Prediction of perioperative cerebral fragility from physiological sleep EEG using statistical learning
Background and Context
Post-operative delirium (POD) is a potential complication of anesthesia during surgery. It is often associated with adverse outcomes and is aggravated by ageing. In elderly patients, post-operative complications have been estimated to incur tens of million US dollars of costs each year in the United States by prolonging hospitalization and potentially affecting health prognosis. Recent studies suggest that POD can already be prevented by improving electrophysiological monitoring of anesthesia depth and individual dosage of anesthetic agents. Doing so probably minimizes the time patients spend in a coma-like state that manifests itself in isoelectric burst suppression, an electroencephalogram (EEG) pattern characterized by alternation between quiescence and high-amplitude bursts, and causally linked to POD. However, such an enterprise, currently, depends on the trained clinical electrophysiologist and guidance by commercially provided EEG indices of states of consciousness. One such metric is the bispectral index (BIS), which, like other related metrics, does not explicitly take into account baseline changes related to normative ageing and may therefore be biased when used naively.
While electrophysiological signatures of ageing (e.g. drop in Alpha and Gamma band power), states of consciousness (e.g. drop in Theta band long-range connectivity) and drug response (e.g. anteriorization of alpha band power in propofol anesthesia) have been separately investigated in the past years, their common denominators are not known. It is therefore difficult to detect individual risk, choose the optimal dosage, and automate anesthesia monitoring readily for any patient in any hospital.
The goal of this reseach project is to build statistical models that enable prediction of burst suppression and subsequent POD by exploiting diverse EEG-signatures of states of consciousness in the context of ageing. We approach this challenge by recasting it as a problem of learning brain-age from the point of view of electrophysiology of consciousness.
The PhD thesis will be conducted in collaboration between the INRIA-CEA Parietal team and the INSERM research
unit 942 – BioCANVAS (Biomarkers in Cardio-Neuro-VAScular diseases).
- PhD candidate: David Sabbagh
- PIs INRIA: Denis Engemann, PhD | Alexandre Gramfort, PhD, HDR
- PIs INSERM: Étienne Gayat, MD, PhD, HDR | Fabrice Vallée, MD
Sabbagh, D., Ablin, P., Varoquaux, G., Gramfort, G., Engemann, DA. (2020). Manifold-regression to predict from MEG/EEG brain signals without source modeling. Advances in Neural Information Processing Systems 32 (NeurIPS). 7321-7332. https://arxiv.org/abs/1906.02687v2
Sabbagh, D., Ablin, P., Varoquaux, G., Gramfort, A., Engemann, DA. (2020). Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states. NeuroImage..https://doi.org/10.1016/j.neuroimage.2020.116893