Breast cancer treatment decisions and adherence to National Comprehensive Cancer Center (NCNN) guidelines are significantly impacted by use of an artificial intelligence (AI)-based clinical decision support system (JCO Clin Cancer Inform. 2020;4:824-838. doi:10.1200/CCI.20.00018).
A cross-sectional observational study examined the relationship between AI use and its impact on oncology practice. In the study, 1977 patients at high risk for recurrent or metastatic breast cancer from the Chinese Society of Clinical Oncology were observed for treatment changes. Statistical analyses determined treatment changes and characteristics of physician age, patient age, and receptor subtype/TNM stage.
Of the 1977 patients, 105 (5%) experienced treatment decision changes. The patients with the greatest number of changes were those with hormone receptor (HR)-positive disease or stage IV disease in the first-line therapy setting (73% and 58%, respectively).
“Logistic regressions showed that decision changes were more likely in those with HR-positive cancer (odds ratio [OR], 1.58; P <.05) and less likely in those with stage IIA (OR, 0.29; P <.05) or IIIA cancer (OR, 0.08; P <.01),” wrote Fengrui Xu, MD, Department of Breast Cancer, Academy of Military Medical Sciences, Beijing, People’s Republic of China and colleagues.
Considerations of the clinical decision support system therapeutic options, patient factors highlighted by the tool, and the decision logic of the tool were listed reasons for the changes. Notably, patient age and physician age were not associated with treatment change decisions. An increase by .5% (P = .003) in adherence to NCNN treatment guidelines occurred because of clinical decision support system use.
“Use of an artificial intelligence–based [clinical decision support system] had a significant impact on treatment decisions and NCCN guideline adherence in HR-positive breast cancers,” concluded Dr Xu and colleagues.—Lisa Kuhns
