Journal of Alzheimer's Disease - Volume 99, issue 4

Authors: Wegner, Philipp | Balabin, Helena | Ay, Mehmet Can | Bauermeister, Sarah | Killin, Lewis | Gallacher, John | Hofmann-Apitius, Martin | Salimi, Yasamin

Article Type: Research Article

Abstract: Background: Despite numerous past endeavors for the semantic harmonization of Alzheimer’s disease (AD) cohort studies, an automatic tool has yet to be developed. Objective: As cohort studies form the basis of data-driven analysis, harmonizing them is crucial for cross-cohort analysis. We aimed to accelerate this task by constructing an automatic harmonization tool. Methods: We created a common data model (CDM) through cross-mapping data from 20 cohorts, three CDMs, and ontology terms, which was then used to fine-tune a BioBERT model. Finally, we evaluated the model using three previously unseen cohorts and compared its performance to a …string-matching baseline model. Results: Here, we present our AD-Mapper interface for automatic harmonization of AD cohort studies, which outperformed a string-matching baseline on previously unseen cohort studies. We showcase our CDM comprising 1218 unique variables. Conclusion: AD-Mapper leverages semantic similarities in naming conventions across cohorts to improve mapping performance. Show more

Keywords: Alzheimer’s disease, automatic data harmonization, cohort study, common data model, data interoperability, semantic mapping

DOI: 10.3233/JAD-240116

Citation: Journal of Alzheimer's Disease, vol. 99, no. 4, pp. 1409-1423, 2024

Authors: Hermes, Stephen | Cady, Janet | Armentrout, Steven | O’Connor, James | Holdaway, Sarah Carlson | Cruchaga, Carlos | Wingo, Thomas | Greytak, Ellen McRae

Article Type: Research Article

Abstract: Background: Polygenic risk scores (PRS) are linear combinations of genetic markers weighted by effect size that are commonly used to predict disease risk. For complex heritable diseases such as late-onset Alzheimer’s disease (LOAD), PRS models fail to capture much of the heritability. Additionally, PRS models are highly dependent on the population structure of the data on which effect sizes are assessed and have poor generalizability to new data. Objective: The goal of this study is to construct a paragenic risk score that, in addition to single genetic marker data used in PRS, incorporates epistatic interaction features and …machine learning methods to predict risk for LOAD. Methods: We construct a new state-of-the-art genetic model for risk of Alzheimer’s disease. Our approach innovates over PRS models in two ways: First, by directly incorporating epistatic interactions between SNP loci using an evolutionary algorithm guided by shared pathway information; and second, by estimating risk via an ensemble of non-linear machine learning models rather than a single linear model. We compare the paragenic model to several PRS models from the literature trained on the same dataset. Results: The paragenic model is significantly more accurate than the PRS models under 10-fold cross-validation, obtaining an AUC of 83% and near-clinically significant matched sensitivity/specificity of 75%. It remains significantly more accurate when evaluated on an independent holdout dataset and maintains accuracy within APOE genotype strata. Conclusions: Paragenic models show potential for improving disease risk prediction for complex heritable diseases such as LOAD over PRS models. Show more

Keywords: Alzheimer’s disease, data mining, deep learning, epistasis, machine learning, predictive genetic testing

DOI: 10.3233/JAD-230236

Citation: Journal of Alzheimer's Disease, vol. 99, no. 4, pp. 1425-1440, 2024

Authors: Nakaya, Moto | Sato, Noriko | Matsuda, Hiroshi | Maikusa, Norihide | Ota, Miho | Shigemoto, Yoko | Sone, Daichi | Yamao, Tensho | Kimura, Yukio | Tsukamoto, Tadashi | Yokoi, Yuma | Sakata, Masuhiro | Abe, Osamu

Article Type: Research Article

Abstract: Background: Cortical neurodegenerative processes may precede the emergence of disease symptoms in patients with Alzheimer’s disease (AD) by many years. No study has evaluated the free water of patients with AD using gray matter-based spatial statistics. Objective: The aim of this study was to explore cortical microstructural changes within the gray matter in AD by using free water imaging with gray matter-based spatial statistics. Methods: Seventy-one participants underwent multi-shell diffusion magnetic resonance imaging, 11 C-Pittsburgh compound B positron emission tomography, and neuropsychological evaluations. The patients were divided into two groups: healthy controls (n  = 40) and the …AD spectrum group (n  = 31). Differences between the groups were analyzed using voxel-based morphometry, diffusion tensor imaging, and free water imaging with gray matter-based spatial statistics. Results: Voxel-based morphometry analysis revealed gray matter volume loss in the hippocampus of patients with AD spectrum compared to that in controls. Furthermore, patients with AD spectrum exhibited significantly greater free water, mean diffusivity, and radial diffusivity in the limbic areas, precuneus, frontal lobe, temporal lobe, right putamen, and cerebellum than did the healthy controls. Overall, the effect sizes of free water were greater than those of mean diffusivity and radial diffusivity, and the larger effect sizes of free water were thought to be strongly correlated with AD pathology. Conclusions: This study demonstrates the utility of applying voxel-based morphometry, gray matter-based spatial statistics, free water imaging and diffusion tensor imaging to assess AD pathology and detect changes in gray matter. Show more

Keywords: Alzheimer’s disease, 11C-Pittsburgh compound B PET, diffusion tensor imaging, free water imaging, gray matter-based spatial statistics, voxel-based morphometry

DOI: 10.3233/JAD-231416

Citation: Journal of Alzheimer's Disease, vol. 99, no. 4, pp. 1441-1453, 2024

Authors: Van Asbroeck, Stephanie | Köhler, Sebastian | Wimmers, Sophie C.P.M. | Muris, Jean W.M. | van Boxtel, Martin P.J. | Deckers, Kay

Article Type: Research Article

Abstract: Background: Dementia risk reduction is a public health priority, but interventions that can be easily implemented in routine care are scarce. Objective: To evaluate the feasibility of integrating dementia risk reduction in regular consultations in primary care and the added value of a dedicated smartphone app (‘MyBraincoach’). Methods: 188 participants (40–60 years), with modifiable dementia risk factors were included from ten Dutch general practices in a cluster-randomized trial (NL9773, 06/10/2021). Practices were randomly allocated (1 : 1) to provide a risk-reduction consultation only or to additionally provide the app. During the consultation, participants learned about dementia risk reduction …and how to improve their risk profile. The app group received daily microteaching-notifications about their personally relevant risk factors. Feasibility was evaluated after 3 months using questionnaires assessing knowledge on dementia risk reduction and health behavior change. The primary outcome was change in the validated “LIfestyle for BRAin health” (LIBRA) score. In-depth interviews were conducted with participants and primary care providers (PCPs). Results: The interventions were positively perceived, with 72.0% finding the consultation informative and 69.2% considering the app useful. Drop-out was low (6.9%). LIBRA improved similarly in both groups, as did Mediterranean diet adherence and body mass index. Knowledge of dementia risk reduction increased, but more in the app group. Interviews provided insight in participants’ and PCPs’ needs and wishes. Conclusions: Integrating dementia risk reduction in primary care, supported by a smartphone app, is a viable approach towards dementia risk reduction. Larger trials are needed to establish (cost-)effectiveness. Show more

Keywords: Alzheimer’s disease, dementia, health behavior, lifestyle, prevention and control, primary health care, risk factors, telemedicine

DOI: 10.3233/JAD-240229

Citation: Journal of Alzheimer's Disease, vol. 99, no. 4, pp. 1455-1471, 2024

Authors: Zhao, Amanda | Balcer, Laura J. | Himali, Jayandra J. | O’Donnell, Adrienne | Rahimpour, Yashar | DeCarli, Charles | Gonzales, Mitzi M. | Aparicio, Hugo J. | Ramos-Cejudo, Jaime | Kenney, Rachel | Beiser, Alexa | Seshadri, Sudha | Salinas, Joel

Article Type: Research Article

Abstract: Background: Loneliness has been declared an “epidemic” associated with negative physical, mental, and cognitive health outcomes such as increased dementia risk. Less is known about the relationship between loneliness and advanced neuroimaging correlates of Alzheimer’s disease (AD). Objective: To assess whether loneliness was associated with advanced neuroimaging markers of AD using neuroimaging data from Framingham Heart Study (FHS) participants without dementia. Methods: In this cross-sectional observational analysis, we used functional connectivity MRI (fcMRI), amyloid-β (Aβ) PET, and tau PET imaging data collected between 2016 and 2019 on eligible FHS cohort participants. Loneliness was defined as feeling …lonely at least one day in the past week. The primary fcMRI marker was Default Mode Network intra-network connectivity. The primary PET imaging markers were Aβ deposition in precuneal and FLR (frontal, lateral parietal and lateral temporal, retrosplenial) regions, and tau deposition in the amygdala, entorhinal, and rhinal regions. Results: Of 381 participants (mean age 58 [SD 10]) who met inclusion criteria for fcMRI analysis, 5% were classified as lonely (17/381). No association was observed between loneliness status and network changes. Of 424 participants (mean age 58 [SD = 10]) meeting inclusion criteria for PET analyses, 5% (21/424) were lonely; no associations were observed between loneliness and either Aβ or tau deposition in primary regions of interest. Conclusions: In this cross-sectional study, there were no observable associations between loneliness and select fcMRI, Aβ PET, and tau PET neuroimaging markers of AD risk. These findings merit further investigation in prospective studies of community-based cohorts. Show more

Keywords: Alzheimer’s disease, amyloid, dementia, functional neuroimaging, loneliness, longitudinal studies, tau protein

DOI: 10.3233/JAD-231425

Citation: Journal of Alzheimer's Disease, vol. 99, no. 4, pp. 1473-1484, 2024