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 Sleegers; Régis 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

doi:10.1016/j.trci.2019.11.001

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^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-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 language	English
Pages (from-to)	933-938
Number of pages	6
Journal	Alzheimer's and Dementia: Translational Research and Clinical Interventions
Volume	5
Issue number	1
DOIs	https://doi.org/10.1016/j.trci.2019.11.001
Publication status	Published - 2019

Keywords

EMIF-AD
Alzheimer's disease
Metabolomics
Biomarkers
Machine-Learning

Access to Document

10.1016/j.trci.2019.11.001Licence: CC BY-NC-ND

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(1), 933-938. https://doi.org/10.1016/j.trci.2019.11.001

Stamate, Daniel ; Kim, Min ; Proitsi, Petroula et al. / 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. In: Alzheimer's and Dementia: Translational Research and Clinical Interventions. 2019 ; Vol. 5, No. 1. pp. 933-938.

@article{a6b62a91f5ec4b10987253cc47e7f6da,

title = "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",

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.",

keywords = "EMIF-AD, Alzheimer's disease, Metabolomics, Biomarkers, Machine-Learning",

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

note = "{\textcopyright} 2019 The Authors.",

year = "2019",

doi = "10.1016/j.trci.2019.11.001",

language = "English",

volume = "5",

pages = "933--938",

journal = "Alzheimer's and Dementia: Translational Research and Clinical Interventions",

publisher = "Elsevier Inc.",

number = "1",

}

Stamate, D, Kim, M, Proitsi, P, Westwood, S, Baird, A, Nevado-Holgado, A, Hye, A, Bos, I, Vos, SJB, Vandenberghe, R, Teunissen, CE, Kate, MT, Scheltens, P, Gabel, S, Meersmans, K, Blin, O, Richardson, J, De Roeck, E, Engelborghs, S, Sleegers, K, Bordet, R, Ramit, L, Kettunen, P, Tsolaki, M, Verhey, F, Alcolea, D, Lléo, A, Peyratout, G, Tainta, M, Johannsen, P, Freund-Levi, Y, Frölich, L, Dobricic, V, Frisoni, GB, Molinuevo, JL, Wallin, A, Popp, J, Martinez-Lage, P, Bertram, L, Blennow, K, Zetterberg, H, Streffer, J, Visser, PJ, Lovestone, 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, vol. 5, no. 1, pp. 933-938. https://doi.org/10.1016/j.trci.2019.11.001

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. / Stamate, Daniel; Kim, Min; Proitsi, Petroula et al.
In: Alzheimer's and Dementia: Translational Research and Clinical Interventions, Vol. 5, No. 1, 2019, p. 933-938.

Research output: Contribution to journal › Article › Academic › peer-review

TY - JOUR

T1 - A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood

T2 - 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

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.

KW - EMIF-AD

KW - Alzheimer's disease

KW - Metabolomics

KW - Biomarkers

KW - Machine-Learning

U2 - 10.1016/j.trci.2019.11.001

DO - 10.1016/j.trci.2019.11.001

M3 - Article

C2 - 31890857

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

IS - 1

ER -

Stamate D, Kim M, Proitsi P, Westwood S, Baird A, Nevado-Holgado A et al. 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. 2019;5(1):933-938. doi: 10.1016/j.trci.2019.11.001