A computational model of Alzheimer's disease at the nano, micro, and macroscales.

Introduction: Mathematical models play a crucial role in investigating complex biological systems, enabling a comprehensive understanding of interactions among various components and facilitating in silico testing of intervention strategies. Alzheimer's disease (AD) is characterized by multifactorial causes and intricate interactions among biological entities, necessitating a personalized approach due to the lack of effective treatments. Therefore, mathematical models offer promise as indispensable tools in combating AD. However, existing models in this emerging field often suffer from limitations such as inadequate validation or a narrow focus on single proteins or pathways. Methods: In this paper, we present a multiscale mathematical model that describes the progression of AD through a system of 19 ordinary differential equations. The equations describe the evolution of proteins (nanoscale), cell populations (microscale), and organ-level structures (macroscale) over a 50-year lifespan, as they relate to amyloid and tau accumulation, inflammation, and neuronal death. Results: Distinguishing our model is a robust foundation in biological principles, ensuring improved justification for the included equations, and rigorous parameter justification derived from published experimental literature. Conclusion: This model represents an essential initial step toward constructing a predictive framework, which holds significant potential for identifying effective therapeutic targets in the fight against AD.

Clinical Predictors of Postmortem Amyloid and Nonamyloid Cerebral Small Vessel Disease in Middle-Aged to Older Adults.

Background and Objectives: Sporadic cerebral small vessel disease (CSVD) is a class of important pathologic processes known to affect the aging brain and to contribute to cognitive impairment. We aimed to identify clinical risk factors associated with postmortem CSVD in middle-aged to older adults. Methods: We developed and tested risk models for their predictive accuracy of a pathologic diagnosis of nonamyloid CSVD and cerebral amyloid angiopathy (CAA) in a retrospective sample of 160 autopsied cases from the Edinburgh Brain Bank. Individuals aged 40 years and older covering the spectrum of healthy aging and common forms of dementia (i.e., highly-prevalent etiologies such as Alzheimer disease (AD), vascular cognitive impairment (VCI), and mixed dementia) were included. We performed binomial logistic regression models using sample splitting and cross-validation methods. Demographics, lifestyle habits, traditional vascular risk factors, chronic medical conditions, APOE4, and cognitive status were assessed as potential predictors. Results: Forty percent of our sample had a clinical diagnosis of dementia (AD = 33, VCI = 26 and mixed = 5) while others were cognitively healthy (n = 96). The mean age at death was 73.8 (SD 14.1) years, and 40% were female. The presence of none-to-mild vs moderate-to-severe nonamyloid CSVD was predicted by our model with good accuracy (area under the curve [AUC] = 0.84, sensitivity [SEN] = 72%, specificity [SPE] = 95%), with the most significant clinical predictors being age, history of cerebrovascular events, and cognitive impairment. The presence of CAA pathology was also predicted with high accuracy (AUC = 0.86, SEN = 93%, SPE = 79%). Significant predictors included alcohol intake, history of cerebrovascular events, and cognitive impairment. In a subset of atypical dementias (n = 24), our models provided poor predictive performance for both nonamyloid CSVD (AUC = 0.50) and CAA (AUC = 0.43). Discussion: CSVD pathology can be predicted with high accuracy based on clinical factors in patients within the spectrum of AD, VCI, and normal aging. Whether this prediction can be enhanced by the addition of fluid and neuroimaging biomarkers warrants additional study. Improving our understanding of clinical determinants of vascular brain health may lead to novel strategies in the prevention and treatment of vascular etiologies contributing to cognitive decline. Classification of Evidence: This study provides Class II evidence that selected clinical factors accurately distinguish between middle-aged to older adults with and without cerebrovascular small vessel disease (amyloid and nonamyloid) pathology.

A scoping review of mathematical models covering Alzheimer's disease progression.

Alzheimer's disease is a complex, multi-factorial, and multi-parametric neurodegenerative etiology. Mathematical models can help understand such a complex problem by providing a way to explore and conceptualize principles, merging biological knowledge with experimental data into a model amenable to simulation and external validation, all without the need for extensive clinical trials. We performed a scoping review of mathematical models describing the onset and evolution of Alzheimer's disease as a result of biophysical factors following the PRISMA standard. Our search strategy applied to the PubMed database yielded 846 entries. After using our exclusion criteria, only 17 studies remained from which we extracted data, which focused on three aspects of mathematical modeling: how authors addressed continuous time (since even when the measurements are punctual, the biological processes underlying Alzheimer's disease evolve continuously), how models were solved, and how the high dimensionality and non-linearity of models were managed. Most articles modeled Alzheimer's disease at the cellular level, operating on a short time scale (e.g., minutes or hours), i.e., the micro view (12/17); the rest considered regional or brain-level processes with longer timescales (e.g., years or decades) (the macro view). Most papers were concerned primarily with amyloid beta (n = 8), few described both amyloid beta and tau proteins (n = 3), while some considered more than these two factors (n = 6). Models used partial differential equations (n = 3), ordinary differential equations (n = 7), and both partial differential equations and ordinary differential equations (n = 3). Some did not specify their mathematical formalism (n = 4). Sensitivity analyses were performed in only a small number of papers (4/17). Overall, we found that only two studies could be considered valid in terms of parameters and conclusions, and two more were partially valid. This puts the majority (n = 13) as being either invalid or with insufficient information to ascertain their status. This was the main finding of our paper, in that serious shortcomings make their results invalid or non-reproducible. These shortcomings come from insufficient methodological description, poor calibration, or the impossibility of experimentally validating or calibrating the model. Those shortcomings should be addressed by future authors to unlock the usefulness of mathematical models in Alzheimer's disease.

Myths and Methodologies: Understanding the health impact of head down bedrest for the benefit of older adults and astronauts. Study protocol of the Canadian Bedrest Study.

Weightlessness during spaceflight can harm various bodily systems, including bone density, muscle mass, strength and cognitive functions. Exercise appears to somewhat counteract these effects. A terrestrial model for this is head-down bedrest (HDBR), simulating gravity loss. This mirrors challenges faced by older adults in extended bedrest and space environments. The first Canadian study, backed by the Canadian Space Agency, Canadian Institutes of Health Research, and Canadian Frailty Network, aims to explore these issues. The study seeks to: (1) scrutinize the impact of 14-day HDBR on physiological, psychological and neurocognitive systems, and (2) assess the benefits of exercise during HDBR. Eight teams developed distinct protocols, harmonized in three videoconferences, at the McGill University Health Center. Over 26 days, 23 participants aged 55-65 underwent baseline measurements, 14 days of -6° HDBR, and 7 days of recovery. Half did prescribed exercise thrice daily combining resistance and endurance exercise for a total duration of 1 h. Assessments included demographics, cardiorespiratory fitness, bone health, body composition, quality of life, mental health, cognition, muscle health and biomarkers. This study has yielded some published outcomes, with more forthcoming. Findings will enrich our comprehension of HDBR effects, guiding future strategies for astronaut well-being and aiding bedrest-bound older adults. By outlining evidence-based interventions, this research supports both space travellers and those enduring prolonged bedrest.

Gray matter loss relates to dual task gait in Lewy body disorders and aging.

BACKGROUND: Within the spectrum of Lewy body disorders (LBD), both Parkinson's disease (PD) and dementia with Lewy bodies (DLB) are characterized by gait and balance disturbances, which become more prominent under dual-task (DT) conditions. The brain substrates underlying DT gait variations, however, remain poorly understood in LBD. OBJECTIVE: To investigate the relationship between gray matter volume loss and DT gait variations in LBD. METHODS: Seventy-nine participants including cognitively unimpaired PD, PD with mild cognitive impairment, PD with dementia (PDD), or DLB and 20 cognitively unimpaired controls were examined across a multi-site study. PDD and DLB were grouped together for analyses. Differences in gait speed between single and DT conditions were quantified by dual task cost (DTC). Cortical, subcortical, ventricle, and cerebellum brain volumes were obtained using FreeSurfer. Linear regression models were used to examine the relationship between gray matter volumes and DTC. RESULTS: Smaller amygdala and total cortical volumes, and larger ventricle volumes were associated with a higher DTC across LBD and cognitively unimpaired controls. No statistically significant interaction between group and brain volumes were found. Adding cognitive and motor covariates or white matter hyperintensity volumes separately to the models did not affect brain volume and DTC associations. CONCLUSION: Gray matter volume loss is associated with worse DT gait performance compared to single task gait, across cognitively unimpaired controls through and the LBD spectrum. Impairment in DT gait performance may be driven by age-related cortical neurodegeneration.

Predicting cognitive decline in a low-dimensional representation of brain morphology.

Identifying early signs of neurodegeneration due to Alzheimer's disease (AD) is a necessary first step towards preventing cognitive decline. Individual cortical thickness measures, available after processing anatomical magnetic resonance imaging (MRI), are sensitive markers of neurodegeneration. However, normal aging cortical decline and high inter-individual variability complicate the comparison and statistical determination of the impact of AD-related neurodegeneration on trajectories. In this paper, we computed trajectories in a 2D representation of a 62-dimensional manifold of individual cortical thickness measures. To compute this representation, we used a novel, nonlinear dimension reduction algorithm called Uniform Manifold Approximation and Projection (UMAP). We trained two embeddings, one on cortical thickness measurements of 6237 cognitively healthy participants aged 18-100 years old and the other on 233 mild cognitively impaired (MCI) and AD participants from the longitudinal database, the Alzheimer's Disease Neuroimaging Initiative database (ADNI). Each participant had multiple visits ([Formula: see text]), one year apart. The first embedding's principal axis was shown to be positively associated ([Formula: see text]) with participants' age. Data from ADNI is projected into these 2D spaces. After clustering the data, average trajectories between clusters were shown to be significantly different between MCI and AD subjects. Moreover, some clusters and trajectories between clusters were more prone to host AD subjects. This study was able to differentiate AD and MCI subjects based on their trajectory in a 2D space with an AUC of 0.80 with 10-fold cross-validation.

Impact of 14 Days of Bed Rest in Older Adults and an Exercise Countermeasure on Body Composition, Muscle Strength, and Cardiovascular Function: Canadian Space Agency Standard Measures.

INTRODUCTION: Head-down bed rest (HDBR) has long been used as an analog to microgravity, and it also enables studying the changes occurring with aging. Exercise is the most effective countermeasure for the deleterious effects of inactivity. The aim of this study was to investigate the efficacy of an exercise countermeasure in healthy older participants on attenuating musculoskeletal deconditioning, cardiovascular fitness level, and muscle strength during 14 days of HDBR as part of the standard measures of the Canadian Space Agency. METHODS: Twenty-three participants (12 males and 11 females), aged 55-65 years, were admitted for a 26-day inpatient stay at the McGill University Health Centre. After 5 days of baseline assessment tests, they underwent 14 days of continuous HDBR followed by 7 days of recovery with repeated tests. Participants were randomized to passive physiotherapy or an exercise countermeasure during the HDBR period consisting of 3 sessions per day of either high-intensity interval training (HIIT) or low-intensity cycling or strength exercises for the lower and upper body. Peak aerobic power (V̇O2peak) was determined using indirect calorimetry. Body composition was assessed by dual-energy X-ray absorptiometry, and several muscle group strengths were evaluated using an adjustable chair dynamometer. A vertical jump was used to assess whole-body power output, and a tilt test was used to measure cardiovascular and orthostatic challenges. Additionally, changes in various blood parameters were measured as well as the effects of exercise countermeasure on these measurements. RESULTS: There were no differences at baseline in main characteristics between the control and exercise groups. The exercise group maintained V̇O2peak levels similar to baseline, whereas it decreased in the control group following 14 days of HDBR. Body weight significantly decreased in both groups. Total and leg lean masses decreased in both groups. However, total body fat mass decreased only in the exercise group. Isometric and isokinetic knee extension muscle strength were significantly reduced in both groups. Peak velocity, flight height, and flight time were significantly reduced in both groups with HDBR. CONCLUSION: In this first Canadian HDBR study in older adults, an exercise countermeasure helped maintain aerobic fitness and lean body mass without affecting the reduction of knee extension strength. However, it was ineffective in protecting against orthostatic intolerance. These results support HIIT as a promising approach to preserve astronaut health and functioning during space missions, and to prevent deconditioning as a result of hospitalization in older adults.

Longitudinal association between ß-amyloid accumulation and cognitive decline in cognitively healthy older adults: A systematic review.

This systematic review examined the longitudinal association between amyloid-ß (Aß) accumulation and cognitive decline in cognitively healthy adults. It was conducted using the PubMed, Embase, PsycInfo, and Web of Science databases. The methodological quality of the selected articles was assessed. In fine, seventeen longitudinal clinical studies were included in this review. A minority (seven out of 17) of studies reported a statistically significant association or prediction of cognitive decline with Aß change, measured by positron emission tomography (PET; n = 6) and lumbar puncture (n = 1), with a mean follow-up duration of 3.17 years for cognition and 2.99 years for Aß. The studies reporting significant results with PET found differences in the frontal, posterior cingular, lateral parietal and global (whole brain) cortices as well as in the precuneus. Significant associations were found with episodic memory (n = 6) and global cognition (n = 1). Five of the seven studies using a composite cognitive score found significant results. A quality assessment revealed widespread methodological biases, such as failure to report or account for loss-to follow up and missing data, and failure to report p-values and effect sizes of non-significant results. Overall, the longitudinal association between Aß accumulation and cognitive decline in preclinical Alzheimer's disease remains unclear. The discrepancy in results between studies may be explained in part by the choice of neuroimaging technique used to measure Aß change, the duration of longitudinal studies, the heterogeneity of the healthy preclinical population, and importantly, the use of a composite score to capture cognitive changes with increased sensitivity. More longitudinal studies with larger sample sizes are needed to elucidate this relationship.

Data and Tools Integration in the Canadian Open Neuroscience Platform.

We present the Canadian Open Neuroscience Platform (CONP) portal to answer the research community's need for flexible data sharing resources and provide advanced tools for search and processing infrastructure capacity. This portal differs from previous data sharing projects as it integrates datasets originating from a number of already existing platforms or databases through DataLad, a file level data integrity and access layer. The portal is also an entry point for searching and accessing a large number of standardized and containerized software and links to a computing infrastructure. It leverages community standards to help document and facilitate reuse of both datasets and tools, and already shows a growing community adoption giving access to more than 60 neuroscience datasets and over 70 tools. The CONP portal demonstrates the feasibility and offers a model of a distributed data and tool management system across 17 institutions throughout Canada.

Dual-task gait and white matter hyperintensities in Lewy body diseases: An exploratory analysis.

Background: Parkinson's disease (PD) and dementia with Lewy bodies (DLB) are part of a spectrum of Lewy body disorders, who exhibit a range of cognitive and gait impairments. Cognitive-motor interactions can be examined by performing a cognitive task while walking and quantified by a dual task cost (DTC). White matter hyperintensities (WMH) on magnetic resonance imaging have also been associated with both gait and cognition. Our goal was to examine the relationship between DTC and WMH in the Lewy body spectrum, hypothesizing DTC would be associated with increased WMH volume. Methods: Seventy-eight participants with PD, PD with mild cognitive impairment (PD-MCI), PD with dementia or DLB (PDD/DLB), and 20 cognitively unimpaired participants were examined in a multi-site study. Gait was measured on an electronic walkway during usual gait, counting backward, animal fluency, and subtracting sevens. WMH were quantified from magnetic resonance imaging using an automated pipeline and visual rating. A median split based on DTC was performed. Models included age as well as measures of global cognition and cardiovascular risk. Results: Compared to cognitively unimpaired participants, usual gait speed was lower and DTC was higher in PD-MCI and PDD/DLB. Low DTC participants had higher usual gait speed. WMH burden was greater in high counting DTC participants. Frontal WMH burden remained significant after adjusting for age, cardiovascular risk and global cognition. Conclusion: Increased DTC was associated with higher frontal WMH burden in Lewy body disorders after adjusting for age, cardiovascular risk, and global cognition. Higher DTC was associated with age.

An imaging-based method of mapping multi-echo BOLD intracranial pulsatility.

PURPOSE: Cardiac-related intracranial pulsatility may relate to cerebrovascular health, and this information is contained in BOLD MRI data. There is broad interest in methods to isolate BOLD pulsatility, and the current study examines a deep learning approach. METHODS: Multi-echo BOLD images, respiratory, and cardiac recordings were measured in 55 adults. Ground truth BOLD pulsatility maps were calculated with an established method. BOLD fast Fourier transform magnitude images were used as temporal-frequency image inputs to a U-Net deep learning model. Model performance was evaluated by mean squared error (MSE), mean absolute error (MAE), structural similarity index (SSIM), and mutual information (MI). Experiments evaluated the influence of input channel size, an age group effect during training, dependence on TE, performance without the U-Net architecture, and importance of respiratory preprocessing. RESULTS: The U-Net model generated BOLD pulsatility maps with lower MSE as additional fast Fourier transform input images were used. There was no age group effect for MSE (P > 0.14). MAE and SSIM metrics did not vary across TE (P > 0.36), whereas MI showed a significant TE dependence (P < 0.05). The U-Net versus no U-Net comparison showed no significant difference for MAE (P = 0.059); however, SSIM and MI were significantly different between models (P < 0.001). Within the insula, the cross-correlation values were high (r > 0.90) when comparing the U-Net model trained with/without respiratory preprocessing. CONCLUSION: Multi-echo BOLD pulsatility maps were synthesized from a U-net model that was trained to use temporal-frequency BOLD image inputs. This work adds to the deep learning methods that characterize BOLD physiological signals.

The Influence of Birth Cohorts on Future Cognitive Decline.

BACKGROUND: Slowed rates of cognitive decline have been reported in individuals with higher cognitive reserve (CR), but interindividual discrepancies remain unexplained. Few studies have reported a birth cohort effect, favoring later-born individuals, but these studies remain scarce. OBJECTIVE: We aimed to predict cognitive decline in older adults using birth cohorts and CR. METHODS: Within the Alzheimer's Disease Neuroimaging Initiative, 1,041 dementia-free participants were assessed on four cognitive domains (verbal episodic memory; language and semantic memory; attention; executive functions) at each follow-up visit up to 14 years. Four birth cohorts were formed according to the major historical events of the 20th century (1916-1928; 1929-1938; 1939-1945; 1946-1962). CR was operationalized by merging education, complexity of occupation, and verbal IQ. We used linear mixed-effect models to evaluate the effects of CR and birth cohorts on rate of performance change over time. Age at baseline, baseline structural brain health (total brain and total white matter hyperintensities volumes), and baseline vascular risk factors burden were used as covariates. RESULTS: CR was only associated with slower decline in verbal episodic memory. However, more recent birth cohorts predicted slower annual cognitive decline in all domains, except for executive functions. This effect increased as the birth cohort became more recent. CONCLUSION: We found that both CR and birth cohorts influence future cognitive decline, which has strong public policy implications.

Obesity-Associated Neurodegeneration Pattern Mimics Alzheimer's Disease in an Observational Cohort Study.

BACKGROUND: Excess weight in adulthood leads to health complications such as diabetes, hypertension, or dyslipidemia. Recently, excess weight has also been related to brain atrophy and cognitive decline. Reports show that obesity is linked with Alzheimer's disease (AD)-related changes, such as cerebrovascular damage or amyloid-ß accumulation. However, to date no research has conducted a direct comparison between brain atrophy patterns in AD and obesity. OBJECTIVE: Here, we compared patterns of brain atrophy and amyloid-ß/tau protein accumulation in obesity and AD using a sample of over 1,300 individuals from four groups: AD patients, healthy controls, obese otherwise healthy individuals, and lean individuals. METHODS: We age- and sex-matched all groups to the AD-patients group and created cortical thickness maps of AD and obesity. This was done by comparing AD patients with healthy controls, and obese individuals with lean individuals. We then compared the AD and obesity maps using correlation analyses and permutation-based tests that account for spatial autocorrelation. Similarly, we compared obesity brain maps with amyloid-ß and tau protein maps from other studies. RESULTS: Obesity maps were highly correlated with AD maps but were not correlated with amyloid-ß/tau protein maps. This effect was not accounted for by the presence of obesity in the AD group. CONCLUSION: Our research confirms that obesity-related grey matter atrophy resembles that of AD. Excess weight management could lead to improved health outcomes, slow down cognitive decline in aging, and lower the risk for AD.

White matter hyperintensity distribution differences in aging and neurodegenerative disease cohorts.

INTRODUCTION: White matter hyperintensities (WMHs) are common magnetic resonance imaging (MRI) findings in the aging population in general, as well as in patients with neurodegenerative diseases. They are known to exacerbate the cognitive deficits and worsen the clinical outcomes in the patients. However, it is not well-understood whether there are disease-specific differences in prevalence and distribution of WMHs in different neurodegenerative disorders. METHODS: Data included 976 participants with cross-sectional T1-weighted and fluid attenuated inversion recovery (FLAIR) MRIs from the Comprehensive Assessment of Neurodegeneration and Dementia (COMPASS-ND) cohort of the Canadian Consortium on Neurodegeneration in Aging (CCNA) with eleven distinct diagnostic groups: cognitively intact elderly (CIE), subjective cognitive impairment (SCI), mild cognitive impairment (MCI), vascular MCI (V-MCI), Alzheimer's dementia (AD), vascular AD (V-AD), frontotemporal dementia (FTD), Lewy body dementia (LBD), cognitively intact elderly with Parkinson's disease (PD-CIE), cognitively impaired Parkinson's disease (PD-CI), and mixed dementias. WMHs were segmented using a previously validated automated technique. WMH volumes in each lobe and hemisphere were compared against matched CIE individuals, as well as each other, and between men and women. RESULTS: All cognitively impaired diagnostic groups had significantly greater overall WMH volumes than the CIE group. Vascular groups (i.e. V-MCI, V-AD, and mixed dementia) had significantly greater WMH volumes than all other groups, except for FTD, which also had significantly greater WMH volumes than all non-vascular groups. Women tended to have lower WMH burden than men in most groups and regions, controlling for age. The left frontal lobe tended to have a lower WMH burden than the right in all groups. In contrast, the right occipital lobe tended to have greater WMH volumes than the left. CONCLUSIONS: There were distinct differences in WMH prevalence and distribution across diagnostic groups, sexes, and in terms of asymmetry. WMH burden was significantly greater in all neurodegenerative dementia groups, likely encompassing areas exclusively impacted by neurodegeneration as well as areas related to cerebrovascular disease pathology.

A ketogenic intervention improves dorsal attention network functional and structural connectivity in mild cognitive impairment.

Ketones, the brain's alternative fuel to glucose, bypass the brain glucose deficit and improve cognition in mild cognitive impairment (MCI). Our goal was to assess the impact of a 6-month ketogenic intervention on the functional connectivity within eight major brain resting-state networks, and its possible relationship to improved cognitive outcomes in the BENEFIC trial. MCI participants were randomized to a placebo (n = 15) or ketogenic medium chain triglyceride (kMCT; n = 17) intervention. kMCT was associated with increased functional connectivity within the dorsal attention network (DAN), which correlated to improvement in cognitive tests targeting attention. Ketone uptake (11C-acetoacetate PET) specifically in DAN cortical regions was highly increased in the kMCT group and was directly associated with the improved DAN functional connectivity. Analysis of the structural connectome revealed increased fiber density within the DAN following kMCT. Our findings suggest that ketones in MCI may prove beneficial for cognition at least in part because they improve brain network energy status, functional connectivity and axonal integrity.

Data-Driven Analyses of Longitudinal Hippocampal Imaging Trajectories: Discrimination and Biomarker Prediction of Change Classes.

BACKGROUND: Hippocampal atrophy is a well-known biomarker of neurodegeneration, such as that observed in Alzheimer's disease (AD). Although distributions of hippocampal volume trajectories for asymptomatic individuals often reveal substantial heterogeneity, it is unclear whether interpretable trajectory classes can be objectively detected and used for prediction analyses. OBJECTIVE: To detect and predict hippocampal trajectory classes in a computationally competitive context using established AD-related risk factors/biomarkers. METHODS: We used biomarker/risk factor and longitudinal MRI data in asymptomatic adults from the AD Neuroimaging Initiative (n = 351; Mean = 75 years; 48.7% female). First, we applied latent class growth analyses to left (LHC) and right (RHC) hippocampal trajectory distributions to identify distinct classes. Second, using random forest analyses, we tested 38 multi-modal biomarkers/risk factors for their relative importance in discriminating the lower (potentially elevated atrophy risk) from the higher (potentially reduced risk) class. RESULTS: For both LHC and RHC trajectory distribution analyses, we observed three distinct trajectory classes. Three biomarkers/risk factors predicted membership in LHC and RHC lower classes: male sex, higher education, and lower plasma Aß1-42. Four additional factors selectively predicted membership in the lower LHC class: lower plasma tau and Aß1-40, higher depressive symptomology, and lower body mass index. CONCLUSION: Data-driven analyses of LHC and RHC trajectories detected three classes underlying the heterogeneous distributions. Machine learning analyses determined three common and four unique biomarkers/risk factors discriminating the higher and lower LHC/RHC classes. Our sequential analytic approach produced evidence that the dynamics of preclinical hippocampal trajectories can be predicted by AD-related biomarkers/risk factors from multiple modalities.

Multi sequence average templates for aging and neurodegenerative disease populations.

Magnetic resonance image (MRI) processing pipelines use average templates to enable standardization of individual MRIs in a common space. MNI-ICBM152 is currently used as the standard template by most MRI processing tools. However, MNI-ICBM152 represents an average of 152 healthy young adult brains and is vastly different from brains of patients with neurodegenerative diseases. In those populations, extensive atrophy might cause inevitable registration errors when using an average template of young healthy individuals for standardization. Disease-specific templates that represent the anatomical characteristics of the populations can reduce such errors and improve downstream driven estimates. We present multi-sequence average templates for Alzheimer's Dementia (AD), Fronto-temporal Dementia (FTD), Lewy Body Dementia (LBD), Mild Cognitive Impairment (MCI), cognitively intact and impaired Parkinson's Disease patients (PD-CIE and PD-CI, respectively), individuals with Subjective Cognitive Impairment (SCI), AD with vascular contribution (V-AD), Vascular Mild Cognitive Impairment (V-MCI), Cognitively Intact Elderly (CIE) individuals, and a human phantom. We also provide separate templates for males and females to allow better representation of the diseases in each sex group.

Deep learning of chest X-rays can predict mechanical ventilation outcome in ICU-admitted COVID-19 patients.

The COVID-19 pandemic repeatedly overwhelms healthcare systems capacity and forced the development and implementation of triage guidelines in ICU for scarce resources (e.g. mechanical ventilation). These guidelines were often based on known risk factors for COVID-19. It is proposed that image data, specifically bedside computed X-ray (CXR), provide additional predictive information on mortality following mechanical ventilation that can be incorporated in the guidelines. Deep transfer learning was used to extract convolutional features from a systematically collected, multi-institutional dataset of COVID-19 ICU patients. A model predicting outcome of mechanical ventilation (remission or mortality) was trained on the extracted features and compared to a model based on known, aggregated risk factors. The model reached a 0.702 area under the curve (95% CI 0.707-0.694) at predicting mechanical ventilation outcome from pre-intubation CXRs, higher than the risk factor model. Combining imaging data and risk factors increased model performance to 0.743 AUC (95% CI 0.746-0.732). Additionally, a post-hoc analysis showed an increase performance on high-quality than low-quality CXRs, suggesting that using only high-quality images would result in an even stronger model.

Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning.

Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: 'Worse', 'Stable', or 'Improved' on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between "Worse" and "Improved" outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic ('Consolidation', 'Lung Lesion', 'Pleural effusion' and 'Pneumonia'; all P < 0.05). Features from the first CXR of each pair could correctly predict the outcome category between 'Worse' and 'Improved' cases with a 0.81 (0.74-0.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67-0.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.