Search

Your search keyword '"Sarah Sanchez Hoffmann"' showing total 3 results
Start Over Author "Sarah Sanchez Hoffmann"
3 results on '"Sarah Sanchez Hoffmann"'

1. Sociodemographic data and APOE-ε4 augmentation for MRI-based detection of amnestic mild cognitive impairment using deep learning systems.

Author

Obioma Pelka, Christoph M Friedrich, Felix Nensa, Christoph Mönninghoff, Louise Bloch, Karl-Heinz Jöckel, Sara Schramm, Sarah Sanchez Hoffmann, Angela Winkler, Christian Weimar, Martha Jokisch, and Alzheimer’s Disease Neuroimaging Initiative

Subjects
Medicine, Science
Abstract

Detection and diagnosis of early and subclinical stages of Alzheimer's Disease (AD) play an essential role in the implementation of intervention and prevention strategies. Neuroimaging techniques predominantly provide insight into anatomic structure changes associated with AD. Deep learning methods have been extensively applied towards creating and evaluating models capable of differentiating between cognitively unimpaired, patients with Mild Cognitive Impairment (MCI) and AD dementia. Several published approaches apply information fusion techniques, providing ways of combining several input sources in the medical domain, which contributes to knowledge of broader and enriched quality. The aim of this paper is to fuse sociodemographic data such as age, marital status, education and gender, and genetic data (presence of an apolipoprotein E (APOE)-ε4 allele) with Magnetic Resonance Imaging (MRI) scans. This enables enriched multi-modal features, that adequately represent the MRI scan visually and is adopted for creating and modeling classification systems capable of detecting amnestic MCI (aMCI). To fully utilize the potential of deep convolutional neural networks, two extra color layers denoting contrast intensified and blurred image adaptations are virtually augmented to each MRI scan, completing the Red-Green-Blue (RGB) color channels. Deep convolutional activation features (DeCAF) are extracted from the average pooling layer of the deep learning system Inception_v3. These features from the fused MRI scans are used as visual representation for the Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) classification model. The proposed approach is evaluated on a sub-study containing 120 participants (aMCI = 61 and cognitively unimpaired = 59) of the Heinz Nixdorf Recall (HNR) Study with a baseline model accuracy of 76%. Further evaluation was conducted on the ADNI Phase 1 dataset with 624 participants (aMCI = 397 and cognitively unimpaired = 227) with a baseline model accuracy of 66.27%. Experimental results show that the proposed approach achieves 90% accuracy and 0.90 F1-Score at classification of aMCI vs. cognitively unimpaired participants on the HNR Study dataset, and 77% accuracy and 0.83 F1-Score on the ADNI dataset.

Published
2020
Full Text
View/download PDF

2. Blood pressure and cognitive decline – the impact of hypertension over one decade

Author

Sarah Sanchez Hoffmann, Raimund Erbel, Karl-Heinz Jöckel, Diana Müller-Gerards, Jessica Abramowski, Christian Weimar, Martha Jokisch, Susanne Moebus, and Angela Winkler

Subjects
Male, Gerontology, Aging, medicine.medical_specialty, Medizin, Experimental and Cognitive Psychology, Neuropsychological Tests, 050105 experimental psychology, 03 medical and health sciences, 0302 clinical medicine, Risk Factors, Cognitive change, Germany, Epidemiology, medicine, Humans, Cognitive Dysfunction, 0501 psychology and cognitive sciences, Longitudinal Studies, Risk factor, Cognitive decline, Aged, 05 social sciences, Middle Aged, Psychiatry and Mental health, Neuropsychology and Physiological Psychology, Blood pressure, Hypertension, Female, sense organs, Geriatrics and Gerontology, Psychology, 030217 neurology & neurosurgery, Follow-Up Studies
Abstract

Midlife hypertension is a risk factor for cognitive decline in late-life but little is known about the impact of long-term hypertension on cognitive change over time.We examined blood pressure and cognitive function in 2777 participants (baseline: 2000-2003, 45-75 years, 48.4% men) from the Heinz Nixdorf Recall study. Blood pressure was assessed at three study visits and cognitive function was assessed at both follow-ups (mean follow-up: 5.1 years). Z-score differences in five neuropsychological tests, defining cognitive decline, were derived from linear regression models including age and education. The association of cognitive decline over 5 years and blood pressure over 10 years (classified as: normal blood pressure (10 years, reference), prevalent hypertension (10 years), incident hypertension t1 (5 years), incident hypertension t2 (5 years), temporary hypertension (at least one hypertensive reading)) was calculated using linear regression models resulting in coefficient b and 95% confidence interval. We calculated interactions with age (linear and with a cutoff at 65 years).Participants with prevalent hypertension showed a greater cognitive decline in both verbal memory tests. Incident hypertension t1 was associated with a greater decline in the visuospatial organization test. There was no interaction with age.This study showed that prevalent high blood pressure over 10 years is related to cognitive decline. Prevalent hypertension with longer exposure time may be more detrimental than temporary hypertension for cognitive function.

Published
2020

3. Trail Making Test Normative Data for the German Older Population

Author

Andreas Stang, Christian Weimar, Karl-Heinz Jöckel, Sarah Sanchez Hoffmann, Michael Specka, Bernd Kowall, Martha Jokisch, and Norbert Scherbaum

Subjects
050103 clinical psychology, Trail Making Test, Population, Medizin, Neuropsychological Tests, 03 medical and health sciences, 0302 clinical medicine, Reference Values, medicine, Dementia, Humans, 0501 psychology and cognitive sciences, Cognitive Dysfunction, education, education.field_of_study, 05 social sciences, General Medicine, Center for Epidemiologic Studies Depression Scale, medicine.disease, Mental Status and Dementia Tests, Educational attainment, Psychiatry and Mental health, Clinical Psychology, Neuropsychology and Physiological Psychology, Categorization, Normative, Psychology, Neurocognitive, 030217 neurology & neurosurgery, Demography
Abstract

Objective We provide normative data for the Trail Making Test (TMT)-A and B and the derived scores B − A and B/A, for the German general population aged 57–84 years. Methods Data were derived from the third examination of the population-based Heinz Nixdorf Recall study. We excluded participants with a history of dementia or stroke, a depression score above cutoff (CES-D Center for Epidemiologic Studies Depression Scale score ≥ 18), or mild cognitive impairment according to a neurocognitive test battery. The normative sample (n = 2,182) was stratified by age, using the interval superposition approach, and by three levels of educational attainment (up to 10 years of schooling; >10 years of schooling; and university degree). Results We tabulated test performance scores at percentage rank thresholds 5, 10, 15, 20, 25, 50, 75, and 90. In multiple linear regression, TMT-A performance declined by 1 s each year of life, and TMT-B performance by 3 s; educational level had an impact of up to 30 s in TMT-B. TMT-B/A was only weakly associated with age and education. TMT-B and B − A correlated r = 0.96. Completion of the TMT-B within the time limit of 300 s was not achieved by 10.9% of participants >74 years, and especially by those >74 years who were on the lowest educational level (13.9%). Conclusions For TMT-A, TMT-B, and B − A, the narrow age categorization and distinction between three educational levels proved meaningful. The 300 s limit for the TMT-B impedes the identification of thresholds for very low performance in this age group and needs reconsideration.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results