A metabolite-based machine learning approach to diagnose Alzheimer’s-type dementia in blood: Results from the European Medical Information Framework for Alzheimer's Disease biomarker discovery cohort

Stamate, Daniel; Kim, Min; Proitsi, Petroula; Westwood, Sarah; Baird, Alison; Nevado-Holgado, Alejo; Hye, Abdul; Bos, Isabelle; Vos, Stephanie; Vandenberghe, Rik; Teunissen, Charlotte E; Kate, Mara Ten; Scheltens, Philip; Gabel, Silvy; Meersmans, Karen; Blin, Olivier; Richardson, Jill; Roeck, Ellen De; Engelborghs, Sebastiaan; Sleegeres, Kristel; Bordet, Régis; Rami, Lorena; Kettunen, Petronella; Tsolaki, Magd; Verhey, Frans; Alcolea, Daniel; Lléo, Alberto; Peyratout, Gwendoline; Tainta, Mikel; Johannsen, Peter; Freund-Levi, Yvonne; Frölich, Lutz; Dobricic, Valerija; Frisoni, Giovanni B; Molinuevo, José L; Wallin, Anders; Popp, Julius; Martinez-Lage, Pablo; Bertram, Lars; Blennow, Kaj; Zetterberg, Henrik; Streffer, Johannes; Visser, Pieter J; Lovestone, Simon and Legido-Quigley, Cristina. 2019. A metabolite-based machine learning approach to diagnose Alzheimer’s-type dementia in blood: Results from the European Medical Information Framework for Alzheimer's Disease biomarker discovery cohort. Alzheimer’s & Dementia: Translational Research & Clinical Interventions, 5, pp. 933-938. [Article]

[img]
Preview
Text
add.2019.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (562kB) | Preview
[img]
Preview
Text
1-s2.0-S2352873719300873-main.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (749kB) | Preview

Abstract or Description

INTRODUCTION: Machine learning (ML) may harbor the potential to capture the metabolic complexity in Alzheimer’s Disease (AD). Here we set out to test the performance of metabolites in blood to categorise AD when compared to CSF biomarkers.

METHODS: This study analysed 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.

Item Type:

Article

Identification Number (DOI):

https://doi.org/10.1016/j.trci.2019.11.001

Additional Information:

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).

Keywords:

Machine Learning, Predictive Modelling, Gradient Boosting Machines, Deep Learning, Alzheimer's, Dementia, Metabolites

Related URLs:

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
4 November 2019Accepted
18 December 2019Published Online

Item ID:

27637

Date Deposited:

21 Nov 2019 15:04

Last Modified:

15 Jan 2020 03:02

Peer Reviewed:

Yes, this version has been peer-reviewed.

URI:

http://research.gold.ac.uk/id/eprint/27637

View statistics for this item...

Edit Record Edit Record (login required)