High-risk breast lesions – biopsy-diagnosed lesions that carry an increased risk of becoming cancerous – are most commonly surgically removed. However, many such lesions do not pose an immediate threat and can be safely monitored with follow-up imaging, sparing patients from surgery.

"Most institutions recommend surgical excision for high-risk lesions such as atypical ductal hyperplasia, for which the risk of upgrade to cancer is about 20%," explains study author and radiologist Manisha Bahl. "For other types of high-risk lesions, the risk of upgrade varies quite a bit in the literature, and patient management, including the decision about whether to remove or survey the lesion, varies across practices."

Bahl and colleagues aimed to develop a machine learning model that can distinguish high-risk breast lesions that require surgical excision from those that are at low risk for upgrade to cancer. The model analysed traditional risk factors, such as patient age and lesion histology, along with unique features, including words that appeared in the text of the biopsy pathology report.

The researchers trained the model on a group of patients with biopsy-proven high-risk lesions who had surgery or at least two-years' of imaging follow-up. Of the 1006 high-risk lesions identified, 115 (11%) were upgraded to cancer.

After training the machine learning model on two-thirds of the high-risk lesions, the researchers tested it on the remaining 335 lesions. The model correctly predicted 37 of the 38 lesions that were upgraded to cancer, identifying the terms "severely" and "severely atypical" in the text of the pathology reports as associated with a greater risk of upgrade to cancer. Importantly, 30.6% of surgeries of benign lesions could have been avoided.

"Our goal is to apply the tool in clinical settings to help make more informed decisions as to which patients will be surveilled and which will go on to surgery," Bahl added. "I believe we can capitalize on machine learning to inform clinical decision making and ultimately improve patient care."