Resting State Functional Connectivity Signature Differentiates Cognitively Normal from Individuals Who Convert to Symptomatic Alzheimer's Disease

Subject classification and cross-time prediction based on functional connectivity and white matter microstructure features in a rat model of Alzheimer's using machine learning

BACKGROUND

The pathological process of Alzheimer's disease (AD) typically takes decades from onset to clinical symptoms. Early brain changes in AD include MRI-measurable features such as altered functional connectivity (FC) and white matter degeneration. The ability of these features to discriminate between subjects without a diagnosis, or their prognostic value, is however not established.

METHODS

The main trigger mechanism of AD is still debated, although impaired brain glucose metabolism is taking an increasingly central role. Here, we used a rat model of sporadic AD, based on impaired brain glucose metabolism induced by an intracerebroventricular injection of streptozotocin (STZ). We characterized alterations in FC and white matter microstructure longitudinally using functional and diffusion MRI. Those MRI-derived measures were used to classify STZ from control rats using machine learning, and the importance of each individual measure was quantified using explainable artificial intelligence methods.

RESULTS

Overall, combining all the FC and white matter metrics in an ensemble way was the best strategy to discriminate STZ rats, with a consistent accuracy over 0.85. However, the best accuracy early on was achieved using white matter microstructure features, and later on using FC. This suggests that consistent damage in white matter in the STZ group might precede FC. For cross-timepoint prediction, microstructure features also had the highest performance while, in contrast, that of FC was reduced by its dynamic pattern which shifted from early hyperconnectivity to late hypoconnectivity.

CONCLUSIONS

Our study highlights the MRI-derived measures that best discriminate STZ vs control rats early in the course of the disease, with potential translation to humans.

Increasing hub disruption parallels dementia severity in autosomal dominant Alzheimer disease

Hub regions in the brain, recognized for their roles in ensuring efficient information transfer, are vulnerable to pathological alterations in neurodegenerative conditions, including Alzheimer Disease (AD). Given their essential role in neural communication, disruptions to these hubs have profound implications for overall brain network integrity and functionality. Hub disruption, or targeted impairment of functional connectivity at the hubs, is recognized in AD patients. Computational models paired with evidence from animal experiments hint at a mechanistic explanation, suggesting that these hubs may be preferentially targeted in neurodegeneration, due to their high neuronal activity levels-a phenomenon termed "activity-dependent degeneration". Yet, two critical issues were unresolved. First, past research hasn't definitively shown whether hub regions face a higher likelihood of impairment (targeted attack) compared to other regions or if impairment likelihood is uniformly distributed (random attack). Second, human studies offering support for activity-dependent explanations remain scarce. We applied a refined hub disruption index to determine the presence of targeted attacks in AD. Furthermore, we explored potential evidence for activity-dependent degeneration by evaluating if hub vulnerability is better explained by global connectivity or connectivity variations across functional systems, as well as comparing its timing relative to amyloid beta deposition in the brain. Our unique cohort of participants with autosomal dominant Alzheimer Disease (ADAD) allowed us to probe into the preclinical stages of AD to determine the hub disruption timeline in relation to expected symptom emergence. Our findings reveal a hub disruption pattern in ADAD aligned with targeted attacks, detectable even in pre-clinical stages. Notably, the disruption's severity amplified alongside symptomatic progression. Moreover, since excessive local neuronal activity has been shown to increase amyloid deposition and high connectivity regions show high level of neuronal activity, our observation that hub disruption was primarily tied to regional differences in global connectivity and sequentially followed changes observed in Aβ PET cortical markers is consistent with the activity-dependent degeneration model. Intriguingly, these disruptions were discernible 8 years before the expected age of symptom onset. Taken together, our findings not only align with the targeted attack on hubs model but also suggest that activity-dependent degeneration might be the cause of hub vulnerability. This deepened understanding could be instrumental in refining diagnostic techniques and developing targeted therapeutic strategies for AD in the future.

Longitudinal changes in metabolic network activity in early Alzheimer's disease

INTRODUCTION

The progression of Alzheimer's disease (AD) has been linked to two metabolic networks, the AD-related pattern (ADRP) and the default mode network (DMN).

METHODS

Converting and clinically stable cognitively normal subjects (n = 47) and individuals with mild cognitive impairment (n = 96) underwent 2-[18 F]fluoro-2-deoxy-D-glucose (FDG) positron emission tomography (PET) three or more times over 6 years (nscans  = 705). Expression levels for ADRP and DMN were measured in each subject and time point, and the resulting changes were correlated with cognitive performance. The role of network expression in predicting conversion to dementia was also evaluated.

RESULTS

Longitudinal increases in ADRP expression were observed in converters, while age-related DMN loss was seen in converters and nonconverters. Cognitive decline correlated with increases in ADRP and declines in DMN, but conversion to dementia was predicted only by baseline ADRP levels.

DISCUSSION

The results point to the potential utility of ADRP as an imaging biomarker of AD progression.

A unique color-coded visualization system with multimodal information fusion and deep learning in a longitudinal study of Alzheimer's disease

PURPOSE

Automated diagnosis and prognosis of Alzheimer's Disease remain a challenging problem that machine learning (ML) techniques have attempted to resolve in the last decade. This study introduces a first-of-its-kind color-coded visualization mechanism driven by an integrated ML model to predict disease trajectory in a 2-year longitudinal study. The main aim of this study is to help capture visually in 2D and 3D renderings the diagnosis and prognosis of AD, therefore augmenting our understanding of the processes of multiclass classification and regression analysis.

METHOD

The proposed method, Machine Learning for Visualizing AD (ML4VisAD), is designed to predict disease progression through a visual output. This newly developed model takes baseline measurements as input to generate a color-coded visual image that reflects disease progression at different time points. The architecture of the network relies on convolutional neural networks. With 1123 subjects selected from the ADNI QT-PAD dataset, we use a 10-fold cross-validation process to evaluate the method. Multimodal inputs* include neuroimaging data (MRI, PET), neuropsychological test scores (excluding MMSE, CDR-SB, and ADAS to avoid bias), cerebrospinal fluid (CSF) biomarkers with measures of amyloid beta (ABETA), phosphorylated tau protein (PTAU), total tau protein (TAU), and risk factors that include age, gender, years of education, and ApoE4 gene.

FINDINGS/RESULTS

Based on subjective scores reached by three raters, the results showed an accuracy of 0.82 ± 0.03 for a 3-way classification and 0.68 ± 0.05 for a 5-way classification. The visual renderings were generated in 0.08 msec for a 23 × 23 output image and in 0.17 ms for a 45 × 45 output image. Through visualization, this study (1) demonstrates that the ML visual output augments the prospects for a more accurate diagnosis and (2) highlights why multiclass classification and regression analysis are incredibly challenging. An online survey was conducted to gauge this visualization platform's merits and obtain valuable feedback from users. All implementation codes are shared online on GitHub.

CONCLUSION

This approach makes it possible to visualize the many nuances that lead to a specific classification or prediction in the disease trajectory, all in context to multimodal measurements taken at baseline. This ML model can serve as a multiclass classification and prediction model while reinforcing the diagnosis and prognosis capabilities by including a visualization platform.

The Amyloid Cascade Hypothesis in Alzheimer’s Disease: Should We Change Our Thinking?

Old age increases the risk of Alzheimer’s disease (AD), the most common neurodegenerative disease, a devastating disorder of the human mind and the leading cause of dementia. Worldwide, 50 million people have the disease, and it is estimated that there will be 150 million by 2050. Today, healthcare for AD patients consumes 1% of the global economy. According to the amyloid cascade hypothesis, AD begins in the brain by accumulating and aggregating Aβ peptides and forming β-amyloid fibrils (Aβ42). However, in clinical trials, reducing Aβ peptide production and amyloid formation in the brain did not slow cognitive decline or improve daily life in AD patients. Prevention studies in cognitively unimpaired people at high risk or genetically destined to develop AD also have not slowed cognitive decline. These observations argue against the amyloid hypothesis of AD etiology, its development, and disease mechanisms. Here, we look at other avenues in the research of AD, such as the presenilin hypothesis, synaptic glutamate signaling, and the role of astrocytes and the glutamate transporter EAAT2 in the development of AD.

Assessment of Instrumental Activities of Daily Living in Preclinical Alzheimer Disease

Questionnaires are used to assess instrumental activities of daily living (IADL) among individuals with preclinical Alzheimer disease (AD). They have indicated no functional impairment among this population. We aim to determine among cognitively normal (CN) older adults with and without preclinical AD whether: (a) performance-based IADL assessment measures a wider range of function than an IADL questionnaire and (b) biomarkers of AD are associated with IADL performance. In this cross-sectional analysis of 161 older adults, participants in studies of AD completed an IADL questionnaire, performance-based IADL assessment, cognitive assessments, and had biomarkers of AD (amyloid, hippocampal volume, brain network strength) assessed within 2 to 3 years. Performance-based IADL scores were more widely distributed compared with the IADL questionnaire. Smaller hippocampal volumes and reduced brain network connections were associated with worse IADL performance. A performance-based IADL assessment demonstrates functional impairment associated with neurodegeneration among CN older adults.

Use of machine learning to identify functional connectivity changes in a clinical cohort of patients at risk for dementia

Objective

Progressive conditions characterized by cognitive decline, including mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are clinical conditions representing a major risk factor to develop dementia, however, the diagnosis of these pre-dementia conditions remains a challenge given the heterogeneity in clinical trajectories. Earlier diagnosis requires data-driven approaches for improved and targeted treatment modalities.

Methods

Neuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI (rsfMRI), and diffusion weighted scans were obtained from 35 patients with SCD, 19 with MCI, and 36 age-matched healthy controls (HC). A recently developed machine learning technique, Hollow Tree Super (HoTS) was utilized to classify subjects into diagnostic categories based on their FC, and derive network and parcel-based FC features contributing to each model. The same approach was used to identify features associated with performance in a range of neuropsychological tests. We concluded our analysis by looking at changes in PageRank centrality (a measure of node hubness) between the diagnostic groups.

Results

Subjects were classified into diagnostic categories with a high area under the receiver operating characteristic curve (AUC-ROC), ranging from 0.73 to 0.84. The language networks were most notably associated with classification. Several central networks and sensory brain regions were predictors of poor performance in neuropsychological tests, suggesting maladaptive compensation. PageRank analysis highlighted that basal and limbic deep brain region, along with the frontal operculum demonstrated a reduction in centrality in both SCD and MCI patients compared to controls.

Conclusion

Our methods highlight the potential to explore the underlying neural networks contributing to the cognitive changes and neuroplastic responses in prodromal dementia.

The Role of Visual Experience in Individual Differences of Brain Connectivity

Visual cortex organization is highly consistent across individuals. But to what degree does this consistency depend on life experience, in particular sensory experience? In this study, we asked whether visual cortex reorganization in congenital blindness results in connectivity patterns that are particularly variable across individuals, focusing on resting-state functional connectivity (RSFC) patterns from the primary visual cortex. We show that the absence of shared visual experience results in more variable RSFC patterns across blind individuals than sighted controls. Increased variability is specifically found in areas that show a group difference between the blind and sighted in their RSFC. These findings reveal a relationship between brain plasticity and individual variability; reorganization manifests variably across individuals. We further investigated the different patterns of reorganization in the blind, showing that the connectivity to frontal regions, proposed to have a role in the reorganization of the visual cortex of the blind toward higher cognitive roles, is highly variable. Further, we link some of the variability in visual-to-frontal connectivity to another environmental factor-duration of formal education. Together, these findings show a role of postnatal sensory and socioeconomic experience in imposing consistency on brain organization. By revealing the idiosyncratic nature of neural reorganization, these findings highlight the importance of considering individual differences in fitting sensory aids and restoration approaches for vision loss.SIGNIFICANCE STATEMENT The typical visual system is highly consistent across individuals. What are the origins of this consistency? Comparing the consistency of visual cortex connectivity between people born blind and sighted people, we showed that blindness results in higher variability, suggesting a key impact of postnatal individual experience on brain organization. Further, connectivity patterns that changed following blindness were particularly variable, resulting in diverse patterns of brain reorganization. Individual differences in reorganization were also directly affected by nonvisual experiences in the blind (years of formal education). Together, these findings show a role of sensory and socioeconomic experiences in creating individual differences in brain organization and endorse the use of individual profiles for rehabilitation and restoration of vision loss.

BDNF and KIBRA Polymorphisms Are Related to Altered Resting State Network Connectivity in Middle Age

BACKGROUND

Disease-modifying treatments for Alzheimer's disease (AD) may be more successful if interventions occur early, prior to significant neurodegeneration and subsequent to the onset of clinical symptoms, potentially during middle age. Polymorphisms within BDNF, COMT, and KIBRA have been implicated in AD and relate to episodic memory and executive functioning, two domains that decline early in AD.

OBJECTIVE

The purpose of the current study was to use an endophenotype approach to examine in healthy, non-demented middle-aged adults the association between polymorphisms in BDNF, COMT, and KIBRA and functional connectivity within networks related to episodic memory and executive function (i.e., default mode network (DMN), executive control network (ECN), and frontoparietal network (FPN)).

METHODS

Resting state networks were identified using independent component analysis and spatial maps with associated time courses were extracted using a dual regression approach.

RESULTS

Functional connectivity within the DMN was associated with polymorphisms in BDNF (rs11030096, rs1491850) and KIBRA (rs1030182, rs6555791, rs6555802) (ps < 0.05), ECN connectivity was associated with polymorphisms in KIBRA (rs10475878, rs6555791) (ps < 0.05), and FPN connectivity was associated with KIBRA rs6555791 (p < 0.05). There were no COMT-related differences in functional connectivity of any of the three networks investigated (ps > 0.05).

CONCLUSION

Our study demonstrates that in middle age, polymorphisms in BDNF and KIBRA are associated with altered functional connectivity in networks that are affected early in AD. Future preclinical work should consider these polymorphisms to further elucidate their role in pathological aging and to aid in the identification of biomarkers.

Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment

Objective

Alzheimer’s Disease (AD) is a progressive condition characterized by cognitive decline. AD is often preceded by mild cognitive impairment (MCI), though the diagnosis of both conditions remains a challenge. Early diagnosis of AD, and prediction of MCI progression require data-driven approaches to improve patient selection for treatment. We used a machine learning tool to predict performance in neuropsychological tests in AD and MCI based on functional connectivity using a whole-brain connectome, in an attempt to identify network substrates of cognitive deficits in AD.

Methods

Neuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI, and diffusion weighted imaging scans were obtained from 149 MCI, and 85 AD patients; and 140 cognitively unimpaired geriatric participants. A novel machine learning tool, Hollow Tree Super (HoTS) was utilized to extract feature importance from each machine learning model to identify brain regions that were associated with deficit and absence of deficit for 11 neuropsychological tests.

Results

11 models attained an area under the receiver operating curve (AUC-ROC) greater than 0.65, while five models had an AUC-ROC ≥ 0.7. 20 parcels of the Human Connectome Project Multimodal Parcelation Atlas matched to poor performance in at least two neuropsychological tests, while 14 parcels were associated with good performance in at least two tests. At a network level, most parcels predictive of both presence and absence of deficit were affiliated with the Central Executive Network, Default Mode Network, and the Sensorimotor Networks. Segregating predictors by the cognitive domain associated with each test revealed areas of coherent overlap between cognitive domains, with the parcels providing possible markers to screen for cognitive impairment.

Conclusion

Approaches such as ours which incorporate whole-brain functional connectivity and harness feature importance in machine learning models may aid in identifying diagnostic and therapeutic targets in AD.

Altered basal forebrain BOLD signal variability at rest in posttraumatic stress disorder: A potential candidate vulnerability mechanism for neurodegeneration in PTSD

Individuals with posttraumatic stress disorder (PTSD) are at increased risk for the development of various forms of dementia. Nevertheless, the neuropathological link between PTSD and neurodegeneration remains unclear. Degeneration of the human basal forebrain constitutes a pathological hallmark of neurodegenerative diseases, such as Alzheimer's and Parkinson's disease. In this seed-based resting-state (rs-)fMRI study identifying as outcome measure the temporal BOLD signal fluctuation magnitude, a seed-to-voxel analyses assessed temporal correlations between the average BOLD signal within a bilateral whole basal forebrain region-of-interest and each whole-brain voxel among individuals with PTSD (n = 65), its dissociative subtype (PTSD+DS) (n = 38) and healthy controls (n = 46). We found that compared both with the PTSD and healthy controls groups, the PTSD+DS group exhibited increased BOLD signal variability within two nuclei of the seed region, specifically in its extended amygdaloid region: the nucleus accumbens and the sublenticular extended amygdala. This finding is provocative, because it mimics staging models of neurodegenerative diseases reporting allocation of neuropathology in early disease stages circumscribed to the basal forebrain. Here, underlying candidate etiopathogenetic mechanisms are neurovascular uncoupling, decreased connectivity in local- and large-scale neural networks, or disrupted mesolimbic dopaminergic circuitry, acting indirectly upon the basal forebrain cholinergic pathways. These abnormalities may underpin reward-related deficits representing a putative link between persistent traumatic memory in PTSD and anterograde memory deficits in neurodegeneration. Observed alterations of the basal forebrain in the dissociative subtype of PTSD point towards the urgent need for further exploration of this region as a potential candidate vulnerability mechanism for neurodegeneration in PTSD.

Association of Lifestyle Activities with Functional Brain Connectivity and Relationship to Cognitive Decline among Older Adults

This study examines the relationship of engagement in different lifestyle activities to connectivity in large-scale functional brain networks, and whether network connectivity modifies cognitive decline, independent of brain amyloid levels. Participants (N = 153, mean age = 69 years, including N = 126 with amyloid imaging) were cognitively normal when they completed resting-state functional magnetic resonance imaging, a lifestyle activity questionnaire, and cognitive testing. They were followed with annual cognitive tests up to 5 years (mean = 3.3 years). Linear regressions showed positive relationships between cognitive activity engagement and connectivity within the dorsal attention network, and between physical activity levels and connectivity within the default-mode, limbic, and frontoparietal control networks, and global within-network connectivity. Additionally, higher cognitive and physical activity levels were independently associated with higher network modularity, a measure of functional network specialization. These associations were largely independent of APOE4 genotype, amyloid burden, global brain atrophy, vascular risk, and level of cognitive reserve. Moreover, higher connectivity in the dorsal attention, default-mode, and limbic networks, and greater global connectivity and modularity were associated with reduced cognitive decline, independent of APOE4 genotype and amyloid burden. These findings suggest that changes in functional brain connectivity may be one mechanism by which lifestyle activity engagement reduces cognitive decline.

Network dysfunction in cognitively normal APOE ε4 carriers is related to subclinical tau

INTRODUCTION

Apolipoprotein E (APOE) ε4 allele status is associated with amyloid and tau-related pathological changes related to Alzheimer's disease (AD). However, it is unknown whether brain network changes are related to amyloid beta (Aβ) and/or tau-related pathology in cognitively normal APOE ε4 carriers with subthreshold Aβ accumulation.

METHODS

Resting state functional connectivity measures of network integrity were evaluated in cognitively normal individuals (n = 121, mean age 76.6 ± 7.8 years, 15% APOE ε4 carriers, 65% female) with minimal Aβ per cerebrospinal fluid (CSF) or amyloid positron emission tomography.

RESULTS

APOE ε4 carriers had increased lateralized connections relative to callosal connections within the default-mode, memory, and salience networks (P = .02), with significant weighting on linear regression toward CSF total tau (P = .03) and CSF phosphorylated tau at codon 181 (P = .03), but not CSF Aβ₄₂ .

DISCUSSION

Cognitively normal APOE ε4 carriers with subthreshold amyloid accumulation may have network reorganization associated with tau.

The Effects of Amyloid and Tau on Functional Network Connectivity in Older Populations

Background: Neuroimaging studies suggest that aged brains show altered connectivity within and across functional networks. Similar changes in functional network integrity are also linked to the accumulation of pathological proteins in the brain, such as amyloid-beta plaques and neurofibrillary tau tangles seen in Alzheimer's disease. However, less is known about the specific impacts of amyloid and tau on functional network connectivity in cognitively normal older adults who harbor these proteins. Methods: We briefly summarize recent neuroimaging studies of aging and then thoroughly review positron emission tomography and functional magnetic resonance imaging studies measuring the relationship between amyloid-tau pathology and functional connectivity in cognitively normal older individuals. Results: The literature overall suggests that amyloid-positive older individuals show minor cognitive dysfunction and aberrant default mode network connectivity compared with amyloid-negative individuals. Tau, however, is more closely associated with network hypoconnectivity and poorer cognition. Those with substantial amyloid and tau experience even greater cognitive decline compared with those with primarily amyloid or tau, suggesting a potential interaction. Multimodal neuroimaging studies suggest that older adults with pathological protein deposits show amyloid-related hyperconnectivity and tau-related hypoconnectivity in multiple functional networks, including the default mode and frontoparietal networks. Discussion: We propose an updated model considering the effects of amyloid and tau on functional connectivity in older individuals. Large, longitudinal neuroimaging studies with multiple levels of analysis are required to obtain a deeper understanding of the dynamic relationship between pathological protein accumulation and functional connectivity changes, as amyloid- and tau-induced connectivity alterations may have critical and time-varying effects on neurodegeneration and cognitive decline. Impact statement Amyloid and tau accumulation have been linked with altered functional connectivity in cognitively normal older adults. This review synthesized recent functional imaging literatures in a discussion of how amyloid and tau can interactively affect functional connectivity in nonlinear ways, which can explain previous conflicting findings. Changes in connectivity strength may depend on the accumulation of both amyloid and tau, and their integrative effects seem to have critical consequences on cognition. Elucidating the effects of these pathological proteins on brain functioning is paramount to understand the etiology of Alzheimer's disease and the aging process overall.

Introduction to Functional MR Imaging

During the past decade, functional MR imaging has rapidly moved from the research environment into clinical practice. Preoperative functional MR imaging is now standard clinical practice not only in major academic institutions, but also in community neurosurgical and neuroradiologic practices. The clinical use of functional MR imaging will only increase in the years to come. Application of functional MR imaging (including resting-state functional MR imaging) to the context of neuropsychiatric diseases is likely to continue to advance.

Evaluating resting-state BOLD variability in relation to biomarkers of preclinical Alzheimer's disease

Recent functional magnetic resonance imaging studies have demonstrated that moment-to-moment variability in the blood oxygen level-dependent (BOLD) signal is related to age differences, cognition, and symptomatic Alzheimer's disease (AD). However, no studies have examined BOLD variability in the context of preclinical AD. We tested relationships between resting-state BOLD variability and biomarkers of amyloidosis, tauopathy, and neurodegeneration in a large (N = 321), well-characterized sample of cognitively normal adults (age = 39-93), using multivariate machine learning techniques. Furthermore, we controlled for cardiovascular health factors, which may contaminate resting-state BOLD variability estimates. BOLD variability, particularly in the default mode network, was related to cerebrospinal fluid (CSF) amyloid-β42 but was not related to CSF phosphorylated tau-181. Furthermore, BOLD variability estimates were also related to markers of neurodegeneration, including CSF neurofilament light protein, hippocampal volume, and a cortical thickness composite. Notably, relationships with hippocampal volume and cortical thickness survived correction for cardiovascular health and also contributed to age-related differences in BOLD variability. Thus, BOLD variability may be sensitive to preclinical pathology, including amyloidosis and neurodegeneration in AD-sensitive areas.