New artificial intelligence software developed by researchers at the Houston Methodist Research Institute in Texas can accurately predict breast cancer risk.
The team says the program can interpret mammograms and translate patient data into diagnostic information 30 times faster than a human doctor, with 99% accuracy.
The researchers used the software to evaluate mammograms and pathology reports of 500 breast cancer patients. They say the program scanned patient charts, collected diagnostic features, and correlated mammogram findings with breast cancer subtype. Clinicians were able to use the results, such as the expression of tumor proteins, to accurately predict each patient's probability of breast cancer diagnosis.
The team says the software could help physicians make better decisions with regard to which patients need biopsies. They note 20% of the invasive procedures were not needed.
"This has the potential to decrease unnecessary biopsies," says Stephen T. Wong, chair of the institute's Department of Systems Medicine and Bioengineering.
From Wired.co.uk
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found