Software identifies cause of ischemic stroke

Identifying the cause of an ischemic stroke is crucial in preventing a second stroke, but physicians lack the tools to make such a determination. Researchers from Massachusetts General Hospital (MGH) and the MGH Stroke Service have developed software capable of pinpointing such causes.

Published in The Journal of the American Medical Association Neurology, the study tests the Causative Classification of Stroke (CCS) software's ability to review more than 150 possible causes of ischemic stroke. Many patients show symptoms suggesting more than one cause, leading to physicians disagreeing in identifying cause(s).

"This was a much-needed study because, although stroke classifications systems are often used in research and clinical practice, these systems are not always able to produce subtypes with discrete pathophysiological, diagnostic and prognostic characteristics," said Hakan Ay, MD, a vascular neurologist, Martinos Center investigator and senior author. "We found that the CCS-based classifications provided better correlations between clinical and imaging stroke features and were better able to discriminate among stroke outcomes than were two conventional, non-automated classification methods."

The CCS software is able to differentiate between causes by using multiple factors including weeding through multiple causes with clinical and imaging features, considering the number of diagnostic tests and ensuring data is entered consistently.

The study involved an analysis of 1,816 ischemic patient, previously enrolled in two previous MGH studies. CCS was able to identify the cause of ischemic strokes in 20 to 40 percent of patients, which were previously unable to determine, as well as determining the risk of having a second stroke within 90 days. The software was also able to reduce the disagreement time between doctors in identifying the stroke cause from 50 to 20 percent.

"The validity data that have emerged from the current study add to the utility of the software-based approach and highlight once again that careful identification and accurate classification of the underlying etiology is paramount for every patient with stroke," said Ay, who is an associate professor of radiology at Harvard Medical School. "The information the software provides not only is critical for effective stroke prevention but also could increase the chances for new discoveries by enhancing the statistical power in future studies of etiologic stroke subtypes. We estimate that, compared to conventional systems, the use of CCS in stroke prevention trials testing targeted treatments for a particular etiologic subtype could reduce the required sample size by as much as 30 percent."