electrophysiological signal analysis and visualization using cloudwave for epilepsy clinical...
DESCRIPTION
Epilepsy is the most common serious neurological disorder affecting 50-60 million persons worldwide. Electrophysiologi-cal data recordings, such as electroencephalogram (EEG), are the gold standard for diagnosis and pre-surgical evaluation in epilepsy patients. The increasing trend towards multi-center clinical studies require signal visualization and analysis tools to support real time interaction with signal data in a collabora-tive environment, which are cannot be supported by traditional desktop-based standalone applications. As part of the Preven-tion and Risk Identification of SUDEP Mortality (PRISM) project, we have developed a Web-based electrophysiology data visualization and analysis platform called Cloudwave using highly scalable open source cloud computing infrastruc-ture. Cloudwave is integrated with the PRISM patient cohort identification tool called MEDCIS (Multi-modality Epilepsy Data Capture and Integration System). The Epilepsy and Sei-zure Ontology (EpSO) underpins both Cloudwave and MEDCIS to support query composition and result retrieval. Cloudwave is being used by clinicians and research staff at the University Hospital - Case Medical Center (UH-CMC) Epi-lepsy Monitoring Unit (EMU) and will be progressively de-ployed at four EMUs in the United States and the United Kingdom as part of the PRISM project.TRANSCRIPT
Catherine Jayapandian
Case Western Reserve University, Ohio, USA
o Background: Electrophysiological Data Management
o Challenges: Big Data, Mul;center studies o Cloudwave Framework: Features, Components o Current Results o Future Direc;ons
o What is Epilepsy? n Most common neurological disorder affec;ng 60
million worldwide
o How is Epilepsy detected? n Mul;-‐modal Electrophysiological evalua;ons like
EEG, EKG, BP, O2 and CO2, Sleep data, video n Electroencephalogram (EEG) is the gold standard
for diagnosis and pre-‐surgical evalua;on
o Mul;-‐center Clinical Study for Preven;on and Iden;fica;on of Risks in SUDEP Pa;ents
o Key Components
n MEDCIS Mul$modality Epilepsy Data Capture and Integra$on System
n OPIC Online Pa$ent Informa$on Capture
n EpiDEA Epilepsy Data Extrac$on and Annota$on
n Cloudwave Electrophysiological Signal “Big Data” on the Cloud
o Ontology-‐driven Web-‐based Electrophysiological Epilepsy Signal Query, Visualiza;on and Analysis Framework
o Provides High Performance Cloud CompuBng Infrastructure for handling Electrophysiological “Big Data”
o PaBents Cohorts are selected using the MEDCIS Query Builder
o PaBent ID is linked to Cloudwave Signal Viewer
All studies and the related seizure events for the pa;ent can be viewed using Cloudwave interface
o SelecBon of PaBent Study, Montage, Signal/Channels for display
o Facilitate creaBon of new montages (referenBal and bipolar)
o SelecBon of Seizure Events/AnnotaBons Mouse zooming to ;me-‐range of interest
Expor;ng as image and prin;ng
Visually navigate using scroll to select ;me-‐range
o SelecBon of Filters – SensiBvity, HF Filter and Time Constant
o Electrophysiological “Big” Signal Data Storage on HDFS by collec$ng similar signals for correla$on and quan$ta$ve signal analysis using MapReduce distributed processing n Cloudwave: Distributed Processing of “Big Data” from
Electrophysiological Recordings for Epilepsy Clinical Research Using Hadoop, AMIA 2013 (accepted)
o Computa;on of complex Signal Processing algorithms – Cardiac Arrhythmia, Respiratory Arrhythmia and related measurements for real-‐;me rendering on Cloudwave web interface (work in progress)
o PRISM is NIH funded, mul--‐disciplinary and mul--‐center (4 par;cipa;ng centers) – recrui;ng 1200 pa;ents
o Cloudwave establishes the capability for comprehensive comparaBve studies of SUDEP and near-‐SUDEP cases vs. cohort survivors
o Cloudwave is a key component of PRISM project– facilitate the management of Electrophysiological “Big” Data and Real Time Web Rendering of Mul-modal signals
o For more details, please visit: hap://prism.case.edu
o Contact: Catherine Jayapandian ([email protected])