Brain simulation augments machine-learning-based classification of dementia
Standard
Brain simulation augments machine-learning-based classification of dementia. / Triebkorn, Paul; Stefanovski, Leon; Dhindsa, Kiret; Diaz-Cortes, Margarita-Arimatea; Bey, Patrik; Bülau, Konstantin; Pai, Roopa; Spiegler, Andreas; Solodkin, Ana; Jirsa, Viktor; McIntosh, Anthony Randal; Ritter, Petra; Alzheimer’s Disease Neuroimaging Initiative.
in: ALZH DEMENT-TRCI, Jahrgang 8, Nr. 1, e12303, 2022.Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Brain simulation augments machine-learning-based classification of dementia
AU - Triebkorn, Paul
AU - Stefanovski, Leon
AU - Dhindsa, Kiret
AU - Diaz-Cortes, Margarita-Arimatea
AU - Bey, Patrik
AU - Bülau, Konstantin
AU - Pai, Roopa
AU - Spiegler, Andreas
AU - Solodkin, Ana
AU - Jirsa, Viktor
AU - McIntosh, Anthony Randal
AU - Ritter, Petra
AU - Alzheimer’s Disease Neuroimaging Initiative
N1 - © 2022 The Authors. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring published by Wiley Periodicals, LLC on behalf of Alzheimer's Association.
PY - 2022
Y1 - 2022
N2 - INTRODUCTION: Computational brain network modeling using The Virtual Brain (TVB) simulation platform acts synergistically with machine learning (ML) and multi-modal neuroimaging to reveal mechanisms and improve diagnostics in Alzheimer's disease (AD).METHODS: We enhance large-scale whole-brain simulation in TVB with a cause-and-effect model linking local amyloid beta (Aβ) positron emission tomography (PET) with altered excitability. We use PET and magnetic resonance imaging (MRI) data from 33 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI3) combined with frequency compositions of TVB-simulated local field potentials (LFP) for ML classification.RESULTS: The combination of empirical neuroimaging features and simulated LFPs significantly outperformed the classification accuracy of empirical data alone by about 10% (weighted F1-score empirical 64.34% vs. combined 74.28%). Informative features showed high biological plausibility regarding the AD-typical spatial distribution.DISCUSSION: The cause-and-effect implementation of local hyperexcitation caused by Aβ can improve the ML-driven classification of AD and demonstrates TVB's ability to decode information in empirical data using connectivity-based brain simulation.
AB - INTRODUCTION: Computational brain network modeling using The Virtual Brain (TVB) simulation platform acts synergistically with machine learning (ML) and multi-modal neuroimaging to reveal mechanisms and improve diagnostics in Alzheimer's disease (AD).METHODS: We enhance large-scale whole-brain simulation in TVB with a cause-and-effect model linking local amyloid beta (Aβ) positron emission tomography (PET) with altered excitability. We use PET and magnetic resonance imaging (MRI) data from 33 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI3) combined with frequency compositions of TVB-simulated local field potentials (LFP) for ML classification.RESULTS: The combination of empirical neuroimaging features and simulated LFPs significantly outperformed the classification accuracy of empirical data alone by about 10% (weighted F1-score empirical 64.34% vs. combined 74.28%). Informative features showed high biological plausibility regarding the AD-typical spatial distribution.DISCUSSION: The cause-and-effect implementation of local hyperexcitation caused by Aβ can improve the ML-driven classification of AD and demonstrates TVB's ability to decode information in empirical data using connectivity-based brain simulation.
U2 - 10.1002/trc2.12303
DO - 10.1002/trc2.12303
M3 - SCORING: Journal article
C2 - 35601598
VL - 8
JO - ALZH DEMENT-TRCI
JF - ALZH DEMENT-TRCI
SN - 2352-8737
IS - 1
M1 - e12303
ER -
