Abstract Details
Activity Number:
|
554
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 6, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Mental Health Statistics Section
|
Abstract #313513
|
View Presentation
|
Title:
|
A Robust Diagnostic Test for PTSD Using Tensor Regression on Synchronous Neural Interactions
|
Author(s):
|
Ilana Belitskaya-Lévy*+ and Ying Lu and Lexin Li and Apostolos Georgopoulos and Brian Engdahl and Lisa James
|
Companies:
|
Palo Alto VA CSPCC and Palo Alto VA CSPCC/Stanford University and North Carolina State University and Minneapolis VA Health Care System and Minneapolis VA Health Care System and Minneapolis VA Health Care System
|
Keywords:
|
tensor regression ;
diagnostic algorithm ;
diagnostic test ;
PTSD ;
SNI ;
MEG
|
Abstract:
|
Despite concerted efforts to identify a diagnostic biomarker of posttraumatic stress disorder (PTSD), lack of validity and reliability has largely stymied progress. Recently, it has been demonstrated that synchronous neural interactions (SNI) distinguish veterans with PTSD from community controls with remarkable accuracy, providing evidence for a putative PTSD biomarker. We developed and applied a robust PTSD diagnostic test using tensor regression based on SNI in a sample of 197 veterans with PTSD and 235 veteran controls. The performance of our diagnostic test was measured by the area under the receiver operating characteristic curves, sensitivity and specificity in training and validation datasets. Intra-class correlation coefficient (ICC) was used to evaluate reproducibility. Application of a prediction model derived using tensor regression demonstrated remarkable classification accuracy and reproducibility. We conclude that neural functioning in individuals with PTSD is highly distinct from controls and can be used as a diagnostic test to determine patient disease status.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.