A machine learning tool can help identify which high-risk breast lesions are likely to become cancerous with 97 per cent accuracy, an advance that may help reduce unnecessary surgeries, a study has revealed.
High-risk breast lesions are biopsy-diagnosed lesions that carry an increased risk of developing into cancer. Surgery is often the preferred treatment option.
But a lot of the lesions do not pose an immediate danger to patients. However, doctors tend to over-screen for breast cancer.
Using the machine learning tool could help improve detection as well as prevent over treatment, said researchers from Harvard University.
The findings showed that the tool could avoid almost one-third of benign surgeries with accurate prediction of 37 out of 38 lesions, or 97 per cent, that were upgraded to cancer.
The tool, described in the journal Radiology, also identified the terms “severely” and “severely atypical” in the text of the pathology reports as associated with a greater risk of upgrade to cancer.
“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 can also support more targeted, personalised approaches to patient care,” said Constance Lehman, Professor at Harvard Medical School.
“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,” added lead author and radiologist Manisha Bahl, from Massachusetts General Hospital.