Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.
Catherine	
  Jayapandian
	
  
Case	
  Western	
  Reserve	
  University,	
  Ohio,	
  USA	
  
	
  
 
o  Background:	
  Electrophysiological	
  Data	
  
Management	
  
o  Challenges:	
  Big	
  Data,	
  Mul;center	
  studie...
o  What	
  is	
  Epilepsy?	
  
n  Most	
  common	
  neurological	
  disorder	
  affec;ng	
  60	
  
million	
  worldwide	
 ...
o  Mul;-­‐center	
  Clinical	
  Study	
  for	
  Preven;on	
  and	
  
Iden;fica;on	
  of	
  Risks	
  in	
  SUDEP	
  Pa;ents	...
o  Ontology-­‐driven	
  Web-­‐
based	
  Electrophysiological	
  
Epilepsy	
  Signal	
  Query,	
  
Visualiza;on	
  and	
  A...
o  PaBents	
  Cohorts	
  are	
  selected	
  using	
  the	
  MEDCIS	
  Query	
  
Builder	
  
o  PaBent	
  ID	
  is	
  linke...
o  SelecBon	
  of	
  PaBent	
  Study,	
  Montage,	
  Signal/
Channels	
  for	
  display	
  
o  Facilitate	
  creaBon	
  of...
o  SelecBon	
  of	
  Seizure	
  Events/AnnotaBons	
  
Mouse	
  zooming	
  to	
  ;me-­‐
range	
  of	
  interest	
  
Expor;n...
o  SelecBon	
  of	
  Filters	
  –	
  SensiBvity,	
  HF	
  Filter	
  	
  and	
  Time	
  Constant	
  
o  Electrophysiological	
  “Big”	
  Signal	
  Data	
  Storage	
  on	
  
HDFS	
  by	
  collec$ng	
  similar	
  signals	
  f...
o  PRISM	
  is	
  NIH	
  funded,	
  mul--­‐disciplinary	
  and	
  mul--­‐
center	
   (4	
   par;cipa;ng	
   centers)	
   –...
Nächste SlideShare
Wird geladen in …5
×

Electrophysiological Signal Analysis and Visualization using Cloudwave for Epilepsy Clinical Research

607 Aufrufe

Veröffentlicht am

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.

Veröffentlicht in: Technologie, Gesundheit & Medizin, Bildung
  • Als Erste(r) kommentieren

  • Gehören Sie zu den Ersten, denen das gefällt!

Electrophysiological Signal Analysis and Visualization using Cloudwave for Epilepsy Clinical Research

  1. 1. Catherine  Jayapandian   Case  Western  Reserve  University,  Ohio,  USA    
  2. 2.   o  Background:  Electrophysiological  Data   Management   o  Challenges:  Big  Data,  Mul;center  studies   o  Cloudwave  Framework:  Features,  Components   o  Current  Results   o  Future  Direc;ons  
  3. 3. 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  
  4. 4. 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  
  5. 5. 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”  
  6. 6. 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  
  7. 7. o  SelecBon  of  PaBent  Study,  Montage,  Signal/ Channels  for  display   o  Facilitate  creaBon  of  new  montages   (referenBal  and  bipolar)  
  8. 8. 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  
  9. 9. o  SelecBon  of  Filters  –  SensiBvity,  HF  Filter    and  Time  Constant  
  10. 10. 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)  
  11. 11. 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  (cpj3@case.edu)  

×