and 6 (24%) had “Alzheimer’s disease”. A total of 66 individuals had a mean follow-up of 2.1 years (SD = 0.9, min = 0.8, max = 3.9), and 15 of those individuals (22%) showed a clinical progression (defined as a worsening clinical classification, i.e., from CN to MCI or dementia or from MCI to dementia). Overall, participants with the “AD continuum” AT(N) biomarker profile (i.e., A+T−(N)−, A+T−(N)+, A+T+(N)−, and A+T+(N)+) were more likely to clinically progress (p = 0.04). Conclusions: A CSF “AD continuum” AT(N) biomarker profile is associated with an increased risk of future clinical decline in CN or MCI subjects.

Relationships between educational attainment, hypertension, and amyloid negative subcortical vascular dementia: The brain-battering hypothesis

Purpose

Many epidemiological studies suggest that lower education levels and vascular risk factors increase the likelihood of developing Alzheimer's disease dementia (ADD) and subcortical vascular dementia (SVaD). However, whether the brain-battering hypothesis can explain the relationship between education levels and the clinical diagnosis of dementia remains controversial. The objective of this study was to investigate whether vascular risk factors mediate the association between education level and the diagnosis of amyloid-beta positive (Aβ+) ADD and amyloid-beta negative (Aβ-) SVaD.

Methods

We analyzed 376 participants with Aβ normal cognition (Aβ- NC), 481 with Aβ+ ADD, and 102 with Aβ- SVaD. To investigate the association of education level and vascular risk factors with these diagnoses, multivariable logistic regression analysis was used, with age, sex, and APOE ε4 carrier status used as covariates. Path analysis was performed to investigate the mediation effects of hypertension on the diagnosis of Aβ- SVaD.

Results

The Aβ- SVaD group (7.9 ± 5.1 years) had lower education levels than did the Aβ- NC (11.8 ± 4.8 years) and Aβ+ ADD (11.2 ± 4.9 years) groups. The frequencies of hypertension and diabetes mellitus were higher in the Aβ- SVaD group (78.4 and 32.4%, respectively) than in the Aβ- NC (44.4 and 20.8%) and Aβ+ ADD (41.8 and 15.8%, respectively) groups. Increased education level was associated with a lower risk of Aβ- SVaD [odds ratio (OR) 0.866, 95% confidence interval (CI), 0.824–0.911], but not Aβ+ ADD (OR 0.971, 95% CI 0.940–1.003). The frequency of hypertension was associated with a higher risk of developing Aβ- SVaD (OR 3.373, 95% CI, 1.908–5.961), but not Aβ+ ADD (OR 0.884, 95% CI, 0.653–1.196). In the path analysis, the presence of hypertension partially mediated the association between education level and the diagnosis of Aβ- SVaD.

Conclusion

Our findings revealed that education level might influence the development of Aβ- SVaD through the brain-battering hypothesis. Furthermore, our findings suggest that suitable strategies, such as educational attainment and prevention of hypertension, are needed for the prevention of Aβ- SVaD.

Potential Applications of Artificial Intelligence in Clinical Trials for Alzheimer’s Disease

Clinical trials for Alzheimer’s disease (AD) face multiple challenges, such as the high screen failure rate and the even allocation of heterogeneous participants. Artificial intelligence (AI), which has become a potent tool of modern science with the expansion in the volume, variety, and velocity of biological data, offers promising potential to address these issues in AD clinical trials. In this review, we introduce the current status of AD clinical trials and the topic of machine learning. Then, a comprehensive review is focused on the potential applications of AI in the steps of AD clinical trials, including the prediction of protein and MRI AD biomarkers in the prescreening process during eligibility assessment and the likelihood stratification of AD subjects into rapid and slow progressors in randomization. Finally, this review provides challenges, developments, and the future outlook on the integration of AI into AD clinical trials.

Risk Factors Predicting Amyloid PET Positivity in Patients with Mild Cognitive Impairment and Apolipoprotein E ɛ3/ɛ3 Genotypes

BACKGROUND

The apolipoprotein E (APOE) ɛ4 allele is a well-known risk factor for AD and is associated with higher amyloid deposition and earlier dementia onset. However, the relationship between amyloid pathology and the most common APOE allele, ɛ3, has not been well studied.

OBJECTIVE

In this study, we aimed to identify the risk factors predicting amyloid PET positivity in patients with mild cognitive impairment (MCI) and APOEɛ3/ɛ3 genotypes.

METHODS

We retrospectively reviewed the medical records of MCI patients with APOEɛ3/ɛ3 genotypes who underwent amyloid PET scanning. Demographics, neuropsychological tests, and brain MRI were obtained. We analyzed which risk factors could affect amyloid PET positivity in MCI patients with APOEɛ3/ɛ3 genotypes using logistic regression models.

RESULTS

We recruited 171 MCI patients with APOEɛ3/ɛ3 genotypes in this study. Out of 171 patients, 49 patients (28.65%) showed positive results in the amyloid PET scans. In a multivariate logistic regression model, amyloid positivity was associated with frontal atrophy (OR = 2.63, p = 0.009), and CDR-SOB scores (OR = 2.46, p = 0.013). The odds ratio for amyloid PET positivity in patients older than and equal to 75 years with both frontal atrophy and CDR-SOB scores >1.0 was 3.63.

CONCLUSION

Our study demonstrated that frontal atrophy, high CDR-SOB scores, and old age were risk factors associated with amyloid PET positivity in MCI with APOEɛ3/ɛ3 genotypes.

Plasma amyloid-β oligomerization assay as a pre-screening test for amyloid status

OBJECTIVE

We assessed the performance of plasma amyloid oligomerization tendency (OAβ) as a marker for abnormal amyloid status. Additionally, we examined long-term storage effects on plasma OAβ.

METHODS

We included 399 subjects regardless of clinical diagnosis from the Amsterdam Dementia Cohort and European Medical Information Framework for AD project (age, 63.8 ± 6.6; 44% female). Amyloid status was determined by visual read on positron emission tomography (PET; nabnormal = 206). Plasma OAβ was measured using the multimer detection system (MDS). Long-term storage effects on MDS-OAβ were assessed using general linear models. Associations between plasma MDS-OAβ and Aβ-PET status were assessed using logistic regression and receiver operating characteristics analyses. Correlations between plasma MDS-OAβ and CSF biomarker levels were evaluated using Pearson correlation analyses.

RESULTS

MDS-OAβ was higher in individuals with abnormal amyloid, and it identified abnormal Aβ-PET with an area under the curve (AUC) of 0.74 (95% CI, 0.67-0.81), especially in samples with a storage duration < 4 years. Combining APOEe4 and age with plasma MDS-OAβ revealed an AUC of 81% for abnormal amyloid PET status (95% CI, 74-87%). Plasma MDS-OAβ correlated negatively with MMSE (r = - 0.29, p < .01) and CSF Aβ42 (r = - 0.20, p < 0.05) and positively with CSF Tau (r = 0.20, p = 0.01).

CONCLUSIONS

Plasma MDS-OAβ combined with APOEe4 and age accurately identifies brain amyloidosis in a large Aβ-confirmed population. Using plasma MDS-OAβ as a screener reduced the costs and number of PET scans needed to screen for amyloidosis, which is relevant for clinical trials. Additionally, plasma MDS-OAβ levels appeared affected by long-term storage duration, which could be of interest for others measuring plasma Aβ biomarkers.

A cross-sectional study in healthy elderly subjects aimed at development of an algorithm to increase identification of Alzheimer pathology for the purpose of clinical trial participation

Background

In the current study, we aimed to develop an algorithm based on biomarkers obtained through non- or minimally invasive procedures to identify healthy elderly subjects who have an increased risk of abnormal cerebrospinal fluid (CSF) amyloid beta42 (Aβ) levels consistent with the presence of Alzheimer’s disease (AD) pathology. The use of the algorithm may help to identify subjects with preclinical AD who are eligible for potential participation in trials with disease modifying compounds being developed for AD. Due to this pre-selection, fewer lumbar punctures will be needed, decreasing overall burden for study subjects and costs.

Methods

Healthy elderly subjects (n = 200; age 65–70 (N = 100) and age > 70 (N = 100)) with an MMSE > 24 were recruited. An automated central nervous system test battery was used for cognitive profiling. CSF Aβ1-42 concentrations, plasma Aβ1-40, Aβ1-42, neurofilament light, and total Tau concentrations were measured. Aβ1-42/1-40 ratio was calculated for plasma. The neuroinflammation biomarker YKL-40 and APOE ε4 status were determined in plasma. Different mathematical models were evaluated on their sensitivity, specificity, and positive predictive value. A logistic regression algorithm described the data best. Data were analyzed using a 5-fold cross validation logistic regression classifier.

Results

Two hundred healthy elderly subjects were enrolled in this study. Data of 154 subjects were used for the per protocol analysis. The average age of the 154 subjects was 72.1 (65–86) years. Twenty-four (27.3%) were Aβ positive for AD (age 65–83). The results of the logistic regression classifier showed that predictive features for Aβ positivity/negativity in CSF consist of sex, 7 CNS tests, and 1 plasma-based assay. The model achieved a sensitivity of 70.82% (± 4.35) and a specificity of 89.25% (± 4.35) with respect to identifying abnormal CSF in healthy elderly subjects. The receiver operating characteristic curve showed an AUC of 65% (± 0.10).

Conclusion

This algorithm would allow for a 70% reduction of lumbar punctures needed to identify subjects with abnormal CSF Aβ levels consistent with AD. The use of this algorithm can be expected to lower overall subject burden and costs of identifying subjects with preclinical AD and therefore of total study costs.

Trial registration

ISRCTN.org identifier: ISRCTN79036545 (retrospectively registered).

Supplementary Information

The online version contains supplementary material available at 10.1186/s13195-021-00874-9.

Machine learning approaches to predicting amyloid status using data from an online research and recruitment registry: The Brain Health Registry

INTRODUCTION

This study investigated the extent to which subjective and objective data from an online registry can be analyzed using machine learning methodologies to predict the current brain amyloid beta (Aβ) status of registry participants.

METHODS

We developed and optimized machine learning models using data from up to 664 registry participants. Models were assessed on their ability to predict Aβ positivity using the results of positron emission tomography as ground truth.

RESULTS

Study partner-assessed Everyday Cognition score was preferentially selected for inclusion in the models by a feature selection algorithm during optimization.

DISCUSSION

Our results suggest that inclusion of study partner assessments would increase the ability of machine learning models to predict Aβ positivity.

Predicting Amyloid-β Levels in Amnestic Mild Cognitive Impairment Using Machine Learning Techniques

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.

A machine learning approach to screen for preclinical Alzheimer's disease

Combining multimodal biomarkers could help in the early diagnosis of Alzheimer's disease (AD). We included 304 cognitively normal individuals from the INSIGHT-preAD cohort. Amyloid and neurodegeneration were assessed on ¹⁸F-florbetapir and ¹⁸F-fluorodeoxyglucose PET, respectively. We used a nested cross-validation approach with non-invasive features (electroencephalography [EEG], APOE4 genotype, demographic, neuropsychological and MRI data) to predict: 1/ amyloid status; 2/ neurodegeneration status; 3/ decline to prodromal AD at 5-year follow-up. Importantly, EEG was most strongly predictive of neurodegeneration, even when reducing the number of channels from 224 down to 4, as 4-channel EEG best predicted neurodegeneration (negative predictive value [NPV] = 82%, positive predictive value [PPV] = 38%, 77% specificity, 45% sensitivity). The combination of demographic, neuropsychological data, APOE4 and hippocampal volumetry most strongly predicted amyloid (80% NPV, 41% PPV, 70% specificity, 58% sensitivity) and most strongly predicted decline to prodromal AD at 5 years (97% NPV, 14% PPV, 83% specificity, 50% sensitivity). Thus, machine learning can help to screen patients at high risk of preclinical AD using non-invasive and affordable biomarkers.

Predicting amyloid risk by machine learning algorithms based on the A4 screen data: Application to the Japanese Trial-Ready Cohort study

BACKGROUND

Selecting cognitively normal elderly individuals with higher risk of brain amyloid deposition is critical to the success of prevention trials for Alzheimer's disease (AD).

METHODS

Based on the Anti-Amyloid Treatment in Asymptomatic Alzheimer's Disease study data, we built machine-learning models and applied them to our ongoing Japanese Trial-Ready Cohort (J-TRC) webstudy participants registered within the first 9 months (n = 3081) of launch to predict standard uptake value ratio (SUVr) of amyloid positron emission tomography.

RESULTS

Age, family history, online Cognitive Function Instrument and CogState scores were important predictors. In a subgroup of J-TRC webstudy participants with known amyloid status (n = 37), the predicted SUVr corresponded well with the self-reported amyloid test results (area under the curve = 0.806 [0.619-0.992]).

DISCUSSION

Our algorithms may be usable for automatic prioritization of candidate participants with higher amyloid risks to be preferentially recruited from the J-TRC webstudy to in-person study, maximizing efficiency for the identification of preclinical AD participants.

The search for a convenient procedure to detect one of the earliest signs of Alzheimer's disease: A systematic review of the prediction of brain amyloid status

INTRODUCTION

Convenient, cost-effective tests for amyloid beta (Aβ) are needed to identify those at higher risk for developing Alzheimer's disease (AD). This systematic review evaluates recent models that predict dichotomous Aβ. (PROSPERO: CRD42020144734).

METHODS

We searched Embase and identified 73 studies from 29,581 for review. We assessed study quality using established tools, extracted information, and reported results narratively.

RESULTS

We identified few high-quality studies due to concerns about Aβ determination and analytical issues. The most promising convenient, inexpensive classifiers consist of age, apolipoprotein E genotype, cognitive measures, and/or plasma Aβ. Plasma Aβ may be sufficient if pre-analytical variables are standardized and scalable assays developed. Some models lowered costs associated with clinical trial recruitment or clinical screening.

DISCUSSION

Conclusions about models are difficult due to study heterogeneity and quality. Promising prediction models used demographic, cognitive/neuropsychological, imaging, and plasma Aβ measures. Further studies using standardized Aβ determination, and improved model validation are required.

Detection of β-amyloid positivity in Alzheimer's Disease Neuroimaging Initiative participants with demographics, cognition, MRI and plasma biomarkers

In vivo gold standard for the ante-mortem assessment of brain β-amyloid pathology is currently β-amyloid positron emission tomography or cerebrospinal fluid measures of β-amyloid42 or the β-amyloid42/β-amyloid40 ratio. The widespread acceptance of a biomarker classification scheme for the Alzheimer's disease continuum has ignited interest in more affordable and accessible approaches to detect Alzheimer's disease β-amyloid pathology, a process that often slows down the recruitment into, and adds to the cost of, clinical trials. Recently, there has been considerable excitement concerning the value of blood biomarkers. Leveraging multidisciplinary data from cognitively unimpaired participants and participants with mild cognitive impairment recruited by the multisite biomarker study of Alzheimer's Disease Neuroimaging Initiative, here we assessed to what extent plasma β-amyloid42/β-amyloid40, neurofilament light and phosphorylated-tau at threonine-181 biomarkers detect the presence of β-amyloid pathology, and to what extent the addition of clinical information such as demographic data, APOE genotype, cognitive assessments and MRI can assist plasma biomarkers in detecting β-amyloid-positivity. Our results confirm plasma β-amyloid42/β-amyloid40 as a robust biomarker of brain β-amyloid-positivity (area under curve, 0.80-0.87). Plasma phosphorylated-tau at threonine-181 detected β-amyloid-positivity only in the cognitively impaired with a moderate area under curve of 0.67, whereas plasma neurofilament light did not detect β-amyloid-positivity in either group of participants. Clinical information as well as MRI-score independently detected positron emission tomography β-amyloid-positivity in both cognitively unimpaired and impaired (area under curve, 0.69-0.81). Clinical information, particularly APOE ε4 status, enhanced the performance of plasma biomarkers in the detection of positron emission tomography β-amyloid-positivity by 0.06-0.14 units of area under curve for cognitively unimpaired, and by 0.21-0.25 units for cognitively impaired; and further enhancement of these models with an MRI-score of β-amyloid-positivity yielded an additional improvement of 0.04-0.11 units of area under curve for cognitively unimpaired and 0.05-0.09 units for cognitively impaired. Taken together, these multi-disciplinary results suggest that when combined with clinical information, plasma phosphorylated-tau at threonine-181 and neurofilament light biomarkers, and an MRI-score could effectively identify β-amyloid+ cognitively unimpaired and impaired (area under curve, 0.80-0.90). Yet, when the MRI-score is considered in combination with clinical information, plasma phosphorylated-tau at threonine-181 and plasma neurofilament light have minimal added value for detecting β-amyloid-positivity. Our systematic comparison of β-amyloid-positivity detection models identified effective combinations of demographics, APOE, global cognition, MRI and plasma biomarkers. Promising minimally invasive and low-cost predictors such as plasma biomarkers of β-amyloid42/β-amyloid40 may be improved by age and APOE genotype.

Dementias Platform UK Clinical Studies and Great Minds Register: protocol of a targeted brain health studies recontact database

INTRODUCTION

The case for de-risking neurodegenerative research and development through highly informative experimental medicine studies early in the disease process is strong. Such studies depend on the availability of genetic as well as high-granularity, longitudinal, phenotypic data in healthy ageing individuals who can be recruited into early phase trials on the basis of their perceived dementia risk. Until now the creation of such research infrastructure has been hampered by the lack of expense and time required to gather the rich longitudinal data needed for adequate risk stratification. Dementias Platform UK (DPUK) is a public-private partnership that brings together data from over 40 cohorts in a standardised framework, which represent an until now unavailable opportunity to create such a resource through a streamlined brain health recontact platform based on existing cohorts, as well as prospectively collected data.

METHODS AND ANALYSIS

The DPUK recontact platform consists of an opt-in (Great Minds, GM) and an opt-out component (Clinical Studies Register, CSR). GM requires invited DPUK cohort participants to consent to targeted recontact at the GM website and then to provide self-reported demographic and medical history information relevant to recruitment into clinical studies. Participants complete prospective browser-based and smartphone-based cognitive tests and are given the option for remote genetic and actigraphy testing. The GM data are linked to the retrospective DPUK cohort dataset, including genotypic and longitudinal phenotypic data. The CSR is a solution for cohorts explicitly allowing targeted recontact. Approved studies provide prescreening criteria on the basis of the CSR/GM dataset, and individuals meeting these criteria are offered participation directly (GM) or through the parent DPUK cohort (CSR). Descriptive statistics will be used to summarise the outcomes relevant to the number of participants engaged with the register. Its sample size is not defined but is limited by the size of the DPUK parent cohorts.

ETHICS AND DISSEMINATION

The database was approved by the South Central-Oxford C Research Ethics Committee, reference 18/SC/0268 on the 27th of June 2018 and amended on the 1st of November 2019. The availability of the register to researchers will be disseminated through DPUK's official communication channels as well as national and international scientific meetings.

Quantitative informant- and self-reports of subjective cognitive decline predict amyloid beta PET outcomes in cognitively unimpaired individuals independently of age and APOE ε4

INTRODUCTION

Amyloid beta (Aβ) pathology is an Alzheimer's disease early hallmark. Here we assess the value of longitudinal self- and informant reports of cognitive decline to predict Aβ positron emission tomography (PET) outcome in cognitively unimpaired middle-aged individuals.

METHODS

A total of 261 participants from the ALFA+ study underwent [18F]flutemetamol PET and Subjective Cognitive Decline Questionnaire (SCD-Q) concurrently, and 3 years before scan. We used logistic regressions to evaluate the ability of SCD-Q scores (self and informant) to predict Aβ PET visual read, and repeated analysis of variance to assess whether changes in SCD-Q scores relate to Aβ status.

RESULTS

Self-perception of decline in memory (odds ratio [OR] = 1.2), and informant perception of executive decline (OR = 1.6), increased the probability of a positive scan. Informant reports 3 years before scanning predicted Aβ PET outcome. Longitudinal increase of self-reported executive decline was predictive of Aβ in women (P = .003).

DISCUSSION

Subjective reports of cognitive decline are useful to predict Aβ and may improve recruitment strategies.

Predicting amyloid status using self-report information from an online research and recruitment registry: The Brain Health Registry

INTRODUCTION

This study aimed to predict brain amyloid beta (Aβ) status in older adults using collected information from an online registry focused on cognitive aging.

METHODS

Aβ positron emission tomography (PET) was obtained from multiple in-clinic studies. Using logistic regression, we predicted Aβ using self-report variables collected in the Brain Health Registry in 634 participants, as well as a subsample (N = 533) identified as either cognitively unimpaired (CU) or mild cognitive impairment (MCI). Cross-validated area under the curve (cAUC) evaluated the predictive performance.

RESULTS

The best prediction model included age, sex, education, subjective memory concern, family history of Alzheimer's disease, Geriatric Depression Scale Short-Form, self-reported Everyday Cognition, and self-reported cognitive impairment. The cross-validated AUCs ranged from 0.62 to 0.66. This online model could help reduce between 15.2% and 23.7% of unnecessary Aβ PET scans in CU and MCI populations.

DISUCSSION

The findings suggest that a novel, online approach could aid in Aβ prediction.

Detecting Amyloid Positivity in Elderly With Increased Risk of Cognitive Decline

The importance of early interventions in Alzheimer's disease (AD) emphasizes the need to accurately and efficiently identify at-risk individuals. Although many dementia prediction models have been developed, there are fewer studies focusing on detection of brain pathology. We developed a model for identification of amyloid-PET positivity using data on demographics, vascular factors, cognition, APOE genotype, and structural MRI, including regional brain volumes, cortical thickness and a visual medial temporal lobe atrophy (MTA) rating. We also analyzed the relative importance of different factors when added to the overall model. The model used baseline data from the Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) exploratory PET sub-study. Participants were at risk for dementia, but without dementia or cognitive impairment. Their mean age was 71 years. Participants underwent a brain 3T MRI and PiB-PET imaging. PiB images were visually determined as positive or negative. Cognition was measured using a modified version of the Neuropsychological Test Battery. Body mass index (BMI) and hypertension were used as cardiovascular risk factors in the model. Demographic factors included age, gender and years of education. The model was built using the Disease State Index (DSI) machine learning algorithm. Of the 48 participants, 20 (42%) were rated as Aβ positive. Compared with the Aβ negative group, the Aβ positive group had a higher proportion of APOE ε4 carriers (53 vs. 14%), lower executive functioning, lower brain volumes, and higher visual MTA rating. AUC [95% CI] for the complete model was 0.78 [0.65-0.91]. MRI was the most effective factor, especially brain volumes and visual MTA rating but not cortical thickness. APOE was nearly as effective as MRI in improving detection of amyloid positivity. The model with the best performance (AUC 0.82 [0.71-0.93]) was achieved by combining APOE and MRI. Our findings suggest that combining demographic data, vascular risk factors, cognitive performance, APOE genotype, and brain MRI measures can help identify Aβ positivity. Detecting amyloid positivity could reduce invasive and costly assessments during the screening process in clinical trials.

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.

Selection of memory clinic patients for CSF biomarker assessment can be restricted to a quarter of cases by using computerized decision support, without compromising diagnostic accuracy

INTRODUCTION

An accurate and timely diagnosis for Alzheimer's disease (AD) is important, both for care and research. The current diagnostic criteria allow the use of CSF biomarkers to provide pathophysiological support for the diagnosis of AD. How these criteria should be operationalized by clinicians is unclear. Tools that guide in selecting patients in which CSF biomarkers have clinical utility are needed. We evaluated computerized decision support to select patients for CSF biomarker determination.

METHODS

We included 535 subjects (139 controls, 286 Alzheimer's disease dementia, 82 frontotemporal dementia and 28 vascular dementia) from three clinical cohorts. Positive (AD like) and negative (normal) CSF biomarker profiles were simulated to estimate whether knowledge of CSF biomarkers would impact (confidence in) diagnosis. We applied these simulated CSF values and combined them with demographic, neuropsychology and MRI data to initiate CSF testing (computerized decision support approach). We compared proportion of CSF measurements and patients diagnosed with sufficient confidence (probability of correct class ≥0.80) based on an algorithm with scenarios without CSF (only neuropsychology, MRI and APOE), CSF according to the appropriate use criteria (AUC) and CSF for all patients.

RESULTS

The computerized decision support approach recommended CSF testing in 140 (26%) patients, which yielded a diagnosis with sufficient confidence in 379 (71%) of all patients. This approach was more efficient than CSF in none (0% CSF, 308 (58%) diagnosed), CSF selected based on AUC (295 (55%) CSF, 350 (65%) diagnosed) or CSF in all (100% CSF, 348 (65%) diagnosed).

CONCLUSIONS

We used a computerized decision support with simulated CSF results in controls and patients with different types of dementia. This approach can support clinicians in making a balanced decision in ordering additional biomarker testing. Computer-supported prediction restricts CSF testing to only 26% of cases, without compromising diagnostic accuracy.

Prescreening for European Prevention of Alzheimer Dementia (EPAD) trial-ready cohort: impact of AD risk factors and recruitment settings

BACKGROUND

Recruitment is often a bottleneck in secondary prevention trials in Alzheimer disease (AD). Furthermore, screen-failure rates in these trials are typically high due to relatively low prevalence of AD pathology in individuals without dementia, especially among cognitively unimpaired. Prescreening on AD risk factors may facilitate recruitment, but the efficiency will depend on how these factors link to participation rates and AD pathology. We investigated whether common AD-related factors predict trial-ready cohort participation and amyloid status across different prescreen settings.

METHODS

We monitored the prescreening in four cohorts linked to the European Prevention of Alzheimer Dementia (EPAD) Registry (n = 16,877; mean ± SD age = 64 ± 8 years). These included a clinical cohort, a research in-person cohort, a research online cohort, and a population-based cohort. Individuals were asked to participate in the EPAD longitudinal cohort study (EPAD-LCS), which serves as a trial-ready cohort for secondary prevention trials. Amyloid positivity was measured in cerebrospinal fluid as part of the EPAD-LCS assessment. We calculated participation rates and numbers needed to prescreen (NNPS) per participant that was amyloid-positive. We tested if age, sex, education level, APOE status, family history for dementia, memory complaints or memory scores, previously collected in these cohorts, could predict participation and amyloid status.

RESULTS

A total of 2595 participants were contacted for participation in the EPAD-LCS. Participation rates varied by setting between 3 and 59%. The NNPS were 6.9 (clinical cohort), 7.5 (research in-person cohort), 8.4 (research online cohort), and 88.5 (population-based cohort). Participation in the EPAD-LCS (n = 413 (16%)) was associated with lower age (odds ratio (OR) age = 0.97 [0.95-0.99]), high education (OR = 1.64 [1.23-2.17]), male sex (OR = 1.56 [1.19-2.04]), and positive family history of dementia (OR = 1.66 [1.19-2.31]). Among participants in the EPAD-LCS, amyloid positivity (33%) was associated with higher age (OR = 1.06 [1.02-1.10]) and APOE ɛ4 allele carriership (OR = 2.99 [1.81-4.94]). These results were similar across prescreen settings.

CONCLUSIONS

Numbers needed to prescreen varied greatly between settings. Understanding how common AD risk factors link to study participation and amyloid positivity is informative for recruitment strategy of studies on secondary prevention of AD.

Predicting Amyloid Burden to Accelerate Recruitment of Secondary Prevention Clinical Trials

BACKGROUND

Screening to identify individuals with elevated brain amyloid (Aβ+) for clinical trials in Preclinical Alzheimer's Disease (PAD), such as the Anti-Amyloid Treatment in Asymptomatic Alzheimer's disease (A4) trial, is slow and costly. The Trial-Ready Cohort in Preclinical/Prodromal Alzheimer's Disease (TRC-PAD) aims to accelerate and reduce costs of AD trial recruitment by maintaining a web-based registry of potential trial participants, and using predictive algorithms to assess their likelihood of suitability for PAD trials.

OBJECTIVES

Here we describe how algorithms used to predict amyloid burden within TRC-PAD project were derived using screening data from the A4 trial.

DESIGN

We apply machine learning techniques to predict amyloid positivity. Demographic variables, APOE genotype, and measures of cognition and function are considered as predictors. Model data were derived from the A4 trial.

SETTING

TRC-PAD data are collected from web-based and in-person assessments and are used to predict the risk of elevated amyloid and assess eligibility for AD trials.

PARTICIPANTS

Pre-randomization, cross-sectional data from the ongoing A4 trial are used to develop statistical models.

MEASUREMENTS

Models use a range of cognitive tests and subjective memory assessments, along with demographic variables. Amyloid positivity in A4 was confirmed using positron emission tomography (PET).

RESULTS

The A4 trial screened N=4,486 participants, of which N=1323 (29%) were classified as Aβ+ (SUVR ≥ 1.15). The Area under the Receiver Operating Characteristic curves for these models ranged from 0.60 (95% CI 0.56 to 0.64) for a web-based battery without APOE to 0.74 (95% CI 0.70 to 0.78) for an in-person battery. The number needed to screen to identify an Aβ+ individual is reduced from 3.39 in A4 to 2.62 in the remote setting without APOE, and 1.61 in the remote setting with APOE.

CONCLUSIONS

Predictive algorithms in a web-based registry can improve the efficiency of screening in future secondary prevention trials. APOE status contributes most to predictive accuracy with cross-sectional data. Blood-based assays of amyloid will likely improve the prediction of amyloid PET positivity.

PET and CSF amyloid-β status are differently predicted by patient features: information from discordant cases

BACKGROUND

Amyloid-β PET and CSF Aβ42 yield discordant results in 10-20% of memory clinic patients, possibly providing unique information. Although the predictive power of demographic, clinical, genetic, and imaging features for amyloid positivity has previously been investigated, it is unknown whether these features differentially predict amyloid-β status based on PET or CSF or whether this differs by disease stage.

METHODS

We included 768 patients (subjective cognitive decline (SCD, n = 194), mild cognitive impairment (MCI, n = 127), dementia (AD and non-AD, n = 447) with amyloid-β PET and CSF Aβ42 measurement within 1 year. Ninety-seven (13%) patients had discordant PET/CSF amyloid-β status. We performed parallel random forest models predicting separately PET and CSF status using 17 patient features (demographics, APOE4 positivity, CSF (p)tau, cognitive performance, and MRI visual ratings) in the total patient group and stratified by syndrome diagnosis. Thereafter, we selected features with the highest variable importance measure (VIM) as input for logistic regression models, where amyloid status on either PET or CSF was predicted by (i) the selected patient feature and (ii) the patient feature adjusted for the status of the other amyloid modality.

RESULTS

APOE4, CSF tau, and p-tau had the highest VIM for PET and CSF in all groups. In the amyloid-adjusted logistic regression models, p-tau was a significant predictor for PET-amyloid in SCD (OR = 1.02 [1.01-1.04], pFDR = 0.03), MCI (OR = 1.05 [1.02-1.07], pFDR < 0.01), and dementia (OR = 1.04 [1.03-1.05], pFDR < 0.001), but not for CSF-amyloid. APOE4 (OR = 3.07 [1.33-7.07], punc < 0.01) was associated with CSF-amyloid in SCD, while it was only predictive for PET-amyloid in MCI (OR = 9.44 [2.93, 30.39], pFDR < 0.01). Worse MMSE scores (OR = 1.21 [1.03-1.41], punc = 0.02) were associated to CSF-amyloid status in SCD, whereas worse memory (OR = 1.17 [1.05-1.31], pFDR = 0.02) only predicted PET positivity in dementia.

CONCLUSION

Amyloid status based on either PET or CSF was predicted by different patient features, and this varied by disease stage, suggesting that PET-CSF discordance yields unique information. The stronger associations of both APOE4 carriership and worse memory z-scores with CSF-amyloid in SCD suggest that CSF-amyloid is more sensitive early in the disease course. The higher predictive value of CSF p-tau for a positive PET scan suggests that PET is more specific to AD pathology.

Performance of Fully Automated Plasma Assays as Screening Tests for Alzheimer Disease-Related β-Amyloid Status

Importance

Accurate blood-based biomarkers for Alzheimer disease (AD) might improve the diagnostic accuracy in primary care, referrals to memory clinics, and screenings for AD trials.

Objective

To examine the accuracy of plasma β-amyloid (Aβ) and tau measured using fully automated assays together with other blood-based biomarkers to detect cerebral Aβ.

Design, Setting, and Participants

Two prospective, cross-sectional, multicenter studies. Study participants were consecutively enrolled between July 6, 2009, and February 11, 2015 (cohort 1), and between January 29, 2000, and October 11, 2006 (cohort 2). Data were analyzed in 2018. The first cohort comprised 842 participants (513 cognitively unimpaired [CU], 265 with mild cognitive impairment [MCI], and 64 with AD dementia) from the Swedish BioFINDER study. The validation cohort comprised 237 participants (34 CU, 109 MCI, and 94 AD dementia) from a German biomarker study.

Main Outcome and Measures

The cerebrospinal fluid (CSF) Aβ42/Aβ40 ratio was used as the reference standard for brain Aβ status. Plasma Aβ42, Aβ40 and tau were measured using Elecsys immunoassays (Roche Diagnostics) and examined as predictors of Aβ status in logistic regression models in cohort 1 and replicated in cohort 2. Plasma neurofilament light chain (NFL) and heavy chain (NFH) and APOE genotype were also examined in cohort 1.

Results

The mean (SD) age of the 842 participants in cohort 1 was 72 (5.6) years, with a range of 59 to 88 years, and 446 (52.5%) were female. For the 237 in cohort 2, mean (SD) age was 66 (10) years with a range of 23 to 85 years, and 120 (50.6%) were female. In cohort 1, plasma Aβ42 and Aβ40 predicted Aβ status with an area under the receiver operating characteristic curve (AUC) of 0.80 (95% CI, 0.77-0.83). When adding APOE, the AUC increased significantly to 0.85 (95% CI, 0.82-0.88). Slight improvements were seen when adding plasma tau (AUC, 0.86; 95% CI, 0.83-0.88) or tau and NFL (AUC, 0.87; 95% CI, 0.84-0.89) to Aβ42, Aβ40 and APOE. The results were similar in CU and cognitively impaired participants, and in younger and older participants. Applying the plasma Aβ42 and Aβ40 model from cohort 1 in cohort 2 resulted in slightly higher AUC (0.86; 95% CI, 0.81-0.91), but plasma tau did not contribute. Using plasma Aβ42, Aβ40, and APOE in an AD trial screening scenario reduced positron emission tomography costs up to 30% to 50% depending on cutoff.

Conclusions and Relevance

Plasma Aβ42 and Aβ40 measured using Elecsys immunoassays predict Aβ status in all stages of AD with similar accuracy in a validation cohort. Their accuracy can be further increased by analyzing APOE genotype. Potential future applications of these blood tests include prescreening of Aβ positivity in clinical AD trials to lower the costs and number of positron emission tomography scans or lumbar punctures.

Reduction of recruitment costs in preclinical AD trials: validation of automatic pre-screening algorithm for brain amyloidosis

We propose a method for recruiting asymptomatic Amyloid positive individuals in clinical trials, using a two-step process. We first select during a pre-screening phase a subset of individuals which are more likely to be amyloid positive based on the automatic analysis of data acquired during routine clinical practice, before doing a confirmatory PET-scan to these selected individuals only. This method leads to an increased number of recruitments and to a reduced number of PET-scans, resulting in a decrease in overall recruitment costs. We validate our method on three different cohorts, and consider five different classification algorithms for the pre-screening phase. We show that the best results are obtained using solely cognitive, genetic and socio-demographic features, as the slight increased performance when using MRI or longitudinal data is balanced by the cost increase they induce. We show that the proposed method generalizes well when tested on an independent cohort, and that the characteristics of the selected set of individuals are identical to the characteristics of a population selected in a standard way. The proposed approach shows how Machine Learning can be used effectively in practice to optimize recruitment costs in clinical trials.

The combination of apolipoprotein E4, age and Alzheimer's Disease Assessment Scale - Cognitive Subscale improves the prediction of amyloid positron emission tomography status in clinically diagnosed mild cognitive impairment

BACKGROUND AND PURPOSE

Randomized clinical trials involving anti-amyloid interventions focus on the early stages of Alzheimer's disease (AD) with proven amyloid pathology, using amyloid positron emission tomography (amyloid-PET) imaging or cerebrospinal fluid analysis. However, these investigations are either expensive or invasive and are not readily available in resource-limited centres. Hence, the identification of cost-effective clinical alternatives to amyloid-PET is highly desirable. This study aimed to investigate the accuracy of combined clinical markers in predicting amyloid-PET status in mild cognitive impairment (MCI) individuals.

METHODS

In all, 406 MCI participants from the Alzheimer's Disease Neuroimaging Initiative database were dichotomized into amyloid-PET(+) and amyloid-PET(-) using a cut-off of >1.11. The accuracies of single clinical markers [apolipoprotein E4 (ApoE4) genotype, demographics, cognitive measures and cerebrospinal fluid analysis] in predicting amyloid-PET status were evaluated using receiver operating characteristic curve analysis. A logistic regression model was then used to determine the optimal model with combined clinical markers to predict amyloid-PET status.

RESULTS

Cerebrospinal fluid amyloid-β (Aβ) showed the best predictive accuracy of amyloid-PET status [area under the curve (AUC) = 0.927]. Whilst ApoE4 genotype (AUC = 0.737) and Alzheimer's Disease Assessment Scale - Cognitive Subscale (ADAS-Cog) 13 (AUC = 0.724) independently discriminated amyloid-PET(+) and amyloid-PET(-) MCI individuals, the combination of clinical markers (ApoE4 carrier, age >60 years and ADAS-Cog 13 > 13.5) improved the predictive accuracy of amyloid-PET status (AUC = 0.827, P < 0.001).

CONCLUSIONS

Cerebrospinal fluid Aβ, which is an invasive procedure, is most accurate in predicting amyloid-PET status in MCI individuals. The combination of ApoE4, age and ADAS-Cog 13 also accurately predicts amyloid-PET status. As this combination of clinical markers is cheap, non-invasive and readily available, it offers an attractive surrogate assessment for amyloid status amongst MCI individuals in resource-limited settings.

The Role of Biomarkers in Alzheimer's Disease Drug Development

Biomarkers have a key role in Alzheimer's disease (AD) drug development. Biomarkers can assist in diagnosis, demonstrate target engagement, support disease modification, and monitor for safety. The amyloid (A), tau (T), neurodegeneration (N) Research Framework emphasizes brain imaging and CSF measures relevant to disease diagnosis and staging and can be applied to drug development and clinical trials. Demonstration of target engagement in Phase 2 is critical before advancing a treatment candidate to Phase 3. Trials with biomarker outcomes are shorter and smaller than those required to show clinical benefit and are important to understanding the biological impact of an agent and inform go/no-go decisions. Companion diagnostics are required for safe and effective use of treatments and may emerge in AD drug development programs. Complementary biomarkers inform the use of therapies but are not mandatory for use. Biomarkers promise to de-risk AD drug development, attract sponsors to AD research, and accelerate getting new drugs to those with or at risk for AD.

Correlations between plasma and PET beta-amyloid levels in individuals with subjective cognitive decline: the Fundació ACE Healthy Brain Initiative (FACEHBI)

BACKGROUND

Peripheral biomarkers that identify individuals at risk of developing Alzheimer's disease (AD) or predicting high amyloid beta (Aβ) brain burden would be highly valuable. To facilitate clinical trials of disease-modifying therapies, plasma concentrations of Aβ species are good candidates for peripheral AD biomarkers, but studies to date have generated conflicting results.

METHODS

The Fundació ACE Healthy Brain Initiative (FACEHBI) study uses a convenience sample of 200 individuals diagnosed with subjective cognitive decline (SCD) at the Fundació ACE (Barcelona, Spain) who underwent amyloid florbetaben(18F) (FBB) positron emission tomography (PET) brain imaging. Baseline plasma samples from FACEHBI subjects (aged 65.9 ± 7.2 years) were analyzed using the ABtest (Araclon Biotech). This test directly determines the free plasma (FP) and total plasma (TP) levels of Aβ40 and Aβ42 peptides. The association between Aβ40 and Aβ42 plasma levels and FBB-PET global standardized uptake value ratio (SUVR) was determined using correlations and linear regression-based methods. The effect of the APOE genotype on plasma Aβ levels and FBB-PET was also assessed. Finally, various models including different combinations of demographics, genetics, and Aβ plasma levels were constructed using logistic regression and area under the receiver operating characteristic curve (AUROC) analyses to evaluate their ability for discriminating which subjects presented brain amyloidosis.

RESULTS

FBB-PET global SUVR correlated weakly but significantly with Aβ42/40 plasma ratios. For TP42/40, this observation persisted after controlling for age and APOE ε4 allele carrier status (R2 = 0.193, p = 1.01E-09). The ROC curve demonstrated that plasma Aβ measurements are not superior to APOE and age in combination in predicting brain amyloidosis. It is noteworthy that using a simple preselection tool (the TP42/40 ratio with an empirical cut-off value of 0.08) optimizes the sensitivity and reduces the number of individuals subjected to Aβ FBB-PET scanners to 52.8%. No significant dependency was observed between APOE genotype and plasma Aβ measurements (p value for interaction = 0.105).

CONCLUSION

Brain and plasma Aβ levels are partially correlated in individuals diagnosed with SCD. Aβ plasma measurements, particularly the TP42/40 ratio, could generate a new recruitment strategy independent of the APOE genotype that would improve identification of SCD subjects with brain amyloidosis and reduce the rate of screening failures in preclinical AD studies. Independent replication of these findings is warranted.

Secondary prevention of Alzheimer's dementia: neuroimaging contributions

BACKGROUND

In Alzheimer's disease (AD), pathological changes may arise up to 20 years before the onset of dementia. This pre-dementia window provides a unique opportunity for secondary prevention. However, exposing non-demented subjects to putative therapies requires reliable biomarkers for subject selection, stratification, and monitoring of treatment. Neuroimaging allows the detection of early pathological changes, and longitudinal imaging can assess the effect of interventions on markers of molecular pathology and rates of neurodegeneration. This is of particular importance in pre-dementia AD trials, where clinical outcomes have a limited ability to detect treatment effects within the typical time frame of a clinical trial. We review available evidence for the use of neuroimaging in clinical trials in pre-dementia AD. We appraise currently available imaging markers for subject selection, stratification, outcome measures, and safety in the context of such populations.

MAIN BODY

Amyloid positron emission tomography (PET) is a validated in-vivo marker of fibrillar amyloid plaques. It is appropriate for inclusion in trials targeting the amyloid pathway, as well as to monitor treatment target engagement. Amyloid PET, however, has limited ability to stage the disease and does not perform well as a prognostic marker within the time frame of a pre-dementia AD trial. Structural magnetic resonance imaging (MRI), providing markers of neurodegeneration, can improve the identification of subjects at risk of imminent decline and hence play a role in subject inclusion. Atrophy rates (either hippocampal or whole brain), which can be reliably derived from structural MRI, are useful in tracking disease progression and have the potential to serve as outcome measures. MRI can also be used to assess comorbid vascular pathology and define homogeneous groups for inclusion or for subject stratification. Finally, MRI also plays an important role in trial safety monitoring, particularly the identification of amyloid-related imaging abnormalities (ARIA). Tau PET to measure neurofibrillary tangle burden is currently under development. Evidence to support the use of advanced MRI markers such as resting-state functional MRI, arterial spin labelling, and diffusion tensor imaging in pre-dementia AD is preliminary and requires further validation.

CONCLUSION

We propose a strategy for longitudinal imaging to track early signs of AD including quantitative amyloid PET and yearly multiparametric MRI.

Accurate risk estimation of β-amyloid positivity to identify prodromal Alzheimer's disease: Cross-validation study of practical algorithms

INTRODUCTION

The aim was to create readily available algorithms that estimate the individual risk of β-amyloid (Aβ) positivity.

METHODS

The algorithms were tested in BioFINDER (n = 391, subjective cognitive decline or mild cognitive impairment) and validated in Alzheimer's Disease Neuroimaging Initiative (n = 661, subjective cognitive decline or mild cognitive impairment). The examined predictors of Aβ status were demographics; cognitive tests; white matter lesions; apolipoprotein E (APOE); and plasma Aβ₄₂/Aβ₄₀, tau, and neurofilament light.

RESULTS

Aβ status was accurately estimated in BioFINDER using age, 10-word delayed recall or Mini-Mental State Examination, and APOE (area under the receiver operating characteristics curve = 0.81 [0.77-0.85] to 0.83 [0.79-0.87]). When validated, the models performed almost identical in Alzheimer's Disease Neuroimaging Initiative (area under the receiver operating characteristics curve = 0.80-0.82) and within different age, subjective cognitive decline, and mild cognitive impairment populations. Plasma Aβ₄₂/Aβ₄₀ improved the models slightly.

DISCUSSION

The algorithms are implemented on http://amyloidrisk.com where the individual probability of being Aβ positive can be calculated. This is useful in the workup of prodromal Alzheimer's disease and can reduce the number needed to screen in Alzheimer's disease trials.

Understanding disease progression and improving Alzheimer's disease clinical trials: Recent highlights from the Alzheimer's Disease Neuroimaging Initiative

INTRODUCTION

The overall goal of the Alzheimer's Disease Neuroimaging Initiative (ADNI) is to validate biomarkers for Alzheimer's disease (AD) clinical trials. ADNI is a multisite, longitudinal, observational study that has collected many biomarkers since 2004. Recent publications highlight the multifactorial nature of late-onset AD. We discuss selected topics that provide insights into AD progression and outline how this knowledge may improve clinical trials.

METHODS

We used standard methods to identify nearly 600 publications using ADNI data from 2016 and 2017 (listed in Supplementary Material and searchable at http://adni.loni.usc.edu/news-publications/publications/).

RESULTS

(1) Data-driven AD progression models supported multifactorial interactions rather than a linear cascade of events. (2) β-Amyloid (Aβ) deposition occurred concurrently with functional connectivity changes within the default mode network in preclinical subjects and was followed by specific and progressive disconnection of functional and anatomical networks. (3) Changes in functional connectivity, volumetric measures, regional hypometabolism, and cognition were detectable at subthreshold levels of Aβ deposition. 4. Tau positron emission tomography imaging studies detailed a specific temporal and spatial pattern of tau pathology dependent on prior Aβ deposition, and related to subsequent cognitive decline. 5. Clustering studies using a wide range of modalities consistently identified a "typical AD" subgroup and a second subgroup characterized by executive impairment and widespread cortical atrophy in preclinical and prodromal subjects. 6. Vascular pathology burden may act through both Aβ dependent and independent mechanisms to exacerbate AD progression. 7. The APOE ε4 allele interacted with cerebrovascular disease to impede Aβ clearance mechanisms. 8. Genetic approaches identified novel genetic risk factors involving a wide range of processes, and demonstrated shared genetic risk for AD and vascular disorders, as well as the temporal and regional pathological associations of established AD risk alleles. 9. Knowledge of early pathological changes guided the development of novel prognostic biomarkers for preclinical subjects. 10. Placebo populations of randomized controlled clinical trials had highly variable trajectories of cognitive change, underscoring the importance of subject selection and monitoring. 11. Selection criteria based on Aβ positivity, hippocampal volume, baseline cognitive/functional measures, and APOE ε4 status in combination with improved cognitive outcome measures were projected to decrease clinical trial duration and cost. 12. Multiple concurrent therapies targeting vascular health and other AD pathology in addition to Aβ may be more effective than single therapies.

DISCUSSION

ADNI publications from 2016 and 2017 supported the idea of AD as a multifactorial disease and provided insights into the complexities of AD disease progression. These findings guided the development of novel biomarkers and suggested that subject selection on the basis of multiple factors may lower AD clinical trial costs and duration. The use of multiple concurrent therapies in these trials may prove more effective in reversing AD disease progression.

MRI predictors of amyloid pathology: results from the EMIF-AD Multimodal Biomarker Discovery study

BACKGROUND

With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) ε4 genotype, can be used to predict amyloid pathology using machine-learning classification.

METHODS

We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 ± 7.2, 50% female, 27% amyloid positive), mild cognitive impairment (MCI, n = 375, age 69.1 ± 7.5, 53% female, 63% amyloid positive) and AD dementia (n = 98, age 67.0 ± 7.7, 48% female, 97% amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE ε4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects.

RESULTS

In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 ± 0.07 in MCI and an AUC of 0.74 ± 0.08 in CN. In CN, selected features for the classifier included APOE ε4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE ε4 information did not improve after additionally adding imaging measures.

CONCLUSIONS

Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE ε4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.

Prevalence of the apolipoprotein E ε4 allele in amyloid β positive subjects across the spectrum of Alzheimer's disease

INTRODUCTION

Apolipoprotein E (APOE) ε4 is the major genetic risk factor for Alzheimer's disease (AD), but its prevalence is unclear because earlier studies did not require biomarker evidence of amyloid β (Aβ) pathology.

METHODS

We included 3451 Aβ+ subjects (853 AD-type dementia, 1810 mild cognitive impairment, and 788 cognitively normal). Generalized estimating equation models were used to assess APOE ε4 prevalence in relation to age, sex, education, and geographical location.

RESULTS

The APOE ε4 prevalence was 66% in AD-type dementia, 64% in mild cognitive impairment, and 51% in cognitively normal, and it decreased with advancing age in Aβ+ cognitively normal and Aβ+ mild cognitive impairment (P < .05) but not in Aβ+ AD dementia (P = .66). The prevalence was highest in Northern Europe but did not vary by sex or education.

DISCUSSION

The APOE ε4 prevalence in AD was higher than that in previous studies, which did not require presence of Aβ pathology. Furthermore, our results highlight disease heterogeneity related to age and geographical location.

Plasma amyloid β 42/40 ratios as biomarkers for amyloid β cerebral deposition in cognitively normal individuals

INTRODUCTION

Plasma amyloid β (Aβ) peptides have been previously studied as candidate biomarkers to increase recruitment efficiency in secondary prevention clinical trials for Alzheimer's disease.

METHODS

Free and total Aβ42/40 plasma ratios (FP42/40 and TP42/40, respectively) were determined using ABtest assays in cognitively normal subjects from the Australian Imaging, Biomarker and Lifestyle Flagship Study. This population was followed-up for 72 months and their cortical Aβ burden was assessed with positron emission tomography.

RESULTS

Cross-sectional and longitudinal analyses showed an inverse association of Aβ42/40 plasma ratios and cortical Aβ burden. Optimized as a screening tool, TP42/40 reached 81% positive predictive value of high cortical Aβ burden, which represents 110% increase over the population prevalence of cortical Aβ positivity.

DISCUSSION

These findings support the use of plasma Aβ42/40 ratios as surrogate biomarkers of cortical Aβ deposition and enrichment tools, reducing the number of subjects submitted to invasive tests and, consequently, recruitment costs in clinical trials targeting cognitively normal individuals.

Time to Amyloid Positivity and Preclinical Changes in Brain Metabolism, Atrophy, and Cognition: Evidence for Emerging Amyloid Pathology in Alzheimer's Disease

Background: Aβ pathology is associated with longitudinal changes of brain metabolism, atrophy, and cognition, in cognitively healthy elders. However, Aβ information is usually measured cross-sectionally and dichotomized to classify subjects as Aβ-positive or Aβ-negative, making it difficult to evaluate when brain and cognitive changes occur with respect to emerging Aβ pathology. In this study, we use longitudinal Aβ information to combine the level and rate of change of Aβ to estimate the time to Aβ-positivity for each subject and test this temporal proximity to significant Aβ pathology for associations with brain structure, metabolism, and cognition. Methods: In 89 cognitively healthy elders with up to 10 years of follow-up, we estimated the points at which rates of fluorodeoxyglucose (FDG) PET, MRI, and cognitive and functional decline begin to accelerate with respect to the time to Aβ-positivity. Points of initial acceleration in rates of decline were estimated using mixed-effects models with penalized regression splines. Results: Acceleration of rates of FDG PET were observed to occur 20+ years before the conventional threshold for Aβ-positivity. Subtle signs of cognitive dysfunction were observed 10+ years before Aβ-positivity. Conclusions: Aβ may have subtle associations with other hallmarks of Alzheimer's disease before Aβ biomarkers reach conventional thresholds for Aβ-positivity. Therefore, we propose that emerging Aβ pathology occurs many years before cognitively healthy elders reach the current threshold for Aβ positivity (preclinical AD). To allow prevention in the earliest disease stages, AD clinical trials may be designed to also include subjects with Aβ biomarkers in the sub-threshold range.

Qualitative and quantitative assessment of self-reported cognitive difficulties in nondemented elders: Association with medical help seeking, cognitive deficits, and β-amyloid imaging

Introduction

Subjective cognitive decline (SCD) could help identify early stages of Alzheimer's disease. However, SCD is multidetermined and protean, and the type of cognitive complaint associated with preclinical Alzheimer's disease needs refinement.

Methods

A total of 185 nondemented elders recruited from either the community or from a memory clinic filled a questionnaire. We searched for item responses associated with medical help seeking, cognitive deficits, and β-amyloidosis.

Results

Compared with community-recruited control subjects (n = 74), help-seeking patients reported a stronger multidomain SCD that was mostly unrelated to the presence of detectable cognitive deficits. Only a few items, notably assessing temporal disorientation, distinguished help-seeking patients with (n = 78) or without (n = 33) memory deficits. Associations between SCD and β-amyloidosis were not restricted to the memory domain and varied across clinical stages.

Discussion

Detailed evaluation of SCD could provide accessible indication of the presence of β-amyloid or cognitive deficits, which might prove useful for early diagnosis and clinical trial enrichment strategies.