TY - JOUR
T1 - A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: Results from the European Medical Information Framework for Alzheimer disease biomarker discovery cohort
AU - Stamate, Daniel
AU - Kim, Min
AU - Proitsi, Petroula
AU - Westwood, Sarah
AU - Baird, Alison
AU - Nevado-Holgado, Alejo
AU - Hye, Abdul
AU - Bos, Isabelle
AU - Vos, Stephanie J.B.
AU - Vandenberghe, Rik
AU - Teunissen, Charlotte E.
AU - Kate, Mara Ten
AU - Scheltens, Philip
AU - Gabel, Silvy
AU - Meersmans, Karen
AU - Blin, Olivier
AU - Richardson, Jill
AU - De Roeck, Ellen
AU - Engelborghs, Sebastiaan
AU - Sleegers, Kristel
AU - Bordet, Régis
AU - Ramit, Lorena
AU - Kettunen, Petronella
AU - Tsolaki, Magda
AU - Verhey, Frans
AU - Alcolea, Daniel
AU - Lléo, Alberto
AU - Peyratout, Gwendoline
AU - Tainta, Mikel
AU - Johannsen, Peter
AU - Freund-Levi, Yvonne
AU - Frölich, Lutz
AU - Dobricic, Valerija
AU - Frisoni, Giovanni B.
AU - Molinuevo, José L.
AU - Wallin, Anders
AU - Popp, Julius
AU - Martinez-Lage, Pablo
AU - Bertram, Lars
AU - Blennow, Kaj
AU - Zetterberg, Henrik
AU - Streffer, Johannes
AU - Visser, Pieter J.
AU - Lovestone, Simon
AU - Legido-Quigley, Cristina
N1 - Funding Information:
The authors thank the individuals and families who took part in this research. The authors would also like to thank all people involved in data and sample collection and/or logistics across the different centers, and in particular Marije Benedictus, Wiesje van de Flier, Charlotte Teunissen, Ellen De Roeck, Naomi De Roeck, Ellis Niemantsverdriet, Charisse Somers, Babette Reijs, Andrea Izagirre Otaegi, Mirian, Ecay Torres, Sindre Rolstad, Eva Bringman, Domile Tautvydaite, Barbara Moullet, Charlotte Evenepoel, Isabelle Cleynen, Bea Bosch, Daniel Alcolea Rodriguez, Moira Marizzoni, Alberto Redolfi and Paolo Bosco. Funding: The present study was conducted as part of the EMIF-AD project, which has received support from the Innovative Medicines Initiative Joint Undertaking under EMIF grant agreement no. 115372, resources of which are composed of financial contribution from the European Union's Seventh Framework Program (FP7/2007–2013) and EFPIA companies' in-kind contribution. The DESCRIPA study was funded by the European Commission within the fifth framework program (QLRT-2001-2455). The EDAR study was funded by the European Commission within the fifth framework program (contract no. 37670). The San Sebastian GAP study is partially funded by the Department of Health of the Basque Government (allocation 17.0.1.08.12.0000.2.454.01. 41142.001.H). Kristel Sleegers is supported by the Research Fund of the University of Antwerp . Daniel Stamate is supported by the Alzheimer's Research UK ( ARUK-PRRF2017-012 ).
Publisher Copyright:
© 2019 The Authors
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2019
Y1 - 2019
N2 - Introduction: Machine learning (ML) may harbor the potential to capture the metabolic complexity in Alzheimer Disease (AD). Here we set out to test the performance of metabolites in blood to categorize AD when compared to CSF biomarkers. Methods: This study analyzed samples from 242 cognitively normal (CN) people and 115 with AD-type dementia utilizing plasma metabolites (n = 883). Deep Learning (DL), Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were used to differentiate AD from CN. These models were internally validated using Nested Cross Validation (NCV). Results: On the test data, DL produced the AUC of 0.85 (0.80–0.89), XGBoost produced 0.88 (0.86–0.89) and RF produced 0.85 (0.83–0.87). By comparison, CSF measures of amyloid, p-tau and t-tau (together with age and gender) produced with XGBoost the AUC values of 0.78, 0.83 and 0.87, respectively. Discussion: This study showed that plasma metabolites have the potential to match the AUC of well-established AD CSF biomarkers in a relatively small cohort. Further studies in independent cohorts are needed to validate whether this specific panel of blood metabolites can separate AD from controls, and how specific it is for AD as compared with other neurodegenerative disorders.
AB - Introduction: Machine learning (ML) may harbor the potential to capture the metabolic complexity in Alzheimer Disease (AD). Here we set out to test the performance of metabolites in blood to categorize AD when compared to CSF biomarkers. Methods: This study analyzed samples from 242 cognitively normal (CN) people and 115 with AD-type dementia utilizing plasma metabolites (n = 883). Deep Learning (DL), Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were used to differentiate AD from CN. These models were internally validated using Nested Cross Validation (NCV). Results: On the test data, DL produced the AUC of 0.85 (0.80–0.89), XGBoost produced 0.88 (0.86–0.89) and RF produced 0.85 (0.83–0.87). By comparison, CSF measures of amyloid, p-tau and t-tau (together with age and gender) produced with XGBoost the AUC values of 0.78, 0.83 and 0.87, respectively. Discussion: This study showed that plasma metabolites have the potential to match the AUC of well-established AD CSF biomarkers in a relatively small cohort. Further studies in independent cohorts are needed to validate whether this specific panel of blood metabolites can separate AD from controls, and how specific it is for AD as compared with other neurodegenerative disorders.
UR - http://www.scopus.com/inward/record.url?scp=85076456435&partnerID=8YFLogxK
U2 - 10.1016/j.trci.2019.11.001
DO - 10.1016/j.trci.2019.11.001
M3 - Journal articles
AN - SCOPUS:85076456435
SN - 2352-8737
VL - 5
SP - 933
EP - 938
JO - Alzheimer's and Dementia: Translational Research and Clinical Interventions
JF - Alzheimer's and Dementia: Translational Research and Clinical Interventions
ER -