Kremers, Walter K.

AbstractFrom a complex systems perspective, clinical syndromes emerging from neurodegenerative diseases are thought to result from multiscale interactions between aggregates of misfolded proteins and the disequilibrium of large-scale networks coordinating functional operations underpinning cognitive phenomena. Across all syndromic presentations of Alzheimer’s disease, age-related disruption of the default mode network is accelerated by amyloid deposition. Conversely, syndromic variability may reflect selective neurodegeneration of modular networks supporting specific cognitive abilities. In this study, we leveraged the breadth of the Human Connectome Project-Aging cohort of non-demented individuals (N = 724) as a normative cohort to assess the robustness of a biomarker of default mode network dysfunction in Alzheimer’s disease, the network failure quotient, across the aging spectrum. We then examined the capacity of the network failure quotient and focal markers of neurodegeneration to discriminate patients with amnestic (N = 8) or dysexecutive (N = 10) Alzheimer’s disease from the normative cohort at the patient level, as well as between Alzheimer’s disease phenotypes. Importantly, all participants and patients were scanned using the Human Connectome Project-Aging protocol, allowing for the acquisition of high-resolution structural imaging and longer resting-state connectivity acquisition time. Using a regression framework, we found that the network failure quotient related to age, global and focal cortical thickness, hippocampal volume, and cognition in the normative Human Connectome Project-Aging cohort, replicating previous results from the Mayo Clinic Study of Aging that used a different scanning protocol. Then, we used quantile curves and group-wise comparisons to show that the network failure quotient commonly distinguished both dysexecutive and amnestic Alzheimer’s disease patients from the normative cohort. In contrast, focal neurodegeneration markers were more phenotype-specific, where the neurodegeneration of parieto-frontal areas associated with dysexecutive Alzheimer’s disease, while the neurodegeneration of hippocampal and temporal areas associated with amnestic Alzheimer’s disease. Capitalizing on a large normative cohort and optimized imaging acquisition protocols, we highlight a biomarker of default mode network failure reflecting shared system-level pathophysiological mechanisms across aging and dysexecutive and amnestic Alzheimer’s disease and biomarkers of focal neurodegeneration reflecting distinct pathognomonic processes across the amnestic and dysexecutive Alzheimer’s disease phenotypes. These findings provide evidence that variability in inter-individual cognitive impairment in Alzheimer’s disease may relate to both modular network degeneration and default mode network disruption. These results provide important information to advance complex systems approaches to cognitive aging and degeneration, expand the armamentarium of biomarkers available to aid diagnosis, monitor progression and inform clinical trials.

There is a growing interest in the application of machine learning (ML) in Alzheimer’s disease (AD) research. However, neuropsychiatric symptoms (NPS), frequent in subjects with AD, mild cognitive impairment (MCI), and other related dementias have not been analyzed sufficiently using ML methods. To portray the landscape and potential of ML research in AD and NPS studies, we present a comprehensive literature review of existing ML approaches and commonly studied AD biomarkers. We conducted PubMed searches with keywords related to NPS, AD biomarkers, machine learning, and cognition. We included a total of 38 articles in this review after excluding some irrelevant studies from the search results and including 6 articles based on a snowball search from the bibliography of the relevant studies. We found a limited number of studies focused on NPS with or without AD biomarkers. In contrast, multiple statistical machine learning and deep learning methods have been used to build predictive diagnostic models using commonly known AD biomarkers. These mainly included multiple imaging biomarkers, cognitive scores, and various omics biomarkers. Deep learning approaches that combine these biomarkers or multi-modality datasets typically outperform single-modality datasets. We conclude ML may be leveraged to untangle the complex relationships of NPS and AD biomarkers with cognition. This may potentially help to predict the progression of MCI or dementia and develop more targeted early intervention approaches based on NPS.

Background. Mortality risk assessment before kidney transplantation (KT) is imperfect. An emerging risk factor for death in nontransplant populations is physiological age as determined by the application of artificial intelligence to the electrocardiogram (ECG). The aim of this study was to examine the relationship between ECG age and KT waitlist mortality. Methods. We applied a previously developed convolutional neural network to the ECGs of KT candidates evaluated 2014 to 2019 to determine ECG age. We used a Cox proportional hazard model to examine whether ECG age was associated with waitlist mortality. Results. Of the 2183 patients evaluated, 59.1% were male, 81.4% were white, and 11.4% died during follow-up. Mean ECG age was 59.0 ± 12.0 y and mean chronological age at ECG was 53.3 ± 13.6 y. After adjusting for chronological age, comorbidities, and other characteristics associated with mortality, each increase in ECG age of >10 y than the average ECG age for patients of a similar chronological age was associated with an increase in mortality risk (hazard ratio 3.59 per 10-y increase; 95% confidence interval, 2.06-5.72; P < 0.0001). Conclusions. ECG age is a risk factor for KT waitlist mortality. Determining ECG age through artificial intelligence may help guide risk-benefit assessment when evaluating candidates for KT.

AbstractIntroductionEmpathy relies on fronto‐cingular and temporal networks that are selectively vulnerable in behavioral variant frontotemporal dementia (bvFTD). This study modeled when in the disease process empathy changes begin, and how they progress.MethodsFour hundred thirty‐one individuals with asymptomatic genetic FTD (n = 114), genetic and sporadic bvFTD (n = 317), and 163 asymptomatic non‐carrier controls were enrolled. In sub‐samples, we investigated empathy measured by the informant‐based Interpersonal Reactivity Index (IRI) at each disease stage and over time (n = 91), and its correspondence to underlying atrophy (n = 51).ResultsEmpathic concern (estimate = 4.38, 95% confidence interval [CI] = 2.79, 5.97; p < 0.001) and perspective taking (estimate = 5.64, 95% CI = 3.81, 7.48; p < 0.001) scores declined between the asymptomatic and very mild symptomatic stages regardless of pathogenic variant status. More rapid loss of empathy corresponded with subcortical atrophy.DiscussionLoss of empathy is an early and progressive symptom of bvFTD that is measurable by IRI informant ratings and can be used to monitor behavior in neuropsychiatry practice and treatment trials.

Abstract Introduction We aimed to define a Mayo Preclinical Alzheimer's disease Cognitive Composite (Mayo‐PACC) that prioritizes parsimony and use of public domain measures to facilitate clinical translation. Methods Cognitively unimpaired participants aged 65 to 85 at baseline with amyloid PET imaging were included, yielding 428 amyloid negative (A‐) and 186 amyloid positive (A+) individuals with 7 years mean follow‐up. Sensitivity to amyloid‐related cognitive decline was examined using slope estimates derived from linear mixed models (difference in annualized change across A+ and A‐ groups). We compared differences in rates of change between Mayo‐PACC and other composites (A+ > A‐ indicating more significant decline in A+). Results All composites showed sensitivity to amyloid‐related longitudinal cognitive decline (A+ > A‐ annualized change p < 0.05). Comparisons revealed that Mayo‐PACC (AVLT sum of trials 1‐5+6+delay, Trails B, animal fluency) showed comparable longitudinal sensitivity to other composites. Discussion Mayo‐PACC performs similarly to other composites and can be directly translated to the clinic.

AbstractBackgroundStudies of aging and dementia often acquire brain MRI and PET images, then de‐identify and share these widely with other researchers. It is known that research participants can potentially be re‐identified from brain MRI and CT using face recognition, but this has not been tested with PET imaging.MethodWe generated face reconstruction images of 182 volunteers using their existing amyloid (PiB), tau (FTP), and FDG PET scans from clinical GE PET/CT scanners, and we measured how often commercial automatic face recognition (Microsoft Azure) correctly matched these reconstructions with photographs of their faces. We additionally compared these match rates with face reconstructions from CT (from PET/CT) and MRI. When testing face recognition from PET scans, CT was used only during PET reconstruction, not for face recognition. We also validated our updated mri_reface software, originally developed to de‐identify (“de‐face”) faces in MRI, with new support for PET images. We measured face recognition rates before and after applying mri_reface to PET, CT, and MRI. In addition, we measured effects of de‐facing on biomarker measurements (global and regional SUVR) using 244 ADNI Florbetapir (FBP) amyloid PET scans with two automated pipelines: FreeSurfer 6.0 (PETSurfer) and an in‐house SPM12‐based pipeline.ResultRates of successful face recognition with PET ranged from 32‐41% (Table 1) across tracers. These were lower than MRI (98%) and CT (78%) but still concerning for participant privacy. Using mri_reface reduced face recognition to 0‐3.5% for PET, 5% for CT, and 8% for MRI. mri_reface had little effect on global amyloid SUVR measurements from ADNI PET images (Figure 1). ICC values between original and de‐faced images were 1.00 with biases and median absolute differences < 0.5%, across both pipelines. Effects on individual regions all had ICC values > 0.98 with biases and median absolute differences < 2%.ConclusionFace reconstructions from PET images have sufficient quality for potential re‐identification using publicly available face recognition technology. Research studies should consider using face de‐identification (de‐facing) software on PET images in addition to CT and structural MRI. Our free, automatic mri_reface software greatly reduced the potential for face recognition without substantially affecting SUVR measurements.

AbstractBackgroundPhysical and cognitive activities are associated with decreased risk of mild cognitive impairment and dementia. However, the longitudinal associations between physical and cognitive activities with trajectories of Alzheimer’s disease (AD) neuroimaging biomarkers among older adults free of dementia remain unclear.MethodWe conducted a longitudinal study derived from the population‐based Mayo Clinic Study of Aging, including individuals aged ≥ 50 years who were free of dementia. Participants had information on physical and cognitive activity engagement in midlife (ages 30‐45 for participants aged 50‐69; ages 50‐65 for participants aged ≥ 70) and late‐life (12 months prior to baseline assessment), and AD biomarker assessments. We calculated linear mixed‐effect models to examine the association between baseline physical and cognitive activity composite scores for mid‐ and late‐life, and trajectories for individual yearly change in amyloid deposition (measured by PiB‐PET), tau burden (measured by Tau‐PET), regional glucose hypometabolism (measured by FDG‐PET), cortical thickness (measured by MRI), and white matter hyper intensities (WMH, measured by FLAIR‐MRI). The models were adjusted for age, sex, and APOE ɛ4 carrier status.ResultThe sample included 2755 persons (52% males; 2462 cognitively unimpaired, 293 with MCI). The mean [SD] age was 72.7 [9.8] years; 774 participants were APOE ɛ4 carriers. Although, overall, participants showed an increase in amyloid deposition, tau burden, WMH, and a decrease in glucose metabolism and cortical thickness over time, those with higher late‐life physical activity experienced less pronounced increase in Tau‐PET SUVR over time [estimate for late‐life physical activity with time interaction: ‐0.002; 95% CI ‐0.004, ‐0.000; p = 0.034]. In addition, participants with higher cognitive activities in midlife [est. for midlife cognitive activity with time interaction: 0.001; 95% CI 0.000, 0.003; p = 0.026] and late‐life [est. for late‐life cognitive activity with time interaction 0.002; 95% CI 0.001, 0.003; p = 0.005] had less pronounced decrease in FDG‐PET SUVR over time. There were no further significant interactions.ConclusionPreliminary findings suggest significant associations between 1) late‐life physical activity and less tauopathy, and 2) cognitive activities in mid‐ and late‐life with less synaptic dysfunction over time. Further research is needed to validate study findings.

AbstractBackgroundMayo Test Drive (MTD): Test Development through Rapid Iteration, Validation and Expansion, is a web‐based platform optimized for remote self‐administered assessment that includes a computer adaptive word list memory test (Stricker Learning Span; SLS) and a measure of processing speed (Symbols Test). Study aims were to determine 1) convergent validity of MTD through correlations with in‐person neuropsychological measures and 2) criterion validity of MTD by qualitatively comparing the ability of Mayo Test Drive and in‐person administered neuropsychological measures to differentiate biomarker‐defined groups, independent of clinical diagnosis.MethodsMayo Clinic Study of Aging participants (N = 282) completed a brief remote cognitive assessment (mean age = 74, SD = 12; 262 CU and 20 MCI per consensus conference diagnosis; see Table 1). A subset of participants had brain amyloid and/or brain tau PET scans available within 3 years; overlapping groups were formed for 1) those on the Alzheimer’s disease (AD) continuum (A+, n = 31) or not (A‐, n = 57) and for 2) those with biological AD (A+T+, n = 19) or without any AD biomarkers (A‐T‐, n = 47). Primary outcome variables were SLS sum of trials, AVLT sum of trials, SYM Correct Trials response time, Digit Symbol Coding, MTD composite and Mayo‐PACC (AVLT sum of trials, Trails B, animals). Bivariate correlations were performed across all participants. Linear model ANOVAs were used to investigate biomarker subgroup differences; Hedge’s g effect sizes are reported.ResultsConvergent validity was supported through significant correlation (p’s < .001) of SLS and AVLT (r = .63), SYM and Coding (r = ‐.64), and MTD composite with Mayo‐PACC (r = .67); see Table 2. MTD subtests showed expected relationships with age and education (p’s < .05; Table 3). All MTD performances were significantly lower for A+ and A+T+ participants relative to A‐ or A‐T‐ (p’s<.001; Table 4). All MTD outcome measures showed a similar or greater group difference effect size relative to traditional in‐person administered neuropsychological measures for separating A+ vs. A‐ and A+T+ vs. A‐T‐ groups. See Figure 1 and Table 4.ConclusionsMTD subtests show evidence of convergent validity through strong correlations with traditional in‐person cognitive measures. Preliminary analyses suggest MTD has promise for differentiating PET biomarker groups.