A5021330813- EEG and Brain-Computer Interfaces
- Epilepsy research and treatment
- Neurological disorders and treatments
- Neuroscience and Neural Engineering
- Advanced MRI Techniques and Applications
- Machine Learning in Healthcare
- Topic Modeling
- Advanced Neuroimaging Techniques and Applications
- Neural dynamics and brain function
- Functional Brain Connectivity Studies
- Bioinformatics and Genomic Networks
- Algal biology and biofuel production
- Cell Image Analysis Techniques
- Botulinum Toxin and Related Neurological Disorders
- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Medical Imaging Techniques and Applications
- Non-Invasive Vital Sign Monitoring
- Healthcare Technology and Patient Monitoring
- Blind Source Separation Techniques
- Tryptophan and brain disorders
- Advanced Memory and Neural Computing
- Advanced Drug Delivery Systems
- Inflammatory Bowel Disease
- Genetic Neurodegenerative Diseases
Massachusetts General Hospital
2022-2024
Harvard University
2024
University of Pennsylvania
2012-2022
The University of Melbourne
2017
California University of Pennsylvania
2017
Philadelphia University
2017
Princeton University
2012-2013
Children's Hospital of Philadelphia
2012
BackgroundSeizure prediction can increase independence and allow preventative treatment for patients with epilepsy. We present a proof-of-concept seizure system that is accurate, fully automated, patient-specific, tunable to an individual's needs.MethodsIntracranial electroencephalography (iEEG) data of ten obtained from advisory were analyzed as part pseudoprospective study. First, deep learning classifier was trained distinguish between preictal interictal signals. Second, performance...
Brain stimulation has emerged as an effective treatment for a wide range of neurological and psychiatric diseases. Parkinson's disease, epilepsy, essential tremor have FDA indications electrical brain using intracranially implanted electrodes. Interfacing implantable devices with local cloud computing resources the potential to improve efficacy, disease tracking, management. Epilepsy, in particular, is that might benefit from integration implants off-the-body tracking therapy. Recent...
There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing validated is limited access high-quality, expertly annotated data from prolonged recordings. To overcome this, we hosted a kaggle.com competition crowdsource the development using canines...
Abstract Objective Seizure frequency and seizure freedom are among the most important outcome measures for patients with epilepsy. In this study, we aimed to automatically extract clinical information from unstructured text in notes. If successful, could improve decision-making epilepsy allow rapid, large-scale retrospective research. Materials Methods We developed a finetuning pipeline pretrained neural models classify as being seizure-free containing their date of last annotated 1000 notes...
Abstract The gut microbiome plays a key role in human health and alterations of the normal flora are associated with variety distinct disease states. Yet, natural dependencies between microbes healthy diseased individuals remain far from understood. Here we use network-based approach to characterize microbial co-occurrence inflammatory bowel (IBD) (non-IBD control) individuals. We find that networks patients IBD differ both global structure local connectivity patterns. While “core” is...
Objective. Implanting subdural and penetrating electrodes in the brain causes acute trauma inflammation that affect intracranial electroencephalographic (iEEG) recordings. This behavior its potential impact on clinical decision-making algorithms for implanted devices have not been assessed detail. In this study we aim to characterize temporal spatial variability of continuous, prolonged human iEEG Approach. Intracranial electroencephalography from 15 patients with drug-refractory epilepsy,...
Objective For stroke patients with unknown time of onset, mismatch between diffusion‐weighted imaging (DWI) and fluid‐attenuated inversion recovery (FLAIR) magnetic resonance (MRI) can guide thrombolytic intervention. However, access to MRI for hyperacute is limited. Here, we sought evaluate whether a portable, low‐field (LF)‐MRI scanner identify DWI‐FLAIR in acute ischemic stroke. Methods Eligible diagnosis underwent LF‐MRI acquisition on 0.064‐T within 24 h last known well. Qualitative...
Closed-loop implantable neural stimulators are an exciting treatment option for patients with medically refractory epilepsy, a number of new devices in or nearing clinical trials. These must accurately detect variety seizure types order to reliably deliver therapeutic stimulation. While effective, broadly-applicable detection algorithms have recently been published, these methods too computationally intensive be directly deployed device. We demonstrate strategy that couples cloud computing...
Objective. Recently the FDA approved first responsive, closed-loop intracranial device to treat epilepsy. Because these devices must respond within seconds of seizure onset and not miss events, they are tuned have high sensitivity, leading frequent false positive stimulations decreased battery life. In this work, we propose a more robust detection model. Approach. We use Bayesian nonparametric Markov switching process parse EEG (iEEG) data into distinct dynamic event states. Each state is...
Current brain stimulation paradigms are largely empirical rather than theoretical. An opportunity exists to improve upon their modest effectiveness in closed-loop control strategies with the development of theoretically grounded, model-based designs.
The Unified Huntington's Disease Rating Scale (UHDRS) is the primary clinical assessment tool for rating motor function in patients with disease (HD). However, UHDRS and similar scales (e.g., UPDRS) are both subjective limited to in-office assessments that must be administered by a trained experienced rater. An objective, automated method of quantifying severity would facilitate superior patient care could used better track over time. We conducted present study evaluate feasibility using...
The purpose of this study is to demonstrate a method for virtually evaluating novel imaging devices using machine learning and open-access datasets, here applied new, low-field strength portable 64mT MRI device. Paired 3 T brain images were used develop validate transformation converting standard clinical quality images. Separately, aggregated from open-source databases spanning four neuropathologies: low-grade glioma (LGG, N = 76), high-grade (HGG, 259), stroke (N 28), multiple sclerosis...
New approaches are needed to interpret large amounts of physiologic data continuously recorded in the ICU. We developed and prospectively validated a versatile platform (IRIS) for real-time ICU monitoring, clinical decision making, caretaker notification.IRIS was implemented neurointensive care unit stream multimodal time series data, including EEG, intracranial pressure (ICP), brain tissue oxygenation (PbtO2), from monitors an analysis server. IRIS applied 364 patients undergoing continuous...
Continuous electroencephalogram monitoring is associated with lower mortality in critically ill patients; however, it underused due to the resource-intensive nature of manually interpreting prolonged streams continuous data. Here, we present a novel real-time, machine learning-based alerting and system for epilepsy seizures that dramatically reduces amount manual review.We developed custom data reduction algorithm using random forest deployed within an online cloud-based platform, which...
The optimal epilepsy management device requires: 1) automated seizure detection 2) accurate electronic diaries 3) forecasting 4) active brain probing to track state and 5) stimulation therapy adjustment that can respond changes in probability prevent seizures. In this paper, we describe an platform using Medtronic's investigational Activa RC+S Research System. provides chronic nervous system stimulation, sensing, embedded analytics. Continuous iEEG telemetry from the be received by a...
Background and Aims: Treatment options for acute ischemic stroke (AIS) are uniquely dependent on the time of onset. Intravenous thrombolysis must be administered within 4.5 hours symptoms commencing, yet a subset patients wake-up with onset is unknown. Mismatch between fluid-attenuated inversion recovery (FLAIR) diffusion-weighted imaging (DWI) MRI can used to qualify strokes thrombolysis. This has been shown lead improved functional outcomes in multicenter trials (WAKE-UP, MR-WITNESS)....
Neuroimaging is an important component of diagnosis and presurgical planning for localization-related epilepsy. The evaluation treatment medication-refractory epilepsy are changing as clinicians move toward less invasive more selective adaptive approaches. This article reviews concepts terms, including the International League Against Epilepsy 2017 revised classification seizures; presents common lesions approaches to finding them; provides updates in advanced structural functional imaging....
Understanding brain dynamics in epilepsy is critical for establishing rigorous control objectives that enable new therapeutic methods to mitigate seizure occurrence. In multichannel electrocorticography (ECoG) recordings acquired 21 subjects during a total of 94 seizures, we apply dynamical systems stability analysis assess the balance versus imbalance across different timescales and regions. Specifically, consider sliding time window multivariate autoregressive linear approximation data...
The optimal epilepsy management device requires: automated seizure detection, accurate electronic diaries, forecasting, active brain probing to track state, and stimulation therapy adjustment that can respond in a control law approach probability prevent seizures. In this session, we want describe demonstrate an platform using Medtronic's investigational Activa RC+S Research System implanted living canines with epilepsy. provides chronic nervous system sensing analytics embedded scientific...