525P - Clinical Experience with IBM Watson for Oncology (WFO) for Multiple types of Cancer patients in China (525P)

Date 18 November 2017
Event ESMO Asia 2017 Congress
Session Poster lunch
Topics Personalised Medicine
Presenter Lu Yue
Citation Annals of Oncology (2017) 28 (suppl_10): x155-x165. 10.1093/annonc/mdx676
Authors L. Yue, L. Yang
  • Oncology Department, Qingdao Municipal hospital, 266071 - Qingdao/CN

Abstract

Background

IBM Watson for Oncology (WFO) is a Memorial Sloan Kettering-trained cognitive computing system that uses natural language processing (NLP) to ingest data in structured and unstructured formats. WFO provides physicians with evidence-based treatment options and ranks them into three categories for oncology treatment decision support. This study examined the concordance between treatment recommendations proposed by WFO and Qingdao Municipal hospital.

Methods

Retrospective data from 160 stage I-IV cancer patients were ingested into WFO from April 2017 to June 2017. WFO recommendations were provided in 3 categories: “Recommended”, “For Consideration”, and “Not Recommended.” Concordance was analyzed by comparing the treatment decisions proposed by WFO to those of the multi-disciplinary tumor board. Concordance was achieved when the multi-disciplinary tumor boards’ treatment decisions were in the “Recommended” or “For Consideration” categories in WFO.

Results

A total of 160 cancer cases were recorded and analyzed. By tumor type, 35% of patients were colorectal cancer, 21.8% were gastric cancer, 21.8% were lung cancer, 19.3% were breast cancer. Overall, treatment recommendations were concordant in 95% of cases. Among them, the coincidence rate is 98% in breast cancer, 96% in colorectal cancer, 93% in gastric cancer, and 87% in lung cancer. By tumor type, the concordant level was higher in colorectal and breast cancer but lower in lung cancer. The major reason for this situation is perhaps that some types of tumor, such as lung cancer, are general complex and WFO still needs constant learning.

Conclusions

Treatment recommendations made by Qingdao Municipal hospital shows WFO is a good assistant for oncologist, especially for doctors with limited clinical experiences. And due to its rapidity and convenience, WFO will play an important role in the treatment of cancer.

Clinical trial identification

Legal entity responsible for the study

Qingdao Municipal hospital

Funding

None

Disclosure

All authors have declared no conflicts of interest.