Triple blinded prospective study assessing the impact of genomics: EndoPredict and artificial intelligence Watson for Oncology (WFO) on MDT’s decision of adjuvant systemic therapy for hormone receptor positive early breast carcinoma.

Abstract

e18013 Background: : Decision on adjuvant systemic therapy in hormone positive early breast carcinoma is the only grey area in breast carcinoma management. This study was done to investigate the concordance between the results of genomic test, artificial intelligence and tumor board decision and implications of the same in clinical practice. Methods: This was a triple blinded, prospective study. Decision regarding the adjuvant systemic therapy was done by the multidisciplinary tumor board (MDT)after reviewing the pathology reports & the results correlated with Endopredict test reports & artificial intelligence(Watson for Oncology). Results: Total of 42 patients included. Mean age was 58.3 years, 71.4% were post-menopausal. Breast conservation was done in 47.6%. 64.2% were T1-2N0 stage. Infiltrating ducal carcinoma was major type (83.3%). Decision by MDT to give adjuvant chemotherapy was for 25 patients (59.5%) & hormonal therapy for rest. Recommendation by Watson for oncology was to give adjuvant chemotherapy in 50%. Endopredict score (EPclin) resulted in a low-risk group of 22 patients (52.3%), while 15(47.6%) had a high risk EPclin score. Discordance between the endopredict test, Watson & tumor board was for 11 patients (26.1%): 3 patients had high risk score, but the tumor board decision was to give hormonal therapy due to the age factor. 8 patients had low risk score, but tumor board decision was to give adjuvant chemotherapy. Extremes of age, premenopausal status, intermediate grade & high Ki 67% values were the factors associated with discordance. The treatment decision changed for 4 patients (4/11, 36%) after reviewing the endopredict test and Watson recommendation. Conclusions: Tumor board decision can be more scientific & evidence based with the help of genomics & a learnt colleague in the form of Watson for Oncology. Even though the clinical experience is the important determinant of adjuvant therapy, genomic test with artificial intelligence, which includes the scientific evidence, will guide in decision making. Long term follow up is needed for the validation in our clinical setting.

Physicians’ Perceptions of and Satisfaction With Artificial Intelligence in Cancer Treatment: A Clinical Decision Support System Experience and Implications for Low-Middle–Income Countries

“…These results demonstrate the potential of WfO to positively impact cancer outcomes by providing scientific evidence and up-to-date information on clinical guidelines. In a separate study that focused on adjuvant systemic therapy for breast carcinoma, treatment decisions were changed for 4 of 11 patients after the MDT reviewed WfO's recommendations and EndoPredict (Myriad Genetics Inc) test reports [24]. WfO was able to aid clinicians in providing personalized cancer care while addressing the difficulties of staying informed on evolving cancer guidelines and studies.…”

A Targeted Review of Breast Cancer Studies of Concordance for an Internationally-Implemented Artificially Intelligent Clinical Decision-Support System

“…Of the 56 reports that had different research questions or outcomes, 26 did not report concordance as an outcome, 1 compared concordance of system-generated therapeutic options with real world evidence treatment decisions derived from a cohort of US breast cancer patients, 21 and 1 compared concordance of system-generated therapeutic options with treatments recommended by a breast cancer genomic test. 22 In total, our targeted review included 10 breast cancer concordance studies.…”