Machine Learning Model Predicts Breast Lesions Likely to Become Cancer

A machine learning model may help predict the risk of high-risk breast lesions (HRLs), decreasing unnecessary surgical procedures, according to a proof of concept study published in Radiology.

Researchers from Harvard Medical School in Boston, MA, performed a proof of concept study to see if their machine learning model allowed HRLs diagnosed with image-guided needle biopsy requiring surgical excision could be distinguished from HRLs at low risk for upgrade to cancer at surgery.

“There are different types of high-risk lesions,” study author Manisha Bahl, MD, a radiologist from Massachusetts General Hospital (MGH) and Harvard Medical School, said in a release. “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 percent. 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.”[[{"type":"media","view_mode":"media_crop","fid":"64300","attributes":{"alt":"Manisha Bahl, MD","class":"media-image media-image-right","id":"media_crop_6612538843128","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"8229","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"float: right;","title":"Manisha Bahl, MD","typeof":"foaf:Image"}}]]

The researchers identified consecutive patients with biopsy-proven HRLs who underwent surgery or at least two years of imaging follow-up from June 2006 to April 2015. A random forest machine learning model was developed to identify HRLs at low risk for upgrade to cancer. Traditional features such as age and HRL histologic results were used in the model, as were text features from the biopsy pathologic report.

The results showed that 1006 HRLs were identified, with a cancer upgrade rate of 11.4% (115 of 1006). A machine learning random forest model was developed with 671 HRLs and tested with an independent set of 335 HRLs. Among the most important traditional features were age and HRL histologic results, such as atypical ductal hyperplasia. The researchers noted that an important text feature from the pathologic reports was “severely atypical.” Instead of surgical excision of all HRLs, if those categorized with the model to be at low risk for upgrade were surveilled and the remainder were excised, then 97.4% (37 of 38) of malignancies would have been diagnosed at surgery, and 30.6% (91 of 297) of surgeries of benign lesions could have been avoided.

“Our study provides ‘proof of concept’ that machine learning can not only decrease unnecessary surgery by nearly one-third in this specific patient population, but also can support more targeted, personalized approaches to patient care,” senior author, Constance Lehman, MD, PhD, a professor at Harvard Medical School and Director of Breast Imaging at MGH, said in the same release.

“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.”