Krell‐Roesch, Janina

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.

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.

Background: Considering the world’s rapidly increasing life expectancy, with people working and maintaining active lifestyles longer than ever before, addressing the effects of aging on cognition is of utmost importance. A greater understanding of cognitive aging may also be critical in distinguishing natural cognitive aging from pre-clinical stages of Alzheimer’s disease and related cognitive disorders. Objective: To systematically examine the association between aging and cognitive performance in a cognitively and otherwise healthy probability population-based sample using a computer-based method. Methods: This cross-sectional study enrolled 673 cognitively and otherwise healthy participants aged 25–89 years (mean age 52.3±14.2 years, 52.5% of whom were female) from the Kardiovize study cohort. Mild cognitive impairment and dementia cases were excluded, followed by measurement of cognitive performance with the computer-administered Cogstate Brief Battery. We used ANCOVA and Modified Signed-Likelihood Ratio tests to examine patterns of cognition across age groups. Results: We found a gradual decrease in cognitive performance across the lifespan, which required two decades to demonstrate significant changes. In contrast to attention and learning, psychomotor speed and working memory showed the most significant age-related decrease and variability in performance. The established pattern of cognitive aging was not altered by sex or education. Conclusion: These findings corroborate, validate, and extend the current understanding of natural cognitive aging and pinpoint specific cognitive domains with the most extensive age-related interindividual differences. This will contribute to the development of strategies to preserve cognition with aging and may also serve to improve early diagnostics of cognitive disorders using computer-based methods.

Introduction: Cerebrovascular disease (CVD) and neuropsychiatric symptoms (NPS) are common in older adults and are independently associated with cognitive impairment. In addition, vascular depression (a late-life depression) is hypothesized to be associated with cerebrovascular pathology. Hypothesis: CVD pathology imaging biomarkers (e.g., white matter hyperintensities (WMH), infarctions) are associated with depression and anxiety, and both (depression/anxiety and CVD imaging biomarkers) are independently associated with mild cognitive impairment (MCI). Methods: This cross-sectional study included 1739 Mayo Clinic Study of Aging participants (≥50 years old) without dementia, with comprehensive cognitive evaluations and available data on the Beck Depression Inventory II (BDI), the Beck Anxiety Inventory (BAI) and imaging CVD biomarkers via FLAIR-MRI (i.e., WMH% of total intracranial volume (TIV) and brain infarctions). We used linear and logistic regression models to examine the associations adjusting for age, sex, education, and apolipoprotein E ε4 status. Results: Participants’ mean age (SD) was 71.11 (10.61) years (53.3% males). Higher WMH% TIV burden was significantly associated with higher BDI (b= 0.082, 95%CI: 0.031, 0.133), p=0.002) and BAI scores (b= 0.088, 95%CI: 0.037, 0.140), p=0.001); the presence of infarctions was also associated with a higher BDI score. Both WMH %TIV burden (OR: 1.20 (95%CI:1.05, 1.38), p=0.008) and BDI score (OR: 1.38 (95%CI:1.21, 1.57), p<0.001) were significantly associated with MCI when included simultaneously in the model. We observed similar associations for CVD biomarkers and BAI score with MCI. Conclusions: CVD imaging biomarkers and NPS, as measured by BDI and BAI scores, could represent two distinct processes associated with cognitive impairment. Studies are ongoing to further examine these associations and delineate how CVD, NPS, and other pathophysiology processes (e.g., Alzheimer’s disease) interact and are associated with cognitive impairment.

Abstract Introduction We examined the association between cerebrospinal fluid (CSF)‐derived biomarkers of Alzheimer's disease and neuropsychiatric symptoms (NPS) in older non‐demented adults. Methods We included 784 persons (699 cognitively unimpaired, 85 with mild cognitive impairment) aged ≥ 50 years who underwent CSF amyloid beta (Aβ42), hyperphosphorylated tau 181 (p‐tau), and total tau (t‐tau) as well as NPS assessment using Beck Depression and Anxiety Inventories (BDI‐II, BAI), and Neuropsychiatric Inventory Questionnaire (NPI‐Q). Results Lower CSF Aβ42, and higher t‐tau/Aβ42 and p‐tau/Aβ42 ratios were associated with BDI‐II and BAI total scores, clinical depression (BDI‐II ≥ 13), and clinical anxiety (BAI ≥ 10), as well as NPI‐Q–assessed anxiety, apathy, and nighttime behavior. Discussion CSF Aβ42, t‐tau/Aβ42, and p‐tau/Aβ42 ratios were associated with NPS in community‐dwelling individuals free of dementia. If confirmed by a longitudinal cohort study, the findings have clinical relevance of taking into account the NPS status of individuals with abnormal CSF biomarkers.

Abstract Introduction We investigated the longitudinal relationship between cortical amyloid deposition, anxiety, and depression and the risk of incident mild cognitive impairment (MCI). Methods We followed 1440 community‐dwelling, cognitively unimpaired individuals aged ≥ 50 years for a median of 5.5 years. Clinical anxiety and depression were assessed using Beck Anxiety and Depression Inventories (BAI, BDI‐II). Cortical amyloid beta (Aβ) was measured by Pittsburgh compound B positron emission tomography (PiB‐PET) and elevated deposition (PiB+) was defined as standardized uptake value ratio ≥ 1.48. We calculated Cox proportional hazards models with age as the time scale, adjusted for sex, education, and medical comorbidity. Results Cortical Aβ deposition (PiB+) independent of anxiety (BAI ≥ 10) or depression (BDI‐II ≥ 13) increased the risk of MCI. There was a significant additive interaction between PiB+ and anxiety (joint effect hazard ratio 6.77; 95% confidence interval 3.58–12.79; P = .031) that is, being PiB+ and having anxiety further amplified the risk of MCI. Discussion Anxiety modified the association between PiB+ and incident MCI.

Background and Purpose: Dementia affects physical as well as cognitive performance. In individuals with dementia (IWD), decline in physical performance increases with disease progression and is associated with higher functional dependence and decreased quality of life. It is paramount to examine factors that potentially preserve physical performance in IWD, particularly in light of conflicting findings on the effectiveness of physical activity interventions on physical performance of IWD, mainly due to limited number of high-quality studies, large heterogeneity in methods used, or insufficient reporting of methods. The aim of this study was to investigate the effects of a 16-week multimodal exercise program (MEP) combining physical and cognitive tasks on physical performance in IWD, and to identify individual characteristics of MEP responders. Methods: A multicenter randomized controlled trial with assessment methods identified by an expert panel was conducted. We included 319 IWD of mild to moderate severity, older than 65 years, who underwent a standardized MEP specifically designed for IWD. At baseline and immediately after the MEP, we assessed physical performance (ie, mobility, balance, and strength) and function of lower extremities (primary outcomes). Potential effects of the MEP on physical performance were identified using 2-factor analyses of variance with repeated measurements within 2 samples (ie, intention-to-treat and per-protocol sample). Additionally, we compared characteristics related to physical performance between positive, non-, and negative responders. Results and Discussion: Neither analysis procedure revealed statistically significant time×group effects. However, 28% to 40% of participants were positive responders with regard to balance, and strength and function of lower extremities; and these persons had statistically significant lower baseline performance in the corresponding assessments. Conclusions: This randomized controlled trial revealed no overall effects of the MEP on physical performance, probably due to high heterogeneity of the study sample. Findings in responder analysis showed that IWD with lower physical performance at baseline tended to benefit more than those with higher baseline performance. Thus, a higher degree of individualization of the MEP depending on baseline performance on IWD may improve overall MEP effectiveness.