2017 ASCO Annual Meeting!
Session: Lung Cancer—Non-Small Cell Local-Regional/Small Cell/Other Thoracic Cancers
Type: Poster Session
Time: Saturday June 3, 8:00 AM to 11:30 AM
Location: Hall A
Early experience with IBM Watson for Oncology (WFO) cognitive computing system for lung and colorectal cancer treatment.
Lung Cancer—Non-Small Cell Local-Regional/Small Cell/Other Thoracic Cancers
2017 ASCO Annual Meeting
Poster Board Number:
Poster Session (Board #263)
J Clin Oncol 35, 2017 (suppl; abstr 8527)
Author(s): S.P. Somashekhar, Martín-J. Sepúlveda, Andrew D Norden, Amit Rauthan, Kumar Arun, Poonam Patil, Ramya Y Ethadka, Rohit C Kumar; Manipal Comprehensive Cancer Center, Bangalore, India; IBM, Saint Augustine, FL; IBM Watson Health, Cambridge, MA; Manipal Hospital, Bangalore, India
Background: IBM Watson for Oncology is an artificial intelligence cognitive computing system that provides confidence-ranked, evidence-based treatment recommendations for cancer. In the present study, we examine the level of agreement for lung and colorectal cancer therapy between the multidisciplinary tumour board from Manipal Comprehensive Cancer Centre in Bangalore, India, and Watson for Oncology. Methods: Watson for Oncology is a Memorial Sloan Kettering Cancer Center (New York, USA) trained cognitive computing system that uses natural language processing and machine learning to provide treatment recommendations. It processes structured and unstructured data from medical literature, treatment guidelines, medical records, imaging, lab and pathology reports, and the expertise of Memorial Sloan Kettering experts to formulate therapeutic recommendations. Treatment recommendations are provided in three categories: recommended, for consideration and not recommended. In this report we provide the results of the independent and blinded evaluation by the multidisciplinary tumour board and Watson for Oncology of 362 total cancer cases comprised of 112 lung, 126 colon and 124 rectal cancers seen at the Centre within the last three years. The recommendations of the two agents were compared for agreement and considered concordant when the tumour board recommendation was included in the recommended or for consideration categories of the treatment advisor. Results: Overall, treatment recommendations were concordant in 96.4% of lung, 81.0% of colon and 92.7% of rectal cancer cases. By tumour stage, treatment recommendations were concordant in 88.9% of localized and 97.9% of metastatic lung cancer, 85.5% of localized and 76.6% of metastatic colon cancer, and 96.8% of localized and 80.6% of metastatic rectal cancer. Conclusions: Treatment recommendations made by the Manipal multidisciplinary tumour board and Watson for Oncology were highly concordant in the cancers examined. This cognitive computing technology holds much promise in helping oncologists make information intensive, evidence based treatment decisions.
1. Gefitinib (G) versus vinorelbine+cisplatin (VP) as adjuvant treatment in stage II-IIIA (N1-N2) non-small-cell lung cancer (NSCLC) with EGFR-activating mutation (ADJUVANT): A randomized, Phase III trial (CTONG 1104).