Start Your Search
P1.01 - Advanced NSCLC (ID 757)
- Event: WCLC 2017
- Type: Poster Session with Presenters Present
- Track: Advanced NSCLC
- Presentations: 1
- Coordinates: 10/16/2017, 09:30 - 16:00, Exhibit Hall (Hall B + C)
P1.01-069 - Clinical Experience with IBM Watson for Oncology (WFO) Cognitive System for Lung Cancer Treatment in China (ID 9774)
09:30 - 16:00 | Author(s): A. Li
IBM Watson for Oncology (WFO) is a Memorial Sloan Kettering-trained cognitive computing system. Watson provides evidence-based treatment options and ranks them into three categories for oncologist decision making as "Recommended ","For Consideration" and "Not Recommended". We examined the concordance of treatment options in Lung cancer patients between WFO and tumor board in the Affiliated Hospital of Qingdao University, China.
33patients with stage I-IV lung cancer were enrolled in this study. By tumor stage, 15.1% (5 of 33) patients are Phase I or II, 15.1% (5 of 33) are Phase III and the rest of the patients (23 of 33) are Phase IV. By histology, 18.2% (6 of 33) are small cell lung cancer (SCLC) and 81.8% (27 of 33) are non-small cell lung cancer (NSCLC). Options were considered concordant when it was included in the “Recommended” or “For Consideration” categories.
Overall, treatment recommendations were concordant in 96.9% (32 of 33) of cases. By histology, 100% of SCLC patients’ therapy regimes were concordant with the recommended one, and treatment recommendations were concordant in 96.3% of NSCLC patients. By tumor stage, treatment recommendations were concordant in 100% of I- III and 96% of Phase IV lung cancer. Of the whole cases, 69.7% were recommended and 27.3% were for consideration (figure1). The majority reason for choosing consideration option is that the immunotherapy drugs targeted PD-1 or PD-L1 such as Nivolumab, Pembrolizumab and Atezolizumab recommended by Watson for Oncology had not been launched in China.Figure 1
Treatment recommendations made by the Affiliated Hospital of Qingdao University and Watson for Oncology were highly concordant in lung cancer. We’ll make further analysis for this cognitive computing system in more cases and other types of carcinomas.