Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression

Konrad F. Waschkies; Joram Soch; Margarita Darna; Anni Richter; Slawek Altenstein; Aline Beyle; Frederic Brosseron; Friederike Buchholz; Michaela Butryn; Laura Dobisch; Michael Ewers; Klaus Fliessbach; Tatjana Gabelin; Wenzel Glanz; Doreen Goerss; Daria Gref; Daniel Janowitz; Ingo Kilimann; Andrea Lohse; Matthias H. Munk; Boris Stephan Rauchmann; Ayda Rostamzadeh; Nina Roy; Eike Jakob Spruth; Peter Dechent; Michael T. Heneka; Stefan Hetzer; Alfredo Ramirez; Klaus Scheffler; Katharina Buerger; Christoph Laske; Robert Perneczky; Oliver Peters; Josef Priller; Anja Schneider; Annika Spottke; Stefan Teipel; Emrah Düzel; Frank Jessen; Jens Wiltfang; Björn H. Schott; Jasmin M. Kizilirmak

doi:10.1002/gps.6007

Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression

Konrad F. Waschkies
, Joram Soch
, Margarita Darna
, Anni Richter
, Slawek Altenstein
, Aline Beyle
, Frederic Brosseron
, Friederike Buchholz
, Michaela Butryn
, Laura Dobisch
, Michael Ewers
, Klaus Fliessbach
, Tatjana Gabelin
, Wenzel Glanz
, Doreen Goerss
, Daria Gref
, Daniel Janowitz
, Ingo Kilimann
, Andrea Lohse
, Matthias H. Munk

Boris Stephan Rauchmann, Ayda Rostamzadeh, Nina Roy, Eike Jakob Spruth, Peter Dechent, Michael T. Heneka, Stefan Hetzer, Alfredo Ramirez, Klaus Scheffler, Katharina Buerger, Christoph Laske, Robert Perneczky, Oliver Peters, Josef Priller, Anja Schneider, Annika Spottke, Stefan Teipel, Emrah Düzel, Frank Jessen, Jens Wiltfang, Björn H. Schott, Jasmin M. Kizilirmak

Department of Psychiatry and Psychotherapy

German Center for Neurodegenerative Diseases (DZNE)
University Medical Center
Bernstein Center for Computational Neuroscience Berlin
Leibniz Institute for Neurobiology
German Center for Mental Health (DZPG)
Center for Intervention and Research on Adaptive and Maladaptive Brain Circuits Underlying Mental Health (C-I-R-C)
Charité – Universitätsmedizin Berlin
University of Bonn
Otto-von-Guericke University
Ludwig-Maximilians-Universität München
University of Bonn and University Hospital Bonn
Rostock University Medical Center
University Clinic Tuebingen
University of Sheffield
University of Cologne
Georg August Universität Göttingen
University of Cologne
University Hospital of Cologne
the University of Texas Health Science Center at San Antonio
University of Tübingen
Munich Cluster for Systems Neurology (SyNergy)
Imperial College London
University of Edinburgh
University of Aveiro
Universität Hildesheim

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

9 Scopus citations

Abstract

Background: Alzheimer's disease (AD) is often preceded by stages of cognitive impairment, namely subjective cognitive decline (SCD) and mild cognitive impairment (MCI). While cerebrospinal fluid (CSF) biomarkers are established predictors of AD, other non-invasive candidate predictors include personality traits, anxiety, and depression, among others. These predictors offer non-invasive assessment and exhibit changes during AD development and preclinical stages. Methods: In a cross-sectional design, we comparatively evaluated the predictive value of personality traits (Big Five), geriatric anxiety and depression scores, resting-state functional magnetic resonance imaging activity of the default mode network, apoliprotein E (ApoE) genotype, and CSF biomarkers (tTau, pTau181, Aβ42/40 ratio) in a multi-class support vector machine classification. Participants included 189 healthy controls (HC), 338 individuals with SCD, 132 with amnestic MCI, and 74 with mild AD from the multicenter DZNE-Longitudinal Cognitive Impairment and Dementia Study (DELCODE). Results: Mean predictive accuracy across all participant groups was highest when utilizing a combination of personality, depression, and anxiety scores. HC were best predicted by a feature set comprised of depression and anxiety scores and participants with AD were best predicted by a feature set containing CSF biomarkers. Classification of participants with SCD or aMCI was near chance level for all assessed feature sets. Conclusion: Our results demonstrate predictive value of personality trait and state scores for AD. Importantly, CSF biomarkers, personality, depression, anxiety, and ApoE genotype show complementary value for classification of AD and its at-risk stages.

Original language	English
Article number	e6007
Journal	International Journal of Geriatric Psychiatry
Volume	38
Issue number	10
DOIs	https://doi.org/10.1002/gps.6007
State	Published - Oct 2023

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Alzheimer's disease
amnestic mild cognitive impairment
biomarker
cerebrospinal fluid
fMRI
machine learning
personality
resting-state
subjective cognitive decline
support vector machine

Access to Document

10.1002/gps.6007

Cite this

Waschkies, K. F., Soch, J., Darna, M., Richter, A., Altenstein, S., Beyle, A., Brosseron, F., Buchholz, F., Butryn, M., Dobisch, L., Ewers, M., Fliessbach, K., Gabelin, T., Glanz, W., Goerss, D., Gref, D., Janowitz, D., Kilimann, I., Lohse, A., ... Kizilirmak, J. M. (2023). Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression. International Journal of Geriatric Psychiatry, 38(10), Article e6007. https://doi.org/10.1002/gps.6007

@article{91390aed48dd4799bf0d974924fc62b3,

title = "Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression",

abstract = "Background: Alzheimer's disease (AD) is often preceded by stages of cognitive impairment, namely subjective cognitive decline (SCD) and mild cognitive impairment (MCI). While cerebrospinal fluid (CSF) biomarkers are established predictors of AD, other non-invasive candidate predictors include personality traits, anxiety, and depression, among others. These predictors offer non-invasive assessment and exhibit changes during AD development and preclinical stages. Methods: In a cross-sectional design, we comparatively evaluated the predictive value of personality traits (Big Five), geriatric anxiety and depression scores, resting-state functional magnetic resonance imaging activity of the default mode network, apoliprotein E (ApoE) genotype, and CSF biomarkers (tTau, pTau181, Aβ42/40 ratio) in a multi-class support vector machine classification. Participants included 189 healthy controls (HC), 338 individuals with SCD, 132 with amnestic MCI, and 74 with mild AD from the multicenter DZNE-Longitudinal Cognitive Impairment and Dementia Study (DELCODE). Results: Mean predictive accuracy across all participant groups was highest when utilizing a combination of personality, depression, and anxiety scores. HC were best predicted by a feature set comprised of depression and anxiety scores and participants with AD were best predicted by a feature set containing CSF biomarkers. Classification of participants with SCD or aMCI was near chance level for all assessed feature sets. Conclusion: Our results demonstrate predictive value of personality trait and state scores for AD. Importantly, CSF biomarkers, personality, depression, anxiety, and ApoE genotype show complementary value for classification of AD and its at-risk stages.",

keywords = "Alzheimer's disease, amnestic mild cognitive impairment, biomarker, cerebrospinal fluid, fMRI, machine learning, personality, resting-state, subjective cognitive decline, support vector machine",

author = "Waschkies, \{Konrad F.\} and Joram Soch and Margarita Darna and Anni Richter and Slawek Altenstein and Aline Beyle and Frederic Brosseron and Friederike Buchholz and Michaela Butryn and Laura Dobisch and Michael Ewers and Klaus Fliessbach and Tatjana Gabelin and Wenzel Glanz and Doreen Goerss and Daria Gref and Daniel Janowitz and Ingo Kilimann and Andrea Lohse and Munk, \{Matthias H.\} and Rauchmann, \{Boris Stephan\} and Ayda Rostamzadeh and Nina Roy and Spruth, \{Eike Jakob\} and Peter Dechent and Heneka, \{Michael T.\} and Stefan Hetzer and Alfredo Ramirez and Klaus Scheffler and Katharina Buerger and Christoph Laske and Robert Perneczky and Oliver Peters and Josef Priller and Anja Schneider and Annika Spottke and Stefan Teipel and Emrah D{\"u}zel and Frank Jessen and Jens Wiltfang and Schott, \{Bj{\"o}rn H.\} and Kizilirmak, \{Jasmin M.\}",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors. International Journal of Geriatric Psychiatry published by John Wiley \& Sons Ltd.",

year = "2023",

month = oct,

doi = "10.1002/gps.6007",

language = "English",

volume = "38",

journal = "International Journal of Geriatric Psychiatry",

issn = "0885-6230",

publisher = "John Wiley and Sons Ltd",

number = "10",

}

Waschkies, KF, Soch, J, Darna, M, Richter, A, Altenstein, S, Beyle, A, Brosseron, F, Buchholz, F, Butryn, M, Dobisch, L, Ewers, M, Fliessbach, K, Gabelin, T, Glanz, W, Goerss, D, Gref, D, Janowitz, D, Kilimann, I, Lohse, A, Munk, MH, Rauchmann, BS, Rostamzadeh, A, Roy, N, Spruth, EJ, Dechent, P, Heneka, MT, Hetzer, S, Ramirez, A, Scheffler, K, Buerger, K, Laske, C, Perneczky, R, Peters, O, Priller, J, Schneider, A, Spottke, A, Teipel, S, Düzel, E, Jessen, F, Wiltfang, J, Schott, BH & Kizilirmak, JM 2023, 'Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression', International Journal of Geriatric Psychiatry, vol. 38, no. 10, e6007. https://doi.org/10.1002/gps.6007

TY - JOUR

T1 - Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression

AU - Waschkies, Konrad F.

AU - Soch, Joram

AU - Darna, Margarita

AU - Richter, Anni

AU - Altenstein, Slawek

AU - Beyle, Aline

AU - Brosseron, Frederic

AU - Buchholz, Friederike

AU - Butryn, Michaela

AU - Dobisch, Laura

AU - Ewers, Michael

AU - Fliessbach, Klaus

AU - Gabelin, Tatjana

AU - Glanz, Wenzel

AU - Goerss, Doreen

AU - Gref, Daria

AU - Janowitz, Daniel

AU - Kilimann, Ingo

AU - Lohse, Andrea

AU - Munk, Matthias H.

AU - Rauchmann, Boris Stephan

AU - Rostamzadeh, Ayda

AU - Roy, Nina

AU - Spruth, Eike Jakob

AU - Dechent, Peter

AU - Heneka, Michael T.

AU - Hetzer, Stefan

AU - Ramirez, Alfredo

AU - Scheffler, Klaus

AU - Buerger, Katharina

AU - Laske, Christoph

AU - Perneczky, Robert

AU - Peters, Oliver

AU - Priller, Josef

AU - Schneider, Anja

AU - Spottke, Annika

AU - Teipel, Stefan

AU - Düzel, Emrah

AU - Jessen, Frank

AU - Wiltfang, Jens

AU - Schott, Björn H.

AU - Kizilirmak, Jasmin M.

PY - 2023/10

Y1 - 2023/10

N2 - Background: Alzheimer's disease (AD) is often preceded by stages of cognitive impairment, namely subjective cognitive decline (SCD) and mild cognitive impairment (MCI). While cerebrospinal fluid (CSF) biomarkers are established predictors of AD, other non-invasive candidate predictors include personality traits, anxiety, and depression, among others. These predictors offer non-invasive assessment and exhibit changes during AD development and preclinical stages. Methods: In a cross-sectional design, we comparatively evaluated the predictive value of personality traits (Big Five), geriatric anxiety and depression scores, resting-state functional magnetic resonance imaging activity of the default mode network, apoliprotein E (ApoE) genotype, and CSF biomarkers (tTau, pTau181, Aβ42/40 ratio) in a multi-class support vector machine classification. Participants included 189 healthy controls (HC), 338 individuals with SCD, 132 with amnestic MCI, and 74 with mild AD from the multicenter DZNE-Longitudinal Cognitive Impairment and Dementia Study (DELCODE). Results: Mean predictive accuracy across all participant groups was highest when utilizing a combination of personality, depression, and anxiety scores. HC were best predicted by a feature set comprised of depression and anxiety scores and participants with AD were best predicted by a feature set containing CSF biomarkers. Classification of participants with SCD or aMCI was near chance level for all assessed feature sets. Conclusion: Our results demonstrate predictive value of personality trait and state scores for AD. Importantly, CSF biomarkers, personality, depression, anxiety, and ApoE genotype show complementary value for classification of AD and its at-risk stages.

AB - Background: Alzheimer's disease (AD) is often preceded by stages of cognitive impairment, namely subjective cognitive decline (SCD) and mild cognitive impairment (MCI). While cerebrospinal fluid (CSF) biomarkers are established predictors of AD, other non-invasive candidate predictors include personality traits, anxiety, and depression, among others. These predictors offer non-invasive assessment and exhibit changes during AD development and preclinical stages. Methods: In a cross-sectional design, we comparatively evaluated the predictive value of personality traits (Big Five), geriatric anxiety and depression scores, resting-state functional magnetic resonance imaging activity of the default mode network, apoliprotein E (ApoE) genotype, and CSF biomarkers (tTau, pTau181, Aβ42/40 ratio) in a multi-class support vector machine classification. Participants included 189 healthy controls (HC), 338 individuals with SCD, 132 with amnestic MCI, and 74 with mild AD from the multicenter DZNE-Longitudinal Cognitive Impairment and Dementia Study (DELCODE). Results: Mean predictive accuracy across all participant groups was highest when utilizing a combination of personality, depression, and anxiety scores. HC were best predicted by a feature set comprised of depression and anxiety scores and participants with AD were best predicted by a feature set containing CSF biomarkers. Classification of participants with SCD or aMCI was near chance level for all assessed feature sets. Conclusion: Our results demonstrate predictive value of personality trait and state scores for AD. Importantly, CSF biomarkers, personality, depression, anxiety, and ApoE genotype show complementary value for classification of AD and its at-risk stages.

KW - Alzheimer's disease

KW - amnestic mild cognitive impairment

KW - biomarker

KW - cerebrospinal fluid

KW - fMRI

KW - machine learning

KW - personality

KW - resting-state

KW - subjective cognitive decline

KW - support vector machine

UR - https://www.scopus.com/pages/publications/85173749183

U2 - 10.1002/gps.6007

DO - 10.1002/gps.6007

M3 - Article

C2 - 37800601

AN - SCOPUS:85173749183

SN - 0885-6230

VL - 38

JO - International Journal of Geriatric Psychiatry

JF - International Journal of Geriatric Psychiatry

IS - 10

M1 - e6007

ER -

Machine learning-based classification of Alzheimer's disease and its at-risk states using personality traits, anxiety, and depression

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this