AI May Predict the Risk for Distant Recurrence in Endometrial Cancer

Artificial intelligence (AI) was able to accurately predict which patients with endometrial cancer had a low and high risk for distant recurrence, or the cancer recurring in a part of the body far away from the original tumor’s location, according to recent data from a study.

In particular, researchers used a deep learning risk prediction model, a form of AI, to identify patients at risk for distant recurrence, according to data presented during the 2023 AACR Annual Meeting.

Findings from the study showed that the model was able to identify 89 patients having a low risk, 175 having an intermediate risk and 89 having a high risk of distant recurrence out of a dataset of 353 patients that was not used to train the model. Subsequently, 3.37%, 15.43% and 36%, of patients categorized by the model as being low, intermediate and high risk of recurrence, respectively, actually experienced a distant recurrence.

“Endometrial cancer is the most common gynecological cancer, and the primary treatment is surgery,” Sarah Fremond, a PhD candidate in the department of pathology at Leiden University Medical Center in The Netherlands, said in a presentation of the data. “Most patients have a good prognosis and do not require any adjuvant treatment. (However,) there is a proportion who will develop distant recurrence and for those, you want to recommend adjuvant chemotherapy. This is the only treatment in the adjuvant setting known to lower the risk of distant recurrence, but it also causes morbidity. (We wanted to know how to) accurately identify patients at low and high risk of distant recurrence to reduce under and overtreatment.”

Investigators created the AI model using long-term follow-up data from 1,761 patients with endometrial cancer who had not previously received adjuvant chemotherapy. Patients with stage 4 disease and those who had previously received chemotherapy were excluded from the model.

Fremond noted that patient characteristics currently being considered, such as histological type and grade, stage and molecular class, have challenges when trying to be assessed correctly. Challenges include variability, limited use of visual information in tumor slides, costs, turnaround time and interpretation. Thus, it is currently very difficult to combine all of these data to specifically target risk of distant recurrence, she said. In response, investigators created this model to predict risk of distant recurrence using routine data.

Additional findings showed the 10-year distant recurrence-free survival probability was the highest among patients who were determined by the AI model to have a low-risk of distant recurrence (81 patients).

Study limitations include its retrospective design (comparing two groups of patients: ones with a disease and ones without), according to the researchers.

For more news on cancer updates, research and education, don’t forget to subscribe to CURE®’s newsletters here.