“HPV-related oropharyngeal cancer is now the most common form of this cancer. And these patients respond very well to surgery or surgery.
and radiation, there’s a lot of interest in trying to figure out ways to reduce the burden of treatment so patients can have fewer side effects and long-term problems that reduce quality of life,” said first author Benjamin Kann, MD. A type of minimally invasive surgery for these patients called minimally invasive surgery is an attractive strategy. is to use
However, the presence of ENE is a risk factor for postoperative cancer recurrence and poor overall survival rates, making patients with ENE poor candidates for TORS. “If ENE is detected postoperatively, these patients still need to receive a long course of chemotherapy and radiation or trimodal therapy, which is associated with the worst complications and quality of life outcomes,” Kann said.
Improving Throat Cancer Outcomes with Artificial Intelligence
Historically, ENE has been very difficult to detect using conventional diagnostic imaging, so despite screenings, there are still a significant number of patients who require trimodal therapy. “The unmet need in this study, and the impetus for using artificial intelligence, was to see if we could do a better job of predicting the presence of ENE on CT prior to treatment, so we could help select patients suitable for surgery or chemotherapy and radiation.” for,” said Cannes.
For this study, the team performed a retrospective evaluation of AI algorithm performance using pretreatment CTs and corresponding surgical pathology reports from ECOG-ACRIN Cancer Study Group E3311, a multicenter, phase 2 escalation trial.
“What’s important about this study is that it tested the algorithm in the context of a very large randomized clinical trial where the enrolled patients, by definition, had to be screened for ENE, but a significant proportion still ended up having ENE,” Kann said. “When we applied the algorithm to this population to see how it would do in predicting ENE, we found it performed well with high accuracy—better than four specialist head and neck radiologists.
“The main benefit is increased sensitivity or a lower percentage of missed ENE,” Kann said. “Ideally, better recognition of ENE before treatment would result in a lower rate of trimodal therapy and improved quality of life for patients.”