Published Online
on December 8, 2008

A more recent version of this article appeared on March 1, 2009

This Article Full Text (PDF) All Versions of this Article: 40/3_suppl_1/S67    most recent STROKEAHA.108.533273v1 Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Request Permissions Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Ramoni, R. B. Articles by Ramoni, M. F. Search for Related Content PubMed PubMed Citation Articles by Ramoni, R. B. Articles by Ramoni, M. F. Related Collections Other Stroke Treatment - Medical

Submitted on July 30, 2008
Accepted on July 30, 2008

Predictive Genomics of Cardioembolic Stroke

Rachel Badovinac Ramoni DMD, ScD; Blanca E. Himes PhD; Michele M. Sale PhD; Karen L. Furie MD, MPH; and Marco F. Ramoni PhD^*

From the Department of Developmental Biology (R.B.R.), Harvard School of Dental Medicine, Boston, Mass; the Children's Hospital Informatics Program (B.E.H., M.F.R.), Harvard–MIT Division of Health Sciences and Technology, Boston, Mass; the Department of Medicine (M.M.S.), University of Virginia, Charlottesville, Va; the Department of Neurology (K.L.F.), Massachusetts General Hospital, Harvard Medical School, Boston, Mass; and the Harvard–Partners Center for Genetics and Genomics (M.F.R.), Harvard Medical School, Boston, Mass.

^* To whom correspondence should be addressed. E-mail: marco_ramoni{at}harvard.edu.

Abstract—Cardioembolic stroke is a complex disease resulting from the interaction of numerous factors. Using data from Genes Affecting Stroke Risk and Outcome Study (GASROS), we show that a multivariate predictive model built using Bayesian networks is able to achieve a predictive accuracy of 86% on the fitted values as computed by the area under the receiver operating characteristic curve relative to that of the individual single nucleotide polymorphism with the highest prognostic performance (area under the receiver operating characteristic curve=60%).

Key words: Bayesian networks • genetics • ischemic stroke • prediction • risk factors