Which MCI Patients Should be Included in Prodromal Alzheimer Disease Clinical Trials?

Comparison of deep learning architectures for predicting amyloid positivity in Alzheimer's disease, mild cognitive impairment, and healthy aging, from T1-weighted brain structural MRI

Abnormal β-amyloid (Aβ) accumulation in the brain is an early indicator of Alzheimer's disease (AD) and is typically assessed through invasive procedures such as PET (positron emission tomography) or CSF (cerebrospinal fluid) assays. As new anti-Alzheimer's treatments can now successfully target amyloid pathology, there is a growing interest in predicting Aβ positivity (Aβ+) from less invasive, more widely available types of brain scans, such as T1-weighted (T1w) MRI. Here we compare multiple approaches to infer Aβ + from standard anatomical MRI: (1) classical machine learning algorithms, including logistic regression, XGBoost, and shallow artificial neural networks, (2) deep learning models based on 2D and 3D convolutional neural networks (CNNs), (3) a hybrid ANN-CNN, combining the strengths of shallow and deep neural networks, (4) transfer learning models based on CNNs, and (5) 3D Vision Transformers. All models were trained on paired MRI/PET data from 1,847 elderly participants (mean age: 75.1 yrs. ± 7.6SD; 863 females/984 males; 661 healthy controls, 889 with mild cognitive impairment (MCI), and 297 with Dementia), scanned as part of the Alzheimer's Disease Neuroimaging Initiative. We evaluated each model's balanced accuracy and F1 scores. While further tests on more diverse data are warranted, deep learning models trained on standard MRI showed promise for estimating Aβ + status, at least in people with MCI. This may offer a potential screening option before resorting to more invasive procedures.

Racial and ethnic differences in plasma biomarker eligibility for a preclinical Alzheimer's disease trial

INTRODUCTION

In trials of amyloid-lowering drugs for Alzheimer's disease (AD), differential eligibility may contribute to under-inclusion of racial and ethnic underrepresented groups. We examined plasma amyloid beta 42/40 and positron emission tomography (PET) amyloid eligibility for the ongoing AHEAD Study preclinical AD program (NCT04468659).

METHODS

Univariate logistic regression models were used to examine group differences in plasma and PET amyloid screening eligibility.

RESULTS

Of 4905 participants screened at time of analysis, 1724 were plasma eligible to continue in screening: 13.3% Hispanic Black, 24.7% Hispanic White, 20.8% non-Hispanic (NH) Asian, 24.7% NH Black, and 38.9% NH White. Plasma eligibility differed across groups in models controlling for covariates (odds ratio from 1.9 to 4.0 compared to the NH White reference group, P < 0.001). Among plasma eligible participants, PET eligibility did not differ by group.

DISCUSSION

These results suggest that prevalence of brain amyloid pathology differed, but that eligibility based on plasma was equally effective across racial and ethnic group members.

HIGHLIGHTS

Plasma amyloid eligibility is lower in underrepresented racial and ethnic groups. In plasma eligible adults, positron emission tomography eligibility rates are similar across race and ethnicity. Plasma biomarker tests may be similarly effective across racial and ethnic groups.

Sociotechnical feasibility of natural language processing-driven tools in clinical trial eligibility prescreening for Alzheimer's disease and related dementias

BACKGROUND

Alzheimer's disease and related dementias (ADRD) affect over 55 million globally. Current clinical trials suffer from low recruitment rates, a challenge potentially addressable via natural language processing (NLP) technologies for researchers to effectively identify eligible clinical trial participants.

OBJECTIVE

This study investigates the sociotechnical feasibility of NLP-driven tools for ADRD research prescreening and analyzes the tools' cognitive complexity's effect on usability to identify cognitive support strategies.

METHODS

A randomized experiment was conducted with 60 clinical research staff using three prescreening tools (Criteria2Query, Informatics for Integrating Biology and the Bedside [i2b2], and Leaf). Cognitive task analysis was employed to analyze the usability of each tool using the Health Information Technology Usability Evaluation Scale. Data analysis involved calculating descriptive statistics, interrater agreement via intraclass correlation coefficient, cognitive complexity, and Generalized Estimating Equations models.

RESULTS

Leaf scored highest for usability followed by Criteria2Query and i2b2. Cognitive complexity was found to be affected by age, computer literacy, and number of criteria, but was not significantly associated with usability.

DISCUSSION

Adopting NLP for ADRD prescreening demands careful task delegation, comprehensive training, precise translation of eligibility criteria, and increased research accessibility. The study highlights the relevance of these factors in enhancing NLP-driven tools' usability and efficacy in clinical research prescreening.

CONCLUSION

User-modifiable NLP-driven prescreening tools were favorably received, with system type, evaluation sequence, and user's computer literacy influencing usability more than cognitive complexity. The study emphasizes NLP's potential in improving recruitment for clinical trials, endorsing a mixed-methods approach for future system evaluation and enhancements.

Diagnostic Performance of a Tablet Computer-Based Cognitive Screening Test for Identification of Amnestic Mild Cognitive Impairment

BACKGROUND

Early and appropriate diagnosis of amnestic mild cognitive impairment (aMCI) is clinically important because aMCI is considered the prodromal stage of dementia caused by Alzheimer's disease (AD). aMCI is assessed using the comprehensive neuropsychological (NP) battery, but it is rater-dependent and does not provide quick results. Thus, we investigated the performance of the computerized cognitive screening test (Inbrain Cognitive Screening Test; Inbrain CST) in the diagnosis of aMCI and compared its performance to that of the Korean version of the Consortium to Establish a Registry for Alzheimer's Disease (CERAD) test (CERAD-K), a comprehensive and pencil-and-paper NP test.

METHODS

A total of 166 participants were included in this cross-sectional study. The participants were recruited as part of a prospective, community-based cohort study for MCI (PREcision medicine platform for mild cognitive impairment on multi-omics, imaging, evidence-based R&BD; PREMIER). All participants were assessed using the CERAD-K and the Inbrain CST. The Inbrain CST comprised seven subtests that assessed the following five cognitive domains: attention, language, visuospatial, memory, and executive functions. Seventy-six participants underwent brain magnetic resonance imaging and [18F]-flutemetamol positron emission tomography (PET). We evaluated the diagnostic performance of the Inbrain CST for the identification of aMCI by comparing the findings with those of CERAD-K. We also determined the characteristics of aMCI patients as defined by the CERAD-K and Inbrain CST.

RESULTS

Of the 166 participants, 93 were diagnosed with aMCI, while 73 were cognitively unimpaired. The sensitivity of the Inbrain CST for aMCI diagnosis was 81.7%, and its specificity was 84.9%. Positive and negative predictive values were 87.4% and 78.5%, respectively. The diagnostic accuracy was 83.1%, and the error rate was 16.9%. Demographic and clinical characteristics between individuals with aMCI defined by the Inbrain CST and CERAD-K were not significantly different. The frequency of positive amyloid PET scan, the hippocampal/parahippocampal volumes, and AD signature cortical thickness did not differ between the patients with aMCI defined by CERAD-K and those with aMCI defined by the Inbrain CST.

CONCLUSION

The Inbrain CST showed sufficient sensitivity, specificity, and positive and negative predictive values for diagnosing objective memory impairment in aMCI. In addition, aMCI patients identified by CERAD-K and the Inbrain CST showed comparable clinical and neuroimaging characteristics. Therefore, the Inbrain CST can be considered an alternative test to supplement the limitations of existing pencil-and-paper NP tests.

Digital biomarkers and sex impacts in Alzheimer's disease management - potential utility for innovative 3P medicine approach

Digital biomarkers are defined as objective, quantifiable physiological and behavioral data that are collected and measured by means of digital devices. Their use has revolutionized clinical research by enabling high-frequency, longitudinal, and sensitive measurements. In the field of neurodegenerative diseases, an example of a digital biomarker-based technology is instrumental activities of daily living (iADL) digital medical application, a predictive biomarker of conversion from mild cognitive impairment (MCI) due to Alzheimer's disease (AD) to dementia due to AD in individuals aged 55 + . Digital biomarkers show promise to transform clinical practice. Nevertheless, their use may be affected by variables such as demographics, genetics, and phenotype. Among these factors, sex is particularly important in Alzheimer's, where men and women present with different symptoms and progression patterns that impact diagnosis. In this study, we explore sex differences in Altoida's digital medical application in a sample of 568 subjects consisting of a clinical dataset (MCI and dementia due to AD) and a healthy population. We found that a biological sex-classifier, built on digital biomarker features captured using Altoida's application, achieved a 75% ROC-AUC (receiver operating characteristic - area under curve) performance in predicting biological sex in healthy individuals, indicating significant differences in neurocognitive performance signatures between males and females. The performance dropped when we applied this classifier to more advanced stages on the AD continuum, including MCI and dementia, suggesting that sex differences might be disease-stage dependent. Our results indicate that neurocognitive performance signatures built on data from digital biomarker features are different between men and women. These results stress the need to integrate traditional approaches to dementia research with digital biomarker technologies and personalized medicine perspectives to achieve more precise predictive diagnostics, targeted prevention, and customized treatment of cognitive decline.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-022-00284-3.

Using the Alzheimer's Disease Neuroimaging Initiative to improve early detection, diagnosis, and treatment of Alzheimer's disease

INTRODUCTION

The Alzheimer's Disease Neuroimaging Initiative (ADNI) has accumulated 15 years of clinical, neuroimaging, cognitive, biofluid biomarker and genetic data, and biofluid samples available to researchers, resulting in more than 3500 publications. This review covers studies from 2018 to 2020.

METHODS

We identified 1442 publications using ADNI data by conventional search methods and selected impactful studies for inclusion.

RESULTS

Disease progression studies supported pivotal roles for regional amyloid beta (Aβ) and tau deposition, and identified underlying genetic contributions to Alzheimer's disease (AD). Vascular disease, immune response, inflammation, resilience, and sex modulated disease course. Biologically coherent subgroups were identified at all clinical stages. Practical algorithms and methodological changes improved determination of Aβ status. Plasma Aβ, phosphorylated tau181, and neurofilament light were promising noninvasive biomarkers. Prognostic and diagnostic models were externally validated in ADNI but studies are limited by lack of ethnocultural cohort diversity.

DISCUSSION

ADNI has had a profound impact in improving clinical trials for AD.

Enhanced Association of Tau Pathology and Cognitive Impairment in Mild Cognitive Impairment Subjects with Behavior Symptoms

BACKGROUND

Mild cognitive impairment (MCI) individuals with neuropsychiatric symptoms (NPS) are more likely to develop dementia.

OBJECTIVE

We sought to understand the relationship between neuroimaging markers such as tau pathology and cognitive symptoms both with and without the presence of NPS during the prodromal period of Alzheimer's disease.

METHODS

A total of 151 MCI subjects with tau positron emission tomographic (PET) scanning with 18F AV-1451, amyloid-β (Aβ) PET scanning with florbetapir or florbetaben, magnetic resonance imaging, and cognitive and behavioral evaluations were selected from the Alzheimer's Disease Neuroimaging Initiative. A 4-group division approach was proposed using amyloid (A-/A+) and behavior (B-/B+) status: A-B-, A-B+, A+B-, and A+B+. Pearson's correlation test was conducted for each group to examine the association between tau deposition and cognitive performance.

RESULTS

No statistically significant association between tau deposition and cognitive impairment was found for subjects without behavior symptoms in either the A-B-or A+B-groups after correction for false discovery rate. In contrast, tau deposition was found to be significantly associated with cognitive impairment in entorhinal cortex and temporal pole for the A-B+ group and nearly the whole cerebrum for the A+B+ group.

CONCLUSION

Enhanced associations between tauopathy and cognitive impairment are present in MCI subjects with behavior symptoms, which is more prominent in the presence of elevated amyloid pathology. MCI individuals with NPS may thus be at greater risk for further cognitive decline with the increase of tau deposition in comparison to those without NPS.

A three-range approach enhances the prognostic utility of CSF biomarkers in Alzheimer's disease

Introduction

Alzheimer's disease consensus recommends biomarker dichotomization, a practice with well-described clinical strengths and methodological limitations. Although neuroimaging studies have explored alternative biomarker interpretation strategies, a formally defined three-range approach and its prognostic impact remains under-explored for cerebrospinal fluid (CSF) biomarkers .

Methods

With two-graph receiver-operating characteristics based on different reference schemes, we derived three-range cut-points for CSF Elecsys biomarkers. According to baseline CSF status, we assessed the prognostic utility of this in predicting risk of clinical progression and longitudinal trajectories of cognitive decline and amyloid-beta (Aβ) positron emission tomography (PET) accumulation in non-demented individuals (Alzheimer's Disease Neuroimaging Initiative [ADNI]; n = 1246). In all analyses, we compared herein-derived three-range CSF cut-points to previously described binary ones.

Results

In our main longitudinal analyses, we highlight CSF p-tau181/Aβ1-42 three-range cut-points derived based on the cognitively normal Aβ-PET negative versus dementia Aβ-PET positive reference scheme for best depicting a prognostically relevant biomarker abnormality range. Longitudinally, our approach revealed a divergent intermediate cognitive trajectory undetected by dichotomization and a clearly abnormal group at higher risk for cognitive decline, with power analyses suggesting the latter group as potential trial enrichment candidates. Furthermore, we demonstrate that individuals with intermediate-range CSF status have similar rates of Aβ deposition to those in the clearly abnormal group.

Discussion

The proposed approach can refine clinico-biological prognostic assessment and potentially enhance trial recruitment, as it captures faster biomarker-related cognitive decline in comparison to binary cut-points. Although this approach has implications for trial recruitment and observational studies, further discussion is needed regarding clinical practice applications.

On the design of early-phase Alzheimer's disease clinical trials with cerebrospinal fluid tau outcomes

BACKGROUND/AIMS

The focus of Alzheimer's disease studies has shifted to earlier disease stages, including mild cognitive impairment. Biomarker inclusion criteria are often incorporated into mild cognitive impairment clinical trials to identify individuals with "prodromal Alzheimer's disease" to ensure appropriate drug targets and enrich for participants likely to develop Alzheimer's disease dementia. The use of these eligibility criteria may affect study power.

METHODS

We investigated outcome variability and study power in the setting of proof-of-concept prodromal Alzheimer's disease trials that incorporate cerebrospinal fluid levels of total tau (t-tau) and phosphorylated (p-tau) as primary outcomes and how differing biomarker inclusion criteria affect power. We used data from the Alzheimer's Disease Neuroimaging Initiative to model trial scenarios and to estimate the variance and within-subject correlation of total and phosphorylated tau. These estimates were then used to investigate the differences in study power for trials considering these two surrogate outcomes.

RESULTS

Patient characteristics were similar for all eligibility criteria. The lowest outcome variance and highest within-subject correlation were obtained when phosphorylated tau was used as an eligibility criterion, compared to amyloid beta or total tau, regardless of whether total tau or phosphorylated tau were used as primary outcomes. Power increased when eligibility criteria were broadened to allow for enrollment of subjects with either low amyloid beta or high phosphorylated tau.

CONCLUSION

Specific biomarker inclusion criteria may impact statistical power in trials using total tau or phosphorylated tau as the primary outcome. In concert with other important considerations such as treatment target and population of clinical interest, these results may have implications to the integrity and efficiency of prodromal Alzheimer's disease trial designs.

Research diagnostic criteria for Alzheimer's disease: findings from the LipiDiDiet randomized controlled trial

Background

To explore the utility of the International Working Group (IWG)-1 criteria in recruitment for Alzheimer’s disease (AD) clinical trials, we applied the more recently proposed research diagnostic criteria to individuals enrolled in a randomized controlled prevention trial (RCT) and assessed their disease progression.

Methods

The multinational LipiDiDiet RCT targeted 311 individuals with IWG-1 defined prodromal AD. Based on centrally analyzed baseline biomarkers, participants were classified according to the IWG-2 and National Institute on Aging–Alzheimer’s Association (NIA-AA) 2011 and 2018 criteria. Linear mixed models were used to investigate the 2-year change in cognitive and functional performance (Neuropsychological Test Battery NTB Z scores, Clinical Dementia Rating-Sum of Boxes CDR-SB) (criteria × time interactions; baseline score, randomization group, sex, Mini-Mental State Examination (MMSE), and age also included in the models). Cox models adjusted for randomization group, MMSE, sex, age, and study site were used to investigate the risk of progression to dementia over 2 years.

Results

In total, 88%, 86%, and 69% of participants had abnormal cerebrospinal fluid (CSF) β-amyloid, total tau, and phosphorylated tau, respectively; 64% had an A+T+N+ profile (CSF available for N = 107). Cognitive-functional decline appeared to be more pronounced in the IWG-2 prodromal AD, NIA-AA 2011 high and intermediate AD likelihood, and NIA-AA 2018 AD groups, but few significant differences were observed between the groups within each set of criteria. Hazard ratio (95% CI) for dementia was 4.6 (1.6–13.7) for IWG-2 prodromal AD (reference group no prodromal AD), 7.4 (1.0–54.7) for NIA-AA 2011 high AD likelihood (reference group suspected non-AD pathology SNAP), and 9.4 (1.2–72.7) for NIA-AA 2018 AD (reference group non-Alzheimer’s pathologic change). Compared with the NIA-AA 2011 high AD likelihood group (abnormal β-amyloid and neuronal injury markers), disease progression was similar in the intermediate AD likelihood group (medial temporal lobe atrophy; no CSF available).

Conclusions

Despite being less restrictive than the other criteria, the IWG-1 criteria reliably identified individuals with AD pathology. More pragmatic and easily applicable selection criteria might be preferred due to feasibility in certain situations, e.g., in multidomain prevention trials that do not specifically target β-amyloid/tau pathologies.

Trial registration

Netherlands Trial Register, NL1620. Registered on 9 March 2009

Anterolateral entorhinal cortex thickness as a new biomarker for early detection of Alzheimer's disease

INTRODUCTION

Loss of entorhinal cortex (EC) layer II neurons represents the earliest Alzheimer's disease (AD) lesion in the brain. Research suggests differing functional roles between two EC subregions, the anterolateral EC (aLEC) and the posteromedial EC (pMEC).

METHODS

We use joint label fusion to obtain aLEC and pMEC cortical thickness measurements from serial magnetic resonance imaging scans of 775 ADNI-1 participants (219 healthy; 380 mild cognitive impairment; 176 AD) and use linear mixed-effects models to analyze longitudinal associations among cortical thickness, disease status, and cognitive measures.

RESULTS

Group status is reliably predicted by aLEC thickness, which also exhibits greater associations with cognitive outcomes than does pMEC thickness. Change in aLEC thickness is also associated with cerebrospinal fluid amyloid and tau levels.

DISCUSSION

Thinning of aLEC is a sensitive structural biomarker that changes over short durations in the course of AD and tracks disease severity-it is a strong candidate biomarker for detection of early AD.

Digital biomarker-based individualized prognosis for people at risk of dementia

Background

Research investigating treatments and interventions for cognitive decline fail due to difficulties in accurately recognizing behavioral signatures in the presymptomatic stages of the disease. For this validation study, we took our previously constructed digital biomarker‐based prognostic models and focused on generalizability and robustness of the models.

Method

We validated prognostic models characterizing subjects using digital biomarkers in a longitudinal, multi‐site, 40‐month prospective study collecting data in memory clinics, general practitioner offices, and home environments.

Results

Our models were able to accurately discriminate between healthy subjects and individuals at risk to progress to dementia within 3 years. The model was also able to differentiate between people with or without amyloid neuropathology and classify fast and slow cognitive decliners with a very good diagnostic performance.

Conclusion

Digital biomarker prognostic models can be a useful tool to assist large‐scale population screening for the early detection of cognitive impairment and patient monitoring over time.