LAUSR

Introduction/Background IBM Watson for Oncology (WFO) has begun to be used in Korea. It provides physicians with evidence-based treatment options. We assessed differences of survival between WFO Rx and the Site Rx for each of the patients with cervical cancer IB to IIA undergoing primary surgical treatment. Methodology This retrospective multicenter study collected the database from 4 academic institutes between January 2000 and December 2014. Of the 1612 total, 161 were excluded because they had rare histology, inadequate imaging study, over age-range that covered by WFO or history of neoadjuvant chemotherapy, any of one of which is not applicable to WFO. WFO assign every patient to one of the following subgroups: A. Unavailable to the site. B. Unknown to WFO. C. Green therapies in WFO: preferred. D. Yellow therapies in WFO: acceptable. E. Red therapies in WFO: unacceptable. Results The clinical and pathological characteristics of the patients are shown in table 1. The numbers of each subgroup were as follows: A 0; B 129; C 879; D 80; E 363. The 5-year disease free survival (DFS) were 83.2% in B, 89.0% in C, 93.5% in D, 83.5% in E. The 5-year overall survival (OS) were 93.0% in B, 93.0% in C, 97.4% in D, 92.3% in E. Based on subgroup C, comparison of survival with other subgroups is shown in table 1. Conclusion This retrospective study showed that WFO Rx for the patients with cervical cancer IB to IIA undergoing primary surgical treatment may be effective tools. Disclosure Nothing to disclose. Abstract EP342 Table 1 Comparison of survival with other subgroups based on subgroup C Subgroup p-value (log-rank, DFS) p-value (log-rank, OS) B 0.04 0.85 D 0.71 0.62 E 0.00 0.92