A research team from Mass General Brigham and Dana-Farber Cancer Institute has developed an artificial intelligence (AI) tool designed to predict the risk of cancer spread in patients with oropharyngeal cancer. The findings were published in the Journal of Clinical Oncology.
The AI-based tool uses imaging data from computed tomography scans to estimate the number of lymph nodes affected by extranodal extension (ENE), a condition where cancer spreads beyond the lymph node into surrounding tissue. ENE is currently only confirmed through surgical removal and examination of lymph nodes, making noninvasive prediction valuable for treatment planning.
"Our tool may help identify which patients should receive multiple interventions or would be ideal candidates for clinical trials of intensive strategies such as immunotherapy or additional chemotherapy," said Benjamin Kann, MD, senior author and member of the Artificial Intelligence in Medicine (AIM) Program at Mass General Brigham, as well as a radiation oncologist at Dana-Farber Cancer Institute and Brigham and Women's Hospital. "Our tool can also help identify which patients should undergo de-intensification of treatment, such as surgery alone."
Oropharyngeal cancer treatments often involve combinations of surgery, radiation therapy, and chemotherapy. These treatments can be challenging for patients and may have long-term side effects. Accurately identifying which patients need more aggressive treatment versus those who could benefit from less intensive approaches is important for patient care.
When tested on imaging scans from 1,733 patients with oropharyngeal carcinoma, the AI tool was able to predict uncontrolled cancer spread and lower survival rates. Incorporating the AI's assessment into existing clinical risk models improved predictions regarding patient outcomes.
"The AI tool enables the prediction of number of lymph nodes with ENE, which could not be done before, and shows that it is a powerful, novel prognostic biomarker for oropharyngeal cancer that could be used to improve the current staging scheme and treatment planning," Kann said.
