Genetic risk scores enhance the diagnostic value of plasma biomarkers of brain amyloidosis.

Blood-based biomarkers offer strong potential to revolutionize diagnosis, trial enrolment and treatment monitoring in Alzheimer's disease (AD). However, further advances are needed before these biomarkers can achieve wider deployment beyond selective research studies and specialty memory clinics, including the development of frameworks for optimal interpretation of biomarker profiles. We hypothesized that integrating Alzheimer's disease genetic risk score (AD-GRS) data would enhance the diagnostic value of plasma AD biomarkers by better capturing extant disease heterogeneity. Analysing 962 individuals from a population-based sample, we observed that an AD-GRS was independently associated with amyloid PET levels (an early marker of AD pathophysiology) over and above APOE ε4 or plasma p-tau181, amyloid-ß42/40, glial fibrillary acidic protein or neurofilament light chain. Among individuals with a high or moderately high plasma p-tau181, integrating AD-GRS data significantly improved classification accuracy of amyloid PET positivity, including the finding that the combination of a high AD-GRS and high plasma p-tau181 outperformed p-tau181 alone in classifying amyloid PET positivity (88% versus 68%; P = 0.001). A machine learning approach incorporating plasma biomarkers, demographics and the AD-GRS was highly accurate in predicting amyloid PET levels (90% training set; 89% test set) and Shapley value analyses (an explainer method based in cooperative game theory) indicated that the AD-GRS and plasma biomarkers had differential importance in explaining amyloid deposition across individuals. Polygenic risk for AD dementia appears to account for a unique portion of disease heterogeneity, which could non-invasively enhance the interpretation of blood-based AD biomarker profiles in the population.

Vascular risk, gait, behavioral, and plasma indicators of VCID.

INTRODUCTION: Cost-effective screening tools for vascular contributions to cognitive impairment and dementia (VCID) has significant implications. We evaluated non-imaging indicators of VCID using magnetic resonance imaging (MRI)-measured white matter (WM) damage and hypothesized that these indicators differ based on age. METHODS: In 745 participants from the Mayo Clinic Study of Aging (≥50 years of age) with serial WM assessments from diffusion MRI and fluid-attenuated inversion recovery (FLAIR)-MRI, we examined associations between baseline non-imaging indicators (demographics, vascular risk factors [VRFs], gait, behavioral, plasma glial fibrillary acidic protein [GFAP], and plasma neurofilament light chain [NfL]) and WM damage across three age tertiles. RESULTS: VRFs and gait were associated with diffusion changes even in low age strata. All measures (VRFs, gait, behavioral, plasma GFAP, plasma NfL) were associated with white matter hyperintensities (WMHs) but mainly in intermediate and high age strata. DISCUSSION: Non-imaging indicators of VCID were related to WM damage and may aid in screening participants and assessing outcomes for VCID. HIGHLIGHTS: Non-imaging indicators of VCID can aid in prediction of MRI-measured WM damage but their importance differed by age. Vascular risk and gait measures were associated with early VCID changes measured using diffusion MRI. Plasma markers explained variability in WMH across age strata. Most non-imaging measures explained variability in WMH and vascular WM scores in intermediate and older age groups. The framework developed here can be used to evaluate new non-imaging VCID indicators proposed in the future.

Cross-scanner harmonization methods for structural MRI may need further work: A comparison study.

The clinical usefulness MRI biomarkers for aging and dementia studies relies on precise brain morphological measurements; however, scanner and/or protocol variations may introduce noise or bias. One approach to address this is post-acquisition scan harmonization. In this work, we evaluate deep learning (neural style transfer, CycleGAN and CGAN), histogram matching, and statistical (ComBat and LongComBat) methods. Participants who had been scanned on both GE and Siemens scanners (cross-sectional participants, known as Crossover (n = 113), and longitudinally scanned participants on both scanners (n = 454)) were used. The goal was to match GE MPRAGE (T1-weighted) scans to Siemens improved resolution MPRAGE scans. Harmonization was performed on raw native and preprocessed (resampled, affine transformed to template space) scans. Cortical thicknesses were measured using FreeSurfer (v.7.1.1). Distributions were checked using Kolmogorov-Smirnov tests. Intra-class correlation (ICC) was used to assess the degree of agreement in the Crossover datasets and annualized percent change in cortical thickness was calculated to evaluate the Longitudinal datasets. Prior to harmonization, the least agreement was found at the frontal pole (ICC = 0.72) for the raw native scans, and at caudal anterior cingulate (0.76) and frontal pole (0.54) for the preprocessed scans. Harmonization with NST, CycleGAN, and HM improved the ICCs of the preprocessed scans at the caudal anterior cingulate (>0.81) and frontal poles (>0.67). In the Longitudinal raw native scans, over- and under-estimations of cortical thickness were observed due to the changing of the scanners. ComBat matched the cortical thickness distributions throughout but was not able to increase the ICCs or remove the effects of scanner changeover in the Longitudinal datasets. CycleGAN and NST performed slightly better to address the cortical thickness variations between scanner change. However, none of the methods succeeded in harmonizing the Longitudinal dataset. CGAN was the worst performer for both datasets. In conclusion, the performance of the methods was overall similar and region dependent. Future research is needed to improve the existing approaches since none of them outperformed each other in terms of harmonizing the datasets at all ROIs. The findings of this study establish framework for future research into the scan harmonization problem.

Machine Learning Models of Polygenic Risk for Enhanced Prediction of Alzheimer Disease Endophenotypes.

Background and Objectives: Alzheimer disease (AD) has a polygenic architecture, for which genome-wide association studies (GWAS) have helped elucidate sequence variants (SVs) influencing susceptibility. Polygenic risk score (PRS) approaches show promise for generating summary measures of inherited risk for clinical AD based on the effects of APOE and other GWAS hits. However, existing PRS approaches, based on traditional regression models, explain only modest variation in AD dementia risk and AD-related endophenotypes. We hypothesized that machine learning (ML) models of polygenic risk (ML-PRS) could outperform standard regression-based PRS methods and therefore have the potential for greater clinical utility. Methods: We analyzed combined data from the Mayo Clinic Study of Aging (n = 1,791) and the Alzheimer's Disease Neuroimaging Initiative (n = 864). An AD PRS was computed for each participant using the top common SVs obtained from a large AD dementia GWAS. In parallel, ML models were trained using those SV genotypes, with amyloid PET burden as the primary outcome. Secondary outcomes included amyloid PET positivity and clinical diagnosis (cognitively unimpaired vs impaired). We compared performance between ML-PRS and standard PRS across 100 training sessions with different data splits. In each session, data were split into 80% training and 20% testing, and then five-fold cross-validation was used within the training set to ensure the best model was produced for testing. We also applied permutation importance techniques to assess which genetic factors contributed most to outcome prediction. Results: ML-PRS models outperformed the AD PRS (r2 = 0.28 vs r2 = 0.24 in test set) in explaining variation in amyloid PET burden. Among ML approaches, methods accounting for nonlinear genetic influences were superior to linear methods. ML-PRS models were also more accurate when predicting amyloid PET positivity (area under the curve [AUC] = 0.80 vs AUC = 0.63) and the presence of cognitive impairment (AUC = 0.75 vs AUC = 0.54) compared with the standard PRS. Discussion: We found that ML-PRS approaches improved upon standard PRS for prediction of AD endophenotypes, partly related to improved accounting for nonlinear effects of genetic susceptibility alleles. Further adaptations of the ML-PRS framework could help to close the gap of remaining unexplained heritability for AD and therefore facilitate more accurate presymptomatic and early-stage risk stratification for clinical decision-making.

Advancing Tau PET Quantification in Alzheimer Disease with Machine Learning: Introducing THETA, a Novel Tau Summary Measure.

Alzheimer disease (AD) exhibits spatially heterogeneous 3- or 4-repeat tau deposition across participants. Our overall goal was to develop an automated method to quantify the heterogeneous burden of tau deposition into a single number that would be clinically useful. Methods: We used tau PET scans from 3 independent cohorts: the Mayo Clinic Study of Aging and Alzheimer's Disease Research Center (Mayo, n = 1,290), the Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 831), and the Open Access Series of Imaging Studies (OASIS-3, n = 430). A machine learning binary classification model was trained on Mayo data and validated on ADNI and OASIS-3 with the goal of predicting visual tau positivity (as determined by 3 raters following Food and Drug Administration criteria for 18F-flortaucipir). The machine learning model used region-specific SUV ratios scaled to cerebellar crus uptake. We estimated feature contributions based on an artificial intelligence-explainable method (Shapley additive explanations) and formulated a global tau summary measure, Tau Heterogeneity Evaluation in Alzheimer's Disease (THETA) score, using SUV ratios and Shapley additive explanations for each participant. We compared the performance of THETA with that of commonly used meta-regions of interest (ROIs) using the Mini-Mental State Examination, the Clinical Dementia Rating-Sum of Boxes, clinical diagnosis, and histopathologic staging. Results: The model achieved a balanced accuracy of 95% on the Mayo test set and at least 87% on the validation sets. It classified tau-positive and -negative participants with an AUC of 1.00, 0.96, and 0.94 on the Mayo, ADNI, and OASIS-3 cohorts, respectively. Across all cohorts, THETA showed a better correlation with the Mini-Mental State Examination and the Clinical Dementia Rating-Sum of Boxes (ρ ≥ 0.45, P < 0.05) than did meta-ROIs (ρ < 0.44, P < 0.05) and discriminated between participants who were cognitively unimpaired and those who had mild cognitive impairment with an effect size of 10.09, compared with an effect size of 3.08 for meta-ROIs. Conclusion: Our proposed approach identifies positive tau PET scans and provides a quantitative summary measure, THETA, that effectively captures heterogeneous tau deposition observed in AD. The application of THETA for quantifying tau PET in AD exhibits great potential.

Can integration of Alzheimer's plasma biomarkers with MRI, cardiovascular, genetics, and lifestyle measures improve cognition prediction?

There is increasing interest in Alzheimer's disease related plasma biomarkers due to their accessibility and scalability. We hypothesized that integrating plasma biomarkers with other commonly used and available participant data (MRI, cardiovascular factors, lifestyle, genetics) using machine learning (ML) models can improve individual prediction of cognitive outcomes. Further, our goal was to evaluate the heterogeneity of these predictors across different age strata. This longitudinal study included 1185 participants from the Mayo Clinic Study of Aging who had complete plasma analyte work-up at baseline. We used the Quanterix Simoa immunoassay to measure neurofilament light, Aß1-42 and Aß1-40 (used as Aß42/Aß40 ratio), glial fibrillary acidic protein, and phosphorylated tau 181 (p-tau181). Participants' brain health was evaluated through gray and white matter structural MRIs. The study also considered cardiovascular factors (hyperlipidemia, hypertension, stroke, diabetes, chronic kidney disease), lifestyle factors (area deprivation index, body mass index, cognitive and physical activities), and genetic factors (APOE, single nucleotide polymorphisms, and polygenic risk scores). An ML model was developed to predict cognitive outcomes at baseline and decline (slope). Three models were created: a base model with groups of risk factors as predictors, an enhanced model included socio-demographics, and a final enhanced model by incorporating plasma and socio-demographics into the base models. Models were explained for three age strata: younger than 65 years, 65-80 years, and older than 80 years, and further divided based on amyloid positivity status. Regardless of amyloid status the plasma biomarkers showed comparable performance (R² = 0.15) to MRI (R² = 0.18) and cardiovascular measures (R² = 0.10) when predicting cognitive decline. Inclusion of cardiovascular or MRI measures with plasma in the presence of socio-demographic improved cognitive decline prediction (R² = 0.26 and 0.27). For amyloid positive individuals Aß42/Aß40, glial fibrillary acidic protein and p-tau181 were the top predictors of cognitive decline while Aß42/Aß40 was prominent for amyloid negative participants across all age groups. Socio-demographics explained a large portion of the variance in the amyloid negative individuals while the plasma biomarkers predominantly explained the variance in amyloid positive individuals (21% to 37% from the younger to the older age group). Plasma biomarkers performed similarly to MRI and cardiovascular measures when predicting cognitive outcomes and combining them with either measure resulted in better performance. Top predictors were heterogeneous between cross-sectional and longitudinal cognition models, across age groups, and amyloid status. Multimodal approaches will enhance the usefulness of plasma biomarkers through careful considerations of a study population's socio-demographics, brain and cardiovascular health.

Advancing Tau-PET quantification in Alzheimer's disease with machine learning: introducing THETA, a novel tau summary measure.

Alzheimer's disease (AD) exhibits spatially heterogeneous 3R/4R tau pathology distributions across participants, making it a challenge to quantify extent of tau deposition. Utilizing Tau-PET from three independent cohorts, we trained and validated a machine learning model to identify visually positive Tau-PET scans from regional SUVR values and developed a novel summary measure, THETA, that accounts for heterogeneity in tau deposition. The model for identification of tau positivity achieved a balanced test accuracy of 95% and accuracy of ≥87% on the validation datasets. THETA captured heterogeneity of tau deposition, had better association with clinical measures, and corresponded better with visual assessments in comparison with the temporal meta-region-of-interest Tau-PET quantification methods. Our novel approach aids in identification of positive Tau-PET scans and provides a quantitative summary measure, THETA, that effectively captures the heterogeneous tau deposition seen in AD. The application of THETA for quantifying Tau-PET in AD exhibits great potential.

White Matter Degeneration Pathways Associated With Tau Deposition in Alzheimer Disease.

BACKGROUND AND OBJECTIVES: The dynamics of white matter (WM) changes are understudied in Alzheimer disease (AD). Our goal was to study the association between flortaucipir PET and WM health using neurite orientation dispersion and density imaging (NODDI) and evaluate its association with cognitive performance. Specifically, we focused on NODDI's Neurite Density Index (NDI), which aids in capturing axonal degeneration in WM and has greater specificity than single-shell diffusion MRI methods. METHOD: We estimated regional flortaucipir PET standard uptake value ratios (SUVRs) from 3 regions corresponding to Braak stage I, III/IV, and V/VI to capture the spatial distribution pattern of the 3R/4R tau in AD. Then, we evaluated the associations between these measurements and NDIs in 29 candidate WM tracts using Pearson correlation and multiple regression models. RESULTS: Based on 223 participants who were amyloid positive (mean age of 78 years and 57.0% male, 119 cognitively unimpaired, 56 mild cognitive impairment, and 48 dementia), the results showed that WM tracts NDI decreased with increasing regional Braak tau SUVRs. Of all the significant WM tracts, the uncinate fasciculus (r = -0.274 for Braak I, -0.311 for Braak III/IV, and -0.292 for Braak V/VI, p < 0.05) and cingulum adjoining hippocampus (r = -0.274, -0.288, -0.233, p < 0.05), both tracts anatomically connected to areas of early tau deposition, were consistently found to be within the top 5 distinguishing WM tracts associated with flortaucipir SUVRs. The increase in tau deposition measurable outside the medial temporal lobes in Braak III-VI was associated with a decrease in NDI in the middle and inferior temporal WM tracts. For cognitive performance, WM NDI had similar coefficients of determination (r 2 = 31%) as regional Braak flortaucipir SUVRs (29%), and together WM NDI and regional Braak flortaucipir SUVRs explained 46% of the variance in cognitive performance. DISCUSSION: We found spatially dependent WM degeneration associated with regional flortaucipir SUVRs in Braak stages, suggesting a spatial pattern in WM damage. NDI, a specific marker of axonal density, provides complementary information about disease staging and progression in addition to tau deposition. Measurements of WM changes are important for the mechanistic understanding of multifactorial pathways through which AD causes cognitive dysfunction.

Discrimination of Low-Energy Acetabular Fractures from Controls Using Computed Tomography-Based Bone Characteristics.

The incidence of low-energy acetabular fractures has increased. However, the structural factors for these fractures remain unclear. The objective of this study was to extract trabecular bone architecture and proximal femur geometry (PFG) measures from clinical computed tomography (CT) images to (1) identify possible structural risk factors of acetabular fractures, and (2) to discriminate fracture cases from controls using machine learning methods. CT images of 107 acetabular fracture subjects (25 females, 82 males) and 107 age-gender matched controls were examined. Three volumes of interest, one at the acetabulum and two at the femoral head, were extracted to calculate bone volume fraction (BV/TV), gray-level co-occurrence matrix and histogram of the gray values (GV). The PFG was defined by neck shaft angle and femoral neck axis length. Relationships between the variables were assessed by statistical mean comparisons and correlation analyses. Bayesian logistic regression and Elastic net machine learning models were implemented for classification. We found lower BV/TV at the femoral head (0.51 vs. 0.55, p = 0.012) and lower mean GV at both the acetabulum (98.81 vs. 115.33, p < 0.001) and femoral head (150.63 vs. 163.47, p = 0.005) of fracture subjects when compared to their matched controls. The trabeculae within the femoral heads of the acetabular fracture sides differed in structure, density and texture from the corresponding control sides of the fracture subjects. Moreover, the PFG and trabecular architectural variables, alone and in combination, were able to discriminate fracture cases from controls (area under the receiver operating characteristics curve 0.70 to 0.79). In conclusion, lower density in the acetabulum and femoral head with abnormal trabecular structure and texture at the femoral head, appear to be risk factors for low-energy acetabular fractures.

Structural risk factors for low-energy acetabular fractures.

In this study, we aimed to clarify proximal femur and acetabular structural risk factors associated with low-energy acetabular fractures in the elderly using three-dimensional (3D) computed tomography (CT). Pelvic bones and femurs were segmented and modeled in 3D from abdominopelvic CT images of 121 acetabular fracture patients (mean age 72 ±â€¯12 years, range 50-98 years, 31 females and 90 males) and 121 age-gender matched controls with no fracture. A set of geometric parameters of the proximal femur and the acetabulum was measured. An independent-samples t-test or a Mann-Whitney U test was used for statistical analyses. The fractured side was used for proximal femur geometry, while the contralateral side was used for acetabular geometry. The neck shaft angle (NSA) was significantly smaller (mean 122.1° [95% CI 121.1°-123.2°] vs. 124.6° [123.6°-125.6°], p = 0.001) and the femoral neck axis length (FNALb) was significantly longer (78.1 mm [77.0-79.2 mm] vs. 76.0 mm [74.8-77.2 mm], p = 0.026) in the fracture group than in the controls when genders were combined. The NSA was significantly smaller both for females (120.2° [117.8°-122.6°] vs. 124.7° [122.5°-127.0°], p = 0.007) and for males (122.7° [121.5°-123.8°] vs. 124.6° [123.4°-125.7°], p = 0.006) in the fracture group. However, only males showed a significantly longer FNALb (80.0 mm [78.9-81.1 mm] vs. 77.8 mm [76.6-79.0 mm], p = 0.025). No statistically significant associations of acetabular geometry with fractures were found. However, the mean values of the acetabular angle of Sharp (34°), the lateral center-edge angle (40°), the anterior center-edge angle (62°), and the posterior center-edge angle (105°) indicated possible over-coverage. In conclusion, our findings suggest that proximal femur geometry is associated with low-energy acetabular fractures. Especially elderly subjects with an NSA smaller than normal have an increased risk of acetabular fractures.