Journal
ALZHEIMERS RESEARCH & THERAPY
Volume 10, Issue -, Pages -Publisher
BMC
DOI: 10.1186/s13195-018-0428-1
Keywords
Alzheimer's disease; Mild cognitive impairment; Biomarkers; Magnetic resonance imaging; Amyloid; Machine learning; Support vector machine; European Medical Information Framework for Alzheimer's Disease
Categories
Funding
- Innovative Medicines Initiative Joint Undertaking under EMIF grant [115372]
- European Union's Seventh Framework Programme (FP7/2007-2013)
- EFPIA
- European Commission within the Fifth Framework Programme [QLRT-2001-2455, 37670]
- Stichting Alzheimer Nederland
- Stichting VUmc fonds
- Stichting Dioraphte
- Stichting voor Alzheimer Onderzoek [11020, 13007, 15005]
- Department of Economic Promotion, Rural Areas and Territorial Balance of the Provincial Government of Gipuzkoa [124/16]
- Department of Health of the Basque Government [2016111096]
- Carlos III Institute of Health [PI15/00919]
- Obra Social Kutxa-Fundazioa
- Sahlgrenska University Hospital, Gothenburg, Sweden
- Swiss National Research Foundation [SNF 320030_141179]
- University of Antwerp Research Fund
- Flemish government-initiated Flanders Impulse Program on Networks for Dementia Research (VIND)
- Methusalem Excellence Program, the Research Foundation Flanders (FWO)
- University of Antwerp Research Fund, Belgium
- NIHR UCLH Biomedical Research Centre
- Dementia Research Institute at UCL
- ZonMw
- European Union's Horizon 2020 Research and Innovation Programme [666992]
Ask authors/readers for more resources
Background: With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) epsilon 4 genotype, can be used to predict amyloid pathology using machine-learning classification. Methods: We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 +/- 72, 50% female, 27% amyloid positive), mild cognitive impairment (MCI, n = 375, age 69. 1 +/- 7.5, 53% female, 63% amyloid positive) and AD dementia (n = 98, age 67.0 +/- 7.7, 48% female, 97% amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE epsilon 4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects. Results: In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 +/- O. 07 in MCI and an AUC of 0.74 +/- 0.08 in CN. In CN, selected features for the classifier included APOE epsilon 4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE epsilon 4 information did not improve after additionally adding imaging measures. Conclusions: Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE epsilon 4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available