A Dartmouth research team has found a machine learning method to avoid unnecessary breast surgery, by predicting the upgrade from ADH to cancer.
Atypical ductal hyperplasia (ADH) is a breast lesion which is associated with a four to five-fold increase in breast cancer risk. ADH is usually found using mammography and core needle biopsy. Currently, surgical removal is recommended for all cases on ADH found on core needle biopsies to determine whether the lesion is cancerous. Between around twenty to thirty percent of ADH cases are upgraded to cancer following the surgery, which means that seventy to eighty percent of women go through a surgical procedure for the beningn, yet high-risk, lesion. The research team found the machine learning method to predict the upgrade to cancer, which may help to avoid unnecessary breast surgery.
It could help low-risk patients and clinicians despite whether there is a reasonable alternative to surgical excision for them, such as active surveillance and hormonal therapy.
Saeed Hassanpour, PhD, who led the research team, explained “Our results suggest there are robust clinical differences between women at low versus high risk for ADH upgrade to cancer based on core needle biopsy data that allowed our machine learning model to reliably predict malignancy upgrades in our dataset. This study also identified important clinical variables involved in ADH upgrade risk. Using surgical excision to rule out malignancy is not without harm as 70-80% of women undergo invasive surgical excision for benign ADH lesions. “Our model can potentially help patients and clinicians choose an alternative management approach in low-risk cases,”
Hassanpour concluded: “In the era of personalized medicine, such models can be desirable for patients who value a shared decision-making approach with the ability to choose between surgical excision for certainty versus surveillance to avoid cost, stress, and potential side effects in women at low risk for upgrade of ADH to cancer.”