Authors: Harvey, Danielle J. | Beckett, Laurel A. | Mungas, Dan M.
Article Type: Research Article
Abstract: Longitudinal studies of Alzheimer's disease provide information about cognitive decline and predictors of this decline. However, overall cognitive function is comprised of many underlying processes, each of which may respond differently over time and may be affected by different predictors. In addition to studying how these processes decline independently, one might also be interested in how the processes decline together. Multivariate growth models, an extension and modification of random effects models, provide a means of dealing with these issues and enable assessing the association between the processes of interest. This technique allows for separate random effects and predictors for each …process in the same model, thereby providing simultaneous estimates of the model parameters and variability for each process. We can then determine if factors associated with decline in one process are also associated with decline in another process and the extent to which the processes differ. We provide data that include information on two underlying processes of cognitive function, namely memory and executive function, to illustrate this methodology. Show more
DOI: 10.3233/JAD-2003-5502
Citation: Journal of Alzheimer's Disease, vol. 5, no. 5, pp. 357-365, 2003
Authors: DeCarli, Charles | Villeneuve, Sylvia | Maillard, Pauline | Harvey, Danielle | Singh, Baljeet | Carmichael, Owen | Fletcher, Evan | Olichney, John | Farias, Sarah | Jagust, William | Reed, Bruce | Mungas, Dan
Article Type: Research Article
Abstract: Background/Objective: To determine the impact of vascular burden on rates of decline in episodic memory and executive function. We hypothesize that greater vascular burden will have an additive negative impact on cognition after accounting for baseline cognitive impairment, positron emission tomography (PET) amyloid burden, and magnetic resonance imaging (MRI) measures. Methods: Individuals were followed an average of 5 years with serial cognitive assessments. Predictor variables include vascular burden score (VBS), quantitative brain MRI assessment, and amyloid imaging. Subjects consisted of 65 individuals, 53% of whom were male, aged 73.2±7.2 years on average with an average of 15.5±3.3 years of educational …achievement. Results: Baseline cognitive impairment was significantly associated poorer episodic memory (p < 0.0001), smaller hippocampal volume (p < 0.0001), smaller brain volume (p = 0.0026), and greater global Pittsburg Imaging Compound B (PiB) index (p = 0.0008). Greater amyloid burden was associated with greater decline in episodic memory over time (β= –0.20±0.07, p < 0.005). VBS was significantly associated with the level of executive function performance (β= –0.14±0.05, p < 0.005) and there was a significant negative interaction between VBS, cognitive impairment, and PiB index (β= –0.065±0.03, p = 0.03). Conclusions: Our results find a significant influence of VBS independent of standard MRI measures and cerebral amyloid burden on executive function. In addition, VBS reduced the amount of cerebral amyloid burden needed to result in cognitive impairment. We conclude that the systemic effects of vascular disease as reflected by the VBS independently influence cognitive ability. Show more
Keywords: Alzheimer’s disease, cerebrovascular disorders, cognition, neuroimaging
DOI: 10.3233/JAD-180965
Citation: Journal of Alzheimer's Disease, vol. 68, no. 1, pp. 187-196, 2019
Authors: Ezzati, Ali | Zammit, Andrea R. | Harvey, Danielle J. | Habeck, Christian | Hall, Charles B. | Lipton, Richard B. | for the Alzheimer’s Disease Neuroimaging Initiative
Article Type: Research Article
Abstract: Background: Predicting clinical course of cognitive decline can boost clinical trials’ power and improve our clinical decision-making. Machine learning (ML) algorithms are specifically designed for the purpose of prediction; however. identifying optimal features or algorithms is still a challenge. Objective: To investigate the accuracy of different ML methods and different features to classify cognitively normal (CN) individuals from Alzheimer’s disease (AD) and to predict longitudinal outcome in participants with mild cognitive impairment (MCI). Methods: A total of 1,329 participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) were included: 424 CN, 656 MCI, and 249 AD individuals. Four feature-sets at baseline …(hippocampal volume and volume of 47 cortical and subcortical regions with and without demographics and APOE4 ) and six machine learning methods (decision trees, support vector machines, K-nearest neighbor, ensemble linear discriminant, boosted trees, and random forests) were used to classify participants with normal cognition from participants with AD. Subsequently the model with best classification performance was used for predicting clinical outcome of MCI participants. Results: Ensemble linear discriminant models using demographics and all volumetric magnetic resonance imaging measures as feature-set showed the best performance in classification of CN versus AD participants (accuracy = 92.8%, sensitivity = 95.8%, and specificity = 88.3%). Prediction accuracy of future conversion from MCI to AD for this ensemble linear discriminant at 6, 12, 24, 36, and 48 months was 63.8% (sensitivity = 74.4, specificity = 63.1), 68.9% (sensitivity = 75.9, specificity = 67.8), 74.9% (sensitivity = 71.5, specificity = 76.3), 75.3%, (sensitivity = 65.2, specificity = 79.7), and 77.0% (sensitivity = 59.6, specificity = 86.1), respectively. Conclusions: Machine learning models trained for classification of CN versus AD can improve our prediction ability of MCI conversion to AD. Show more
Keywords: Alzheimer’s disease, classification, early diagnosis, machine learning, magnetic resonance imaging, mild cognitive impairment, predictive analytics
DOI: 10.3233/JAD-190262
Citation: Journal of Alzheimer's Disease, vol. 71, no. 3, pp. 1027-1036, 2019
Authors: Ezzati, Ali | Harvey, Danielle J. | Habeck, Christian | Golzar, Ashkan | Qureshi, Irfan A. | Zammit, Andrea R. | Hyun, Jinshil | Truelove-Hill, Monica | Hall, Charles B. | Davatzikos, Christos | Lipton, Richard B. | for the Alzheimer’s Disease Neuroimaging Initiative
Article Type: Research Article
Abstract: Background: Amyloid-β positivity (Aβ+) based on PET imaging is part of the enrollment criteria for many of the clinical trials of Alzheimer’s disease (AD), particularly in trials for amyloid-targeted therapy. Predicting Aβ positivity prior to PET imaging can decrease unnecessary patient burden and costs of running these trials. Objective: The aim of this study was to evaluate the performance of a machine learning model in estimating the individual risk of Aβ+ based on gold-standard of PET imaging. Methods: We used data from an amnestic mild cognitive impairment (aMCI) subset of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort to develop and …validate the models. The predictors of Aβ status included demographic and ApoE4 status in all models plus a combination of neuropsychological tests (NP), MRI volumetrics, and cerebrospinal fluid (CSF) biomarkers. Results: The models that included NP and MRI measures separately showed an area under the receiver operating characteristics (AUC) of 0.74 and 0.72, respectively. However, using NP and MRI measures jointly in the model did not improve prediction. The models including CSF biomarkers significantly outperformed other models with AUCs between 0.89 to 0.92. Conclusions: Predictive models can be effectively used to identify persons with aMCI likely to be amyloid positive on a subsequent PET scan. Show more
Keywords: Alzheimer’s disease, amyloid imaging, machine learning, mild cognitive impairment, predictive analytics
DOI: 10.3233/JAD-191038
Citation: Journal of Alzheimer's Disease, vol. 73, no. 3, pp. 1211-1219, 2020
Authors: Huie, Emily Z. | Escudero, Anthony | Saito, Naomi | Harvey, Danielle | Nguyen, My-Le | Lucot, Katherine L. | LaGrande, Jayne | Mungas, Dan | DeCarli, Charles | Lamar, Melissa | Schneider, Julie A. | Kapasi, Alifiya | Rissman, Robert A. | Teich, Andrew F. | Dugger, Brittany N.
Article Type: Research Article
Abstract: Background: Transactive Response DNA Binding Protein 43 kDa (TDP-43) pathology is frequently found in cases with Alzheimer’s disease (AD). TDP-43 pathology is associated with hippocampal atrophy and greater AD severity denoted by cognition and clinical representation. Current TDP-43 pathology studies are predominantly based on non-Hispanic White cohorts. Objective: We sought to evaluate the presence of TDP-43 pathology across ethnoracial groups utilizing the National Alzheimer’s Coordinating Center; a database containing data from over 29 institutions across the United States. Cases (N = 1135: Hispanics/Latinos = 29, African Americans/Black Americans = 51, Asians/Asian Americans = 10, American Indians/Alaskan Natives = 2, non-Hispanic …White = 1043) with intermediate/high AD having data on TDP-43 pathology in the amygdala, hippocampus, entorhinal cortex, and neocortex were included. Methods: TDP-43 pathology frequency in each neuroanatomic region among ethnoracial groups were compared using generalized linear mixed effects models with center as a random effect adjusting for age at death, education, and gender. Results: Although groups were imbalanced, there was no significant difference across ethnoracial groups based on TDP-43 pathology (p = 0.84). With respect to neuroanatomical regions evaluated, there were no significant differences across ethnoracial groups (p -values > 0.06). There were also no significant differences for age at death and gender ratios across ethnoracial groups based on TDP-43 pathology. Although not statistically significant, TDP-43 pathology was present less often in Hispanic/Latinos (34%) when compared to non-Hispanic Whites (46%). Conclusion: While this is a preliminary evaluation, it highlights the need for diverse cohorts and on TDP-43 pathology research across ethnoracial groups. This is the first study to our knowledge having a focus on the neuroanatomical distribution of TDP-43 deposits in Hispanic/Latino decedents with AD. Show more
Keywords: African American, Alzheimer’s disease, Asian, brain, cohort studies, Hispanic, Latino, minoritized groups, neuropathology
DOI: 10.3233/JAD-220558
Citation: Journal of Alzheimer's Disease, vol. 91, no. 4, pp. 1291-1301, 2023