551PD - Validation study to assess performance of IBM cognitive computing system Watson for oncology with Manipal multidisciplinary tumour board for 1000 c...

Date 17 December 2016
Event ESMO Asia 2016 Congress
Session Basic science and translational research
Topics Personalised/Precision Medicine
Translational Research
Presenter Somashekhar Somashekhar S P
Citation Annals of Oncology (2016) 27 (suppl_9): ix179-ix180. 10.1093/annonc/mdw601
Authors S. Somashekhar S P1, R. Kumar1, A. Kumar2, P. Patil3, A. Rauthan3
  • 1Surgical Oncology, Manipal Comprehensive Cancer Center Manipal Hospital, 560017 - Bangalore/IN
  • 2Biostatastics, Manipal Comprehensive Cancer Center Manipal Hospital, 560017 - Bangalore/IN
  • 3Medical Oncology, Manipal Comprehensive Cancer Center Manipal Hospital, 560017 - Bangalore/IN



IBM Watson for Oncology (WFO) developed in collaboration with MSKCC, NY is a cognitive computing system. WFO is designed to assist oncologists in making treatment decisions by bringing in together all the available medical information. In the present study we try to evaluate WFO treatment recommendations with Manipal multidisciplinary tumour board (MMDT), a quaternary centre for 1000 cases.


MMDT treatment recommendation and data of 1000 cases of 4 different cancers breast (638), colon (126), rectum (124) and lung (112) which were treated in last 3 years was collected by team of two doctors who were working in oncology department for more than 3 years. The treatment recommendations given by WFO was recorded. WFO treatment option were compared with MMDT treatment recommendation. Treatment recommendation by WFO came in three category with colour coding, Green is the recommended standard treatment (REC), Orange is to be considered (FC) and Red is not recommended (NREC). Concordance between MMDT and WFO was analysed.


Of the treatment recommendations given by MMDT, WFO provided 50% in REC, 28% in FC, 17% in NREC. Nearly 80% of the MMDT treatment recommendations were in WFO REC and WFO-FC group. However 5% of the treatment provided by MMDT was not available with WFO. WFO-REC treatment for Organ was high in Rectum with 85% and least in Lung with 17.8%. In breast cancer alone the WFO-REC treatment was high with triple negative disease with 67.9% and least with hormone positive, Her 2neu negative disease with 35%. WFO took a median of 40 seconds to capture, analyze and give the treatment.


WFO-REC and WFO-FC together were in 80% of time concordant with the MMDT treatment recommendations. WFO could be an essential tool to oncologists by reducing the cognitive burden of physicians in keeping up with medical literature by providing clinically actionable insights to assist them in treating patients. The median time of about 15 minutes needed per patient might be of concern in a busy OPD. However WFO will be only a assisting tool and it will never be able to replace the patient-doctor relationship which is a very essential component of treating a patient suffering with cancer.

Clinical trial indentification


Legal entity responsible for the study

Manipal Hospital


Manipal Hospital


All authors have declared no conflicts of interest.