ABSTRACT
INTRODUCTION Computational brain network modeling using The Virtual Brain (TVB) simulation platform acts synergistically with machine learning and multi-modal neuroimaging to reveal mechanisms and improve diagnostics in Alzheimer’s disease.
METHODS We enhance large-scale whole-brain simulation in TVB with a cause-and-effect model linking local Amyloid β PET with altered excitability. We use PET and MRI data from 33 participants of Alzheimer’s Disease Neuroimaging Initiative (ADNI3) combined with frequency compositions of TVB-simulated local field potentials (LFP) for machine-learning 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 Alzheimer’s-typical spatial distribution.
DISCUSSION The cause-and-effect implementation of local hyperexcitation caused by Amyloid β can improve the machine-learning-driven classification of Alzheimer’s and demonstrates TVB’s ability to decode information in empirical data employing connectivity-based brain simulation.
RESEARCH IN CONTEXT
SYSTEMATIC REVIEW. Machine-learning has been proven to augment diagnostics of dementia in several ways. Imaging-based approaches enable early diagnostic predictions. However, individual projections of long-term outcome as well as differential diagnosis remain difficult, as the mechanisms behind the used classifying features often remain unclear. Mechanistic whole-brain models in synergy with powerful machine learning aim to close this gap.
INTERPRETATION. Our work demonstrates that multi-scale brain simulations considering Amyloid β distributions and cause-and-effect regulatory cascades reveal hidden electrophysiological processes that are not readily accessible through measurements in humans. We demonstrate that these simulation-inferred features hold the potential to improve diagnostic classification of Alzheimer’s disease.
FUTURE DIRECTIONS. The simulation-based classification model needs to be tested for clinical usability in a larger cohort with an independent test set, either with another imaging database or a prospective study to assess its capability for long-term disease trajectories.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
↵2 Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf
The manuscript was shortened and revised, and the introduction was rewritten to outline and clarify the main result. We added a permutation analysis to the results.
† ABBREVIATIONS
- AD
- Alzheimer’s Disease
- Aβ
- Amyloid β
- TVB
- The Virtual Brain
- EEG
- electroencephalography
- LFPs
- local field potentials
- PET
- positron emission tomography
- MCI
- mild cognitive impairment
- HC
- healthy controls
- ML
- machine learning
- ADNI
- Alzheimer’s Disease Neuroimaging Initiative
- MRI
- magnetic resonance imaging
- SC
- structural connectivity
- SVM
- support vector machines
- RF
- random forest
- SUVR
- standardized uptake value ratio
- FI
- feature importance