©2017-2020 Aarti Sathyanarayana

Research

NEUROPHYSICS

The current clinical process for evaluating neurological or neurodevelopment disorders from an electroencephalography (EEG) recording, relies on a clinician’s manual inspection. The electrodynamic signal of the brain is exceptionally complex, and EEG recordings can be minutes, hours, even days long. In contrast, pathologic activity may occur in just a fraction of a second.

 

Quantifying epileptogenicity, the tendency of the brain to have a seizure, is a particularly interesting starting point for EEG analysis, as it has a physical manifestation unlike many other neurological conditions. Seizures occur upon the spontaneous synchronization of neurons in the brain. Thus the electrodynamic state of a highly epileptogenetic brain will differ from the state of “normative” brain which has a low chance of neuronal synchrony. Deciphering these electrodynamic states into actionable digital biomarkers of disease requires creative and novel methodologies.

 

Our approach considers the state of the brain as a trajectory in a nonlinear dynamical system. 

The choice and dosage of antiseizure medication is currently guided by clinical markers including seizure frequency, semiology, etiology, and other diagnostic evaluations. However, finding the right combination can often resort to trial and error.  A neuro-physiological biomarker for the effect of medication on epileptic seizure activity would be useful for clinical decision making. As an early step in this direction, we evaluate changes in brain dynamics of patients in an on-off paradigm. 

Deep learning models have achieved state-of-the-art results in a wide variety of tasks in computer vision, natural language processing and speech recognition. The fact that deep learning models automatically learn abstract feature representations from raw features, while also optimizing on the target prediction tasks, makes them an attractive solution for analyzing wearable device data. 

FOCAL EPILEPSY

Deep learning models have achieved state-of-the-art results in a wide variety of tasks in computer vision, natural language processing and speech recognition. The fact that deep learning models automatically learn abstract feature representations from raw features, while also optimizing on the target prediction tasks, makes them an attractive solution for analyzing wearable device data. 

A data-driven activity recommendation system can take wearable device output, and provide personalized coaching to improve an individual's quality of life. A unique characteristic of activity, is its dynamic trajectory. An individual's behaviour is continuously changing. By evaluating an individuals daily activities using human activity recognition, we can identify behavioural recipes that lead to good or poor quality sleep. These recipes are "archetype behaviours for good sleep", which will guide the recommendations given to users throughout the day.

MEDICATION ON-OFF

Currently there is a large variation in the anti-seizure drug choice and dosage, across clinicians as well as institutions. While those decisions are guided by clinical factors, it can often resort to months of trial and error. Comparing the brain electrodynamics of a patient with epilepsy when on versus off anti-seizure medication, can provide insights regarding medication efficacy and also presents a paradigm of different inferred epileptogenicity levels. Computing nonlinear measures, such as sample entropy, determinism and the Lyapunov exponents, on a group of patients with epilepsy, we were able to distinguish between the different brain states (high versus low medication) using only the comparison of two thirty-second EEGs. We were also able to retrospectively localize the seizure onset region by measuring its relative reaction to medication compared with the rest of the brain. 

PATIENT COHORT

Pre-surgical epilepsy patients admitted to the long term monitoring unit at Boston Children’s Hospital are weaned off of medication for the clinical purpose of inducing an observed seizure to identify the epileptic region of the brain. The patients were admitted to the hospital for 3-5 days of continuous observation.

EEG EXTRACTION

A patient’s timeline is reconstructed from the details of medication administration, the EEG excerpts saved in their medical record, and the recorded seizures during their hospital stay. Two 30-second EEG excerpts are selected as the drug-high and drug-low periods. The drug-high phase is defined as the first 30 second interval of recorded EEG that does not contain seizures. The incoming patients would be on their at-home medication load at this time, as prescribed by their neurologist to prevent seizures. The drug off phase is defined by the largest gap in medication administration. Extracting a 30 second interval from the end of this gap is the lowest amount of medication the patient is on during their stay. Both excerpts are selected such that they do not include seizures, which would effect the electrodynamic state of the rain 

SIGNAL PROCESSING

RESULTS

The results show a difference between the dynamics of the irritative zone of the brain for ASM-on periods versus off. The below figures illustrate the change in sample entropy for the 4 paradigms: ASM- off and non-irritative, ASM-off and irritative, ASM-on and non-irritative, ASM-on and irritative. The change in dynamics of the irritative region from off to on ASM, was at least 95% greater than the change in corresponding dynamics on the non-irritative region, for sample entropy, laminarity,

determinism, and the Lyapunov exponents. Also, for the irritative region, the dynamical state of ASM-on periods converges 34% closer to the state of the non-irritative region, as compared to the state when off ASMs.