New Delhi, Sep 17 (PTI) Researchers have developed an artificial intelligence tool that could predict the risk of heart disease in women by analysing their mammogram and age, without depending on an extensive medical history.
Described in a paper in the journal 'Heart', the AI tool was trained and validated using routine mammograms from over 49,000 women in the state of Victoria, Australia, obtained from hospital and death records.
One of the authors of the paper, Clare Arnott, an associate professor and the global director of the Cardiovascular Program at The George Institute, emphasised the need for new methods to identify women at risk for cardiovascular disease to improve screening.
"By integrating (cardiovascular) risk screening with breast screening through the use of mammograms -- something many women already engage with at a stage in life when their cardiovascular risk increases -- we can identify and potentially prevent two major causes of illness and death at the same time," Arnott said.
"A deep learning algorithm based on only mammographic features and age predicted cardiovascular risk with performance comparable to traditional cardiovascular risk equations," the authors wrote.
The researchers added that previous studies have looked at features of a mammogram, such as breast arterial calcification -- associated with cardiovascular risk in certain populations.
However, relying on the feature alone has limitations, including being less accurate in predicting heart disease risk in older women, they said.
Arnott said, "Our model is the first to use a range of features from mammographic images combined simply with age -- a key advantage of this approach being that it doesn't require additional history taking or medical record data, making it less resource intensive to implement, but still highly accurate." Author and cardiologist Dr Jennifer Barraclough, research fellow at The George Institute, said leveraging an existing risk screening process widely used by women could serve as a cardiovascular risk prediction tool for women in diverse communities across Australia and around the world.
The researchers are looking to test the AI tool in diverse populations and understand potential barriers to its implementation. PTI KRS KRS MPL MPL