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

Daniel Stamate, Min Kim, Petroula Proitsi, Sarah Westwood, Alison Baird, Alejo Nevado-Holgado, Abdul Hye, Isabelle Bos, Stephanie J B Vos, Rik Vandenberghe, Charlotte E Teunissen, Mara Ten Kate, Philip Scheltens, Silvy Gabel, Karen Meersmans, Olivier Blin, Jill Richardson, Ellen De Roeck, Sebastiaan Engelborghs, Kristel SleegersRégis Bordet, Lorena Ramit, Petronella Kettunen, Magda Tsolaki, Frans Verhey, Daniel Alcolea, Alberto Lléo, Gwendoline Peyratout, Mikel Tainta, Peter Johannsen, Yvonne Freund-Levi, Lutz Frölich, Valerija Dobricic, Giovanni B Frisoni, José L Molinuevo, Anders Wallin, Julius Popp, Pablo Martinez-Lage, Lars Bertram, Kaj Blennow, Henrik Zetterberg, Johannes Streffer, Pieter J Visser, Simon Lovestone, Cristina Legido-Quigley

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)933-938
Number of pages6
JournalAlzheimer's and Dementia: Translational Research and Clinical Interventions
Volume5
DOIs
Publication statusPublished - 2019

Cite this

Stamate, D., Kim, M., Proitsi, P., Westwood, S., Baird, A., Nevado-Holgado, A., Hye, A., Bos, I., Vos, S. J. B., Vandenberghe, R., Teunissen, C. E., Kate, M. T., Scheltens, P., Gabel, S., Meersmans, K., Blin, O., Richardson, J., De Roeck, E., Engelborghs, S., ... Legido-Quigley, C. (2019). 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. Alzheimer's and Dementia: Translational Research and Clinical Interventions, 5, 933-938. https://doi.org/10.1016/j.trci.2019.11.001