30 August 2016
US scientists have demonstrated the potential of artificial intelligence to help predict breast cancer in future.
A team from Houston Methodist have developed an AI software that is able to reliably interpret mammograms, intuitively translating patient charts into diagnostic information at 30 times human speed and with 99 per cent accuracy.
Using the software, they were able to evaluate mammograms and pathology reports of 500 breast cancer patients, scanning patient charts, assessing diagnostic features and correlating the findings according to breast cancer subtype.
These results were then used to accurately predict each patient's probability of breast cancer diagnosis. Whereas the manual review of 50 charts took two clinicians 50 to 70 hours, the AI was able to review 500 charts in a few hours.
Dr Stephen Wong, chair of the department of systems medicine and bioengineering at Houston Methodist Research Institute, said: "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."
Given that around 20 per cent of biopsies are currently performed unnecessarily due to false-positive mammogram results, this could be an important advance.
Posted by Edward Bartel
Health News is provided by Axonn Media in collaboration with Spire Healthcare. Please note that all copy above is ©Axonn Media and does not reflect views or opinions of Spire Healthcare unless explicitly stated. Additional comments on the page from individual Spire consultants do not necessarily reflect the views or opinions of other consultants or Spire Healthcare.