This Article is From Aug 30, 2016

New Artificial Intelligence System Can Quickly Predict Breast Cancer Risk

New Artificial Intelligence System Can Quickly Predict Breast Cancer Risk

An artificial intelligence software developed that can assist in predicting breast cancer risk.

Houston: Scientists, including those of Indian origin, have developed an artificial intelligence (AI) software that can assist doctors to quickly and accurately predict breast cancer risk.

The software intuitively translates patient charts and mammograms into diagnostic information at 30 times human speed and with 99 per cent accuracy.

"This software intelligently reviews millions of records in a short amount of time, enabling us to determine breast cancer risk more efficiently using a patient's mammogram. This has the potential to decrease unnecessary biopsies," said Stephen T Wong, from the Houston Methodist Research Institute in the US.

Researchers, including Jitesh Shewale of University of Texas, Tajel Patel and Mamta Puppala from Houston Methodist, used the AI software to evaluate mammograms and pathology reports of 500 breast cancer patients.

The software scanned patient charts, collected diagnostic features and correlated mammogram findings with breast cancer subtype.

Clinicians used results, like the expression of tumor proteins, to accurately predict each patient's probability of breast cancer diagnosis.

Currently, when mammograms fall into the suspicious category, a broad range of 3 to 95 per cent cancer risk, patients are recommended for biopsies.

Over 1.6 million breast biopsies are performed annually nationwide, and about 20 per cent are unnecessarily performed due to false-positive mammogram results of cancer free breasts, researchers said.

Researchers hope this AI software will help physicians better define the per cent risk requiring a biopsy, equipping doctors with a tool to decrease unnecessary breast biopsies.

Manual review of 50 charts took two clinicians 50-70 hours. AI reviewed 500 charts in a few hours, saving over 500 physician hours.

"Accurate review of this many charts would be practically impossible without AI," said Wong.

The research was published in the journal Cancer.
.