A new artificial intelligence (AI) software, developed by researchers at the Houston Methodist Research Institute in the U.S., could soon help doctors to accurately predict the risk of breast cancer in patients by analyzing massive amounts of the patient's data in a very short period.
The AI software is capable of reviewing and interpreting patient charts and mammograms into "diagnostic information" 30 times faster than the speed of humans with 99 percent accuracy, according to a recent study published in the journal Cancer.
Typically, it takes over fifty hours for two people to manually review only fifty charts. However, it would take an AI system only a "few hours" to review a whopping 500 charts.
"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," said Stephen T. Wong, Ph.D., P.E., chair of the Department of Systems Medicine and Bioengineering at Houston Methodist Research Institute. "This has the potential to decrease unnecessary biopsies," Wong added.
The researchers are hoping this AI software would help doctors and clinicians to save hundreds of hours spent in reviewing and also to reduce the percentage of unnecessary biopsies performed due to false-positive results.
The American Cancer Society (ACS) reported that about fifty percent of the total mammograms being performed every year in the U.S. produce false-positive results, and as a consequence, doctors end up telling one in every two healthy women that they have cancer.