Effects of Delay Duration on the WMS Logical Memory Performance of Older Adults with Probable Alzheimer's Disease, Probable Vascular Dementia, and Normal Cognition

A Transformer Approach for Cognitive Impairment Classification and Prediction

INTRODUCTION

Early classification and prediction of Alzheimer disease (AD) and amnestic mild cognitive impairment (aMCI) with noninvasive approaches is a long-standing challenge. This challenge is further exacerbated by the sparsity of data needed for modeling. Deep learning methods offer a novel method to help address these challenging multiclass classification and prediction problems.

METHODS

We analyzed 3 target feature-sets from the National Alzheimer Coordinating Center (NACC) dataset: (1) neuropsychological (cognitive) data; (2) patient health history data; and (3) the combination of both sets. We used a masked Transformer-encoder without further feature selection to classify the samples on cognitive status (no cognitive impairment, aMCI, AD)-dynamically ignoring unavailable features. We then fine-tuned the model to predict the participants' future diagnosis in 1 to 3 years. We analyzed the sensitivity of the model to input features via Feature Permutation Importance.

RESULTS

We demonstrated (1) the masked Transformer-encoder was able to perform prediction with sparse input data; (2) high multiclass current cognitive status classification accuracy (87% control, 79% aMCI, 89% AD); (3) acceptable results for 1- to 3-year multiclass future cognitive status prediction (83% control, 77% aMCI, 91% AD).

CONCLUSION

The flexibility of our methods in handling inconsistent data provides a new venue for the analysis of cognitive status data.

Investigating the effects of age and prior military service on fluid and crystallized cognitive functions using virtual morris water maze (vMWM) and NIH Toolbox tasks

Much of current knowledge of aging involves war veterans and research about age-related cognitive changes in veterans involves generalized or single function tests or health or neurological disorders. The current study examined military service within the context of comparisons of young and old humans involving generally healthy individuals to address normal age-associated cognitive changes. Adult participants included 11 young females (8 non-veterans; 3 veterans; 21-31 years), 5 young males (non-veterans, 21-24 years), 9 older females (non-veterans, 62-80 years), and 21 older males (11 non-veterans; 10 veterans; 60-86 years). They were tested in virtual Morris water maze (vMWM) tasks, which were designed to test spatial learning, cognitive flexibility and working memory, similar to rodent studies, and were validated by correlations with specific NIH Toolbox (NIH-TB) Cognitive Battery or Wechsler Memory Scale (WMS) Logical Memory I and II tests. Significant age-related deficits were seen on multiple vMWM tasks and NIH-TB fluid cognition tasks. Among older males, vMWM tasks appeared to be more sensitive, based on finding statistical differences, to prior military service than NIH Toolbox tasks. Compared with male non-veterans of comparable age and younger, older male veterans exhibited significant deficits in spatial learning, cognitive flexibility, and working memory on vMWM tasks. Our findings support continued development and characterization of vMWM tasks that are comparable between rodents and humans for translating aging interventions between species, and provide impetus for larger investigations examining the extent to which prior military service can serve as a "hidden" variable in normal biological declines of cognitive functions.

The Alzheimer's Disease Neuroimaging Initiative and the role and contributions of the Private Partners Scientific Board (PPSB)

The Alzheimer's Disease Neuroimaging Initiative (ADNI) Private Partners Scientific Board (PPSB) encompasses members from industry, biotechnology, diagnostic, and non-profit organizations that have until recently been managed by the Foundation for the National Institutes of Health (FNIH) and provided financial and scientific support to ADNI programs. In this article, we review some of the major activities undertaken by the PPSB, focusing on those supporting the most recently completed National Institute on Aging grant, ADNI3, and the impact it has had on streamlining biomarker discovery and validation in Alzheimer's disease. We also provide a perspective on the gaps that may be filled with future PPSB activities as part of ADNI4 and beyond. HIGHLIGHTS: The Private Partners Scientific board (PPSB) continues to play a key role in enabling several Alzheimer's Disease Neuroimaging Initiative (ADNI) activities. PPSB working groups have led landscape assessments to provide valuable feedback on new technologies, platforms, and methods that may be taken up by ADNI in current or future iterations.

Leveraging speech and artificial intelligence to screen for early Alzheimer's disease and amyloid beta positivity

Early detection of Alzheimer's disease is required to identify patients suitable for disease-modifying medications and to improve access to non-pharmacological preventative interventions. Prior research shows detectable changes in speech in Alzheimer's dementia and its clinical precursors. The current study assesses whether a fully automated speech-based artificial intelligence system can detect cognitive impairment and amyloid beta positivity, which characterize early stages of Alzheimer's disease. Two hundred participants (age 54-85, mean 70.6; 114 female, 86 male) from sister studies in the UK (NCT04828122) and the USA (NCT04928976), completed the same assessments and were combined in the current analyses. Participants were recruited from prior clinical trials where amyloid beta status (97 amyloid positive, 103 amyloid negative, as established via PET or CSF test) and clinical diagnostic status was known (94 cognitively unimpaired, 106 with mild cognitive impairment or mild Alzheimer's disease). The automatic story recall task was administered during supervised in-person or telemedicine assessments, where participants were asked to recall stories immediately and after a brief delay. An artificial intelligence text-pair evaluation model produced vector-based outputs from the original story text and recorded and transcribed participant recalls, quantifying differences between them. Vector-based representations were fed into logistic regression models, trained with tournament leave-pair-out cross-validation analysis to predict amyloid beta status (primary endpoint), mild cognitive impairment and amyloid beta status in diagnostic subgroups (secondary endpoints). Predictions were assessed by the area under the receiver operating characteristic curve for the test result in comparison with reference standards (diagnostic and amyloid status). Simulation analysis evaluated two potential benefits of speech-based screening: (i) mild cognitive impairment screening in primary care compared with the Mini-Mental State Exam, and (ii) pre-screening prior to PET scanning when identifying an amyloid positive sample. Speech-based screening predicted amyloid beta positivity (area under the curve = 0.77) and mild cognitive impairment or mild Alzheimer's disease (area under the curve = 0.83) in the full sample, and predicted amyloid beta in subsamples (mild cognitive impairment or mild Alzheimer's disease: area under the curve = 0.82; cognitively unimpaired: area under the curve = 0.71). Simulation analyses indicated that in primary care, speech-based screening could modestly improve detection of mild cognitive impairment (+8.5%), while reducing false positives (-59.1%). Furthermore, speech-based amyloid pre-screening was estimated to reduce the number of PET scans required by 35.3% and 35.5% in individuals with mild cognitive impairment and cognitively unimpaired individuals, respectively. Speech-based assessment offers accessible and scalable screening for mild cognitive impairment and amyloid beta positivity.

A Brief Period of Wakeful Rest after Learning Enhances Verbal Memory in Stroke Survivors

OBJECTIVE

Accumulating evidence suggests that wakeful rest (a period of minimal cognitive stimulation) enhances memory in clinical populations with memory impairment. However, no study has previously examined the efficacy of this technique in stroke survivors, despite the high prevalence of post-stroke memory difficulties. We aimed to investigate whether wakeful rest enhances verbal memory in stroke survivors and healthy controls.

METHOD

Twenty-four stroke survivors and 24 healthy controls were presented with two short stories; one story was followed by a 10-minute period of wakeful rest and the other was followed by a 10-minute visual interference task. A mixed factorial analysis of variance (ANOVA) with pairwise comparisons was used to compare participants' story retention at two time points.

RESULTS

After 15-30 minutes, stroke survivors (p = .002, d = .73), and healthy controls (p = .001, d = .76) retained more information from the story followed by wakeful rest, compared with the story followed by an interference task. While wakeful rest remained the superior condition in healthy controls after 7 days (p = .01, d = .58), the beneficial effect was not maintained in stroke survivors (p = .35, d = .19).

CONCLUSIONS

Wakeful rest is a promising technique, which significantly enhanced verbal memory after 15-30 minutes in both groups; however, no significant benefit of wakeful rest was observed after 7 days in stroke survivors. Preliminary findings suggest that wakeful rest enhances early memory consolidation processes by protecting against the effects of interference after learning in stroke survivors.

In vivo mitochondrial and glycolytic impairments in patients with Alzheimer disease

Objective

In vivo glycolysis-related glucose metabolism and electron transport chain-related mitochondrial activity may be different regionally in the brains of patients with Alzheimer disease (AD). To test this hypothesis regarding AD pathophysiology, we measured the availability of mitochondrial complex-I (MC-I) with the novel PET probe [18F]2-tert- butyl-4-chloro-5–2H- pyridazin-3-one ([18F]BCPP-EF), which binds to MC-I, and compared [18F]BCPP-EF uptake with 18F-fluorodeoxyglucose ([18F]FDG) uptake in the living AD brain.

Methods

First, the total distribution volume (VT) of [18F]BCPP-EF from 10 normal controls (NCs) was quantified using arterial blood samples and then tested to observe whether VT could substitute for the standard uptake value relative to the global count (SUVRg). Eighteen NCs and 14 different NCs underwent PET with [18F]BCPP-EF or [18F]FDG, respectively. Second, 32 patients with AD were scanned semiquantitatively with double PET tracers. Interparticipant and intraparticipant comparisons of the levels of MC-I activity ([18F]BCPP-EF) and glucose metabolism ([18F]FDG) were performed.

Results

The [18F]BCPP-EF VT was positively correlated with the [18F]BCPP-EF SUVRg, indicating that the use of the SUVRg was sufficient for semiquantitative evaluation. The [18F]BCPP-EF SUVRg, but not the [18F]FDG SUVRg, was significantly lower in the parahippocampus in patients with AD, highlighting the prominence of oxidative metabolic failure in the medial temporal cortex. Robust positive correlations between the [18F]BCPP-EF SUVRg and [18F]FDG SUVRg were observed in several brain regions, except the parahippocampus, in early-stage AD.

Conclusions

Mitochondrial dysfunction in the parahippocampus was shown in early-stage AD. Mitochondria-related energy failure may precede glycolysis-related hypometabolism in regions with pathologically confirmed early neurodegeneration in AD.

A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer's Disease Stages Using Resting-State fMRI and Residual Neural Networks

Alzheimer's disease (AD) is an incurable neurodegenerative disorder accounting for 70%-80% dementia cases worldwide. Although, research on AD has increased in recent years, however, the complexity associated with brain structure and functions makes the early diagnosis of this disease a challenging task. Resting-state functional magnetic resonance imaging (rs-fMRI) is a neuroimaging technology that has been widely used to study the pathogenesis of neurodegenerative diseases. In literature, the computer-aided diagnosis of AD is limited to binary classification or diagnosis of AD and MCI stages. However, its applicability to diagnose multiple progressive stages of AD is relatively under-studied. This study explores the effectiveness of rs-fMRI for multi-class classification of AD and its associated stages including CN, SMC, EMCI, MCI, LMCI, and AD. A longitudinal cohort of resting-state fMRI of 138 subjects (25 CN, 25 SMC, 25 EMCI, 25 LMCI, 13 MCI, and 25 AD) from Alzheimer's Disease Neuroimaging Initiative (ADNI) is studied. To provide a better insight into deep learning approaches and their applications to AD classification, we investigate ResNet-18 architecture in detail. We consider the training of the network from scratch by using single-channel input as well as performed transfer learning with and without fine-tuning using an extended network architecture. We experimented with residual neural networks to perform AD classification task and compared it with former research in this domain. The performance of the models is evaluated using precision, recall, f1-measure, AUC and ROC curves. We found that our networks were able to significantly classify the subjects. We achieved improved results with our fine-tuned model for all the AD stages with an accuracy of 100%, 96.85%, 97.38%, 97.43%, 97.40% and 98.01% for CN, SMC, EMCI, LMCI, MCI, and AD respectively. However, in terms of overall performance, we achieved state-of-the-art results with an average accuracy of 97.92% and 97.88% for off-the-shelf and fine-tuned models respectively. The Analysis of results indicate that classification and prediction of neurodegenerative brain disorders such as AD using functional magnetic resonance imaging and advanced deep learning methods is promising for clinical decision making and have the potential to assist in early diagnosis of AD and its associated stages.