Adequacy and Effectiveness of Watson For Oncology in the Treatment of Thyroid Carcinoma

Hyeok Jun Yun, Hee Jun Kim, Soo Young Kim, Yong Sang Lee, Chi Young Lim, Hang Seok Chang, Cheong Soo Park

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

Background: IBM’s Watson for Oncology (WFO) is an artificial intelligence tool that trains by acquiring data from the Memorial Sloan Kettering Cancer Center and learns from test cases and experts. This study aimed to analyze the adequacy and effectiveness of WFO in determining the treatment method for patients with thyroid carcinoma. Materials and Methods: We retrospectively enrolled 50 patients with thyroid cancer who underwent surgery in 2018 and entered their clinical data into WFO. The WFO treatment recommendations were compared with the surgical procedures and recommended treatments performed according to the Korean Thyroid Endocrine Surgery Association guidelines. Results: The overall concordance rate between WFO-recommended treatments and actual surgical treatments was 48%, and for patients with stage I, II, and III disease, these rates were 52.4, 50, and 16.7%, respectively. A lower concordance rate was observed with respect to treatment for advanced thyroid cancer. Conclusion: WFO is a useful clinical aid but must be used with caution. A surgeon’s decision takes precedence over WFO recommendations in the treatment of advanced thyroid cancer.

Original languageEnglish
Article number585364
JournalFrontiers in Endocrinology
Volume12
DOIs
Publication statusPublished - 2021 Mar 3

Bibliographical note

Publisher Copyright:
© Copyright © 2021 Yun, Kim, Kim, Lee, Lim, Chang and Park.

All Science Journal Classification (ASJC) codes

  • Endocrinology, Diabetes and Metabolism

Fingerprint

Dive into the research topics of 'Adequacy and Effectiveness of Watson For Oncology in the Treatment of Thyroid Carcinoma'. Together they form a unique fingerprint.

Cite this