2019 ASCO Annual Meeting!
Session: Health Services Research, Clinical Informatics, and Quality of Care
Type: Poster Session
Time: Saturday June 1, 1:15 PM to 4:15 PM
Location: Hall A
A prospective blinded study of 1000 cases analyzing the role of artificial intelligence: Watson for oncology and change in decision making of a Multidisciplinary Tumor Board (MDT) from a tertiary care cancer center.
Care Delivery/Models of Care
Health Services Research, Clinical Informatics, and Quality of Care
2019 ASCO Annual Meeting
Poster Board Number:
Poster Session (Board #224)
J Clin Oncol 37, 2019 (suppl; abstr 6533)
Author(s): S.P. Somashekhar, Martín-J. Sepúlveda, Edward H Shortliffe, Rohit Kumar C, Amit Rauthan, Poonam Patil, Ramya Yethadka; Manipal Comprehensive Cancer Center, Bangalore, India; Retired IBM Research, Saint Augustine, FL; Arizona State Biomedical Informatics, College of Health Solutions, Arizona State University, Phoenix, AZ; Manipal Hospital, Bangalore, India
Background: Artificial intelligence is being used to provide support for information-intensive decision making. In this report, we present our experience in explaining how artificial intelligence adds value to MDT’s decision making ability & paves way for personalized therapy. Methods: 1000 cases involving breast, lung, and colorectal cancer were evaluated by a multidisciplinary tumor board at a major cancer center in India between 2016 and 2018. After the tumor board decision was made, MDT was presented with the Watsons recommendations contemporaneously. MDT reviewed their decision after going through Watson’s recommendations and also the evidences that it put forth supporting its decision. Cases in which decision was changed, objective assessment was done by asking MDT to quote the reasons for reviewing and changing their decision. Results: Of 1000 cases, breast, lung, colon & rectal cancers were 620, 130,126 & 124 respectively. There were 712 non-metastatic & 288 metastatic cases. Mean age of the patients was 54.3 ± 12.2. Treatment concordance was observed in 92% for all cancers combined, 93% for rectal cancer, 92% for breast cancer, 89% for lung cancer, and 81% for colon cancer.MDT changed their decision in 136 cases (13.6%). The reasons for tumour board to change their decision was, Watson provided recent evidences for newer treatment in 55%, better personalized alternative in 30% & new insights from genotypic and phenotypic data and evolving clinical experiences in 15% of time. Conclusions: The study suggest that cognitive computing decision support system holds substantial promise to reduce the cognitive burden on oncologists by providing expert, updated, recent evidence-based insights for treatment-related decision-making. The 13.6 % incremental advantage over and above in a tertiary cancer centre with functioning MDT speaks in itself the value of having a learned colleague like Watson for oncology at our disposal. It will certainly add more value in settings lacking ready access to high quality cancer expertise and information. These systems can be valuable adjuncts to strong patient-clinician relationships in the delivery of high quality cancer care.