Multivariate Prediction of Hippocampal Atrophy in Alzheimer’s Disease

Article type: Research Article

Authors: Liedes, Hilkka^{a; *} | Lötjönen, Jyrki^{a; b} | Kortelainen, Juha M.^a | Novak, Gerald^c | van Gils, Mark^a | Gordon, Mark Forrest^{d; e} | for the Alzheimer’s Disease Neuroimaging Initiative¹ | and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Ageing²

Affiliations: [a] VTT Technical Research Centre of Finland Ltd, Tampere, Finland | [b] Combinostics Ltd, Tampere, Finland | [c] Janssen Pharmaceutical Research and Development, Titusville, NJ, USA | [d] Boehringer Ingelheim Pharmaceuticals, Inc., Ridgefield, CT, USA | [e] Current affiliation: Teva Pharmaceuticals, Inc., Frazer, PA, USA

Correspondence: [*] Correspondence to: Hilkka Liedes, VTT Technical Research Centre of Finland Ltd, P.O. Box 1300, FIN-33101 Tampere, Finland. Tel.: +358 40 152 6627; Fax: +358 20 722 3499; E-mail: hilkka.liedes@vtt.fi.

Note: [1] Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (http://adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf

Note: [2] Data used in the preparation of this article was obtained from the Australian Imaging Biomarkers and Lifestyle flagship study of ageing (AIBL) funded by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) which was made available at the ADNI database (http://www.loni.usc.edu/ADNI). The AIBL researchers contributed data but did not participate in analysis or writing of this report. AIBL researchers are listed at http://www.aibl.csiro.au.

Abstract: Background:Hippocampal atrophy (HA) is one of the biomarkers for Alzheimer’s disease (AD). Objective:To identify the best biomarkers and develop models for prediction of HA over 24 months using baseline data. Methods:The study included healthy elderly controls, subjects with mild cognitive impairment, and subjects with AD, obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI 1) and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Ageing (AIBL) databases. Predictor variables included cognitive and neuropsychological tests, amyloid-β, tau, and p-tau from cerebrospinal fluid samples, apolipoprotein E, and features extracted from magnetic resonance images (MRI). Least-mean-squares regression with elastic net regularization and least absolute deviation regression models were tested using cross-validation in ADNI 1. The generalizability of the models including only MRI features was evaluated by training the models with ADNI 1 and testing them with AIBL. The models including the full set of variables were not evaluated with AIBL because not all needed variables were available in it. Results:The models including the full set of variables performed better than the models including only MRI features (root-mean-square error (RMSE) 1.76–1.82 versus 1.93–2.08). The MRI-only models performed well when applied to the independent validation cohort (RMSE 1.66–1.71). In the prediction of dichotomized HA (fast versus slow), the models achieved a reasonable prediction accuracy (0.79–0.87). Conclusions:These models can potentially help identifying subjects predicted to have a faster HA rate. This can help in selection of suitable patients into clinical trials testing disease-modifying drugs for AD.

Keywords: Alzheimer’s disease, atrophy, decision support techniques, disease progression, hippocampus, magnetic resonance imaging, regression analysis, statistical models

DOI: 10.3233/JAD-180484

Journal: Journal of Alzheimer's Disease, vol. 68, no. 4, pp. 1453-1468, 2019