Software developed by researchers at Imperial College London (ICL) and the University of Edinburgh in the U.K. has helped enhance stroke and dementia diagnosis by quantifying the severity of small vessel disease (SVD).
"This is the first time that machine learning methods have been able to accurately measure a marker of small vessel disease in patients presenting with stroke or memory impairment who undergo [computed tomography (CT)] scanning," says ICL's Paul Bentley.
The researchers used the historical data of 1,082 CT scans of stroke patients across 70 U.K. hospitals over 14 years. The software identified and measured an SVD marker in each scan, producing a severity score.
The team compared the results to those of a committee of expert physicians, whose estimates of SVD severity matched that of the software.
In addition, using magnetic resonance imaging to estimate SVD in 60 patients demonstrated that the software was 85% accurate at predicting its severity.
From Imperial College London
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found