E Doering1,2, M C Hoenig3,4, G N Bischof3,4, K P Bohn5, L M Ellingsen6,7, T van Eimeren3,8, A Drzezga3,9,4. 1. German Center for Neurodegenerative Diseases (DZNE), Bonn-Cologne, Germany. elena.doering@uk-koeln.de. 2. University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Nuclear Medicine, Multimodal Neuroimaging Group, Cologne, Germany. elena.doering@uk-koeln.de. 3. German Center for Neurodegenerative Diseases (DZNE), Bonn-Cologne, Germany. 4. Institute for Neuroscience and Medicine II-Molecular Organization of the Brain, Research Center Juelich, Jülich, Germany. 5. Klinikum Dritter Orden, Department of Radiology and Nuclear Medicine, Munich, Germany. 6. Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA. 7. Department of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland. 8. University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Neurology, Cologne, Germany. 9. University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Nuclear Medicine, Multimodal Neuroimaging Group, Cologne, Germany.
Abstract
BACKGROUND: In patients with mild cognitive impairment (MCI), enhanced cerebral amyloid-β plaque burden is a high-risk factor to develop dementia with Alzheimer's disease (AD). Not all patients have immediate access to the assessment of amyloid status (A-status) via gold standard methods. It may therefore be of interest to find suitable biomarkers to preselect patients benefitting most from additional workup of the A-status. In this study, we propose a machine learning-based gatekeeping system for the prediction of A-status on the grounds of pre-existing information on APOE-genotype 18F-FDG PET, age, and sex. METHODS: Three hundred and forty-two MCI patients were used to train different machine learning classifiers to predict A-status majority classes among APOE-ε4 non-carriers (APOE4-nc; majority class: amyloid negative (Aβ-)) and carriers (APOE4-c; majority class: amyloid positive (Aβ +)) from 18F-FDG-PET, age, and sex. Classifiers were tested on two different datasets. Finally, frequencies of progression to dementia were compared between gold standard and predicted A-status. RESULTS: Aβ- in APOE4-nc and Aβ + in APOE4-c were predicted with a precision of 87% and a recall of 79% and 51%, respectively. Predicted A-status and gold standard A-status were at least equally indicative of risk of progression to dementia. CONCLUSION: We developed an algorithm allowing approximation of A-status in MCI with good reliability using APOE-genotype, 18F-FDG PET, age, and sex information. The algorithm could enable better estimation of individual risk for developing AD based on existing biomarker information, and support efficient selection of patients who would benefit most from further etiological clarification. Further potential utility in clinical routine and clinical trials is discussed.
BACKGROUND: In patients with mild cognitive impairment (MCI), enhanced cerebral amyloid-β plaque burden is a high-risk factor to develop dementia with Alzheimer's disease (AD). Not all patients have immediate access to the assessment of amyloid status (A-status) via gold standard methods. It may therefore be of interest to find suitable biomarkers to preselect patients benefitting most from additional workup of the A-status. In this study, we propose a machine learning-based gatekeeping system for the prediction of A-status on the grounds of pre-existing information on APOE-genotype 18F-FDG PET, age, and sex. METHODS: Three hundred and forty-two MCI patients were used to train different machine learning classifiers to predict A-status majority classes among APOE-ε4 non-carriers (APOE4-nc; majority class: amyloid negative (Aβ-)) and carriers (APOE4-c; majority class: amyloid positive (Aβ +)) from 18F-FDG-PET, age, and sex. Classifiers were tested on two different datasets. Finally, frequencies of progression to dementia were compared between gold standard and predicted A-status. RESULTS: Aβ- in APOE4-nc and Aβ + in APOE4-c were predicted with a precision of 87% and a recall of 79% and 51%, respectively. Predicted A-status and gold standard A-status were at least equally indicative of risk of progression to dementia. CONCLUSION: We developed an algorithm allowing approximation of A-status in MCI with good reliability using APOE-genotype, 18F-FDG PET, age, and sex information. The algorithm could enable better estimation of individual risk for developing AD based on existing biomarker information, and support efficient selection of patients who would benefit most from further etiological clarification. Further potential utility in clinical routine and clinical trials is discussed.
Authors: Felix Carbonell; Alex P Zijdenbos; Donald G McLaren; Yasser Iturria-Medina; Barry J Bedell Journal: J Cereb Blood Flow Metab Date: 2016-06-14 Impact factor: 6.200
Authors: Ralph H B Benedict; Davorka Tomic; Bruce A Cree; Robert Fox; Gavin Giovannoni; Amit Bar-Or; Ralf Gold; Patrick Vermersch; Harald Pohlmann; Ian Wright; Göril Karlsson; Frank Dahlke; Christian Wolf; Ludwig Kappos Journal: Neurology Date: 2020-12-16 Impact factor: 9.910
Authors: Yen Ying Lim; Paul Maruff; Nicolas R Barthélemy; Alison Goate; Jason Hassenstab; Chihiro Sato; Anne M Fagan; Tammie L S Benzinger; Chengjie Xiong; Carlos Cruchaga; Johannes Levin; Martin R Farlow; Neill R Graff-Radford; Christoph Laske; Colin L Masters; Stephen Salloway; Peter R Schofield; John C Morris; Randall J Bateman; Eric McDade Journal: JAMA Neurol Date: 2022-03-01 Impact factor: 29.907
Authors: Timo Grimmer; Carolin Wutz; Alexander Drzezga; Stefan Förster; Hans Förstl; Marion Ortner; Robert Perneczky; Alexander Kurz Journal: Curr Alzheimer Res Date: 2013-01 Impact factor: 3.498
Authors: Manja Lehmann; Pia M Ghosh; Cindee Madison; Anna Karydas; Giovanni Coppola; James P O'Neil; Yadong Huang; Bruce L Miller; William J Jagust; Gil D Rabinovici Journal: J Neurol Neurosurg Psychiatry Date: 2013-08-21 Impact factor: 10.154
Authors: A Drzezga; T Grimmer; G Henriksen; M Mühlau; R Perneczky; I Miederer; C Praus; C Sorg; A Wohlschläger; M Riemenschneider; H J Wester; H Foerstl; M Schwaiger; A Kurz Journal: Neurology Date: 2009-04-01 Impact factor: 9.910
Authors: Kejal Kantarci; Timothy Lesnick; Tanis J Ferman; Scott A Przybelski; Bradley F Boeve; Glenn E Smith; Walter K Kremers; David S Knopman; Clifford R Jack; Ronald C Petersen Journal: Neurology Date: 2016-11-02 Impact factor: 9.910