Hai-Sheng You,1,* Chun-Xia Gao,1,* Hai-Bin Wang,2 Sai-Sai Luo,1 Si-Ying Chen,1 Ya-Lin Dong,1 Jun Lyu,3 Tao Tian4 1Department of Pharmacy, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, Shaanxi, People’s Republic of China; 2Hangzhou Cognitive N&T. Co., Ltd, Hangzhou, Zhengjiang, People’s Republic of China; 3Clinical Research Center, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, Shaanxi, People’s Republic of China; 4Department of Oncology, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, Shaanxi, People’s Republic of China*These authors contributed equally to this workCorrespondence: Tao TianDepartment of Oncology, The First Affiliated Hospital of Xi’an Jiaotong University, No. 277 West Yanta Road, Xi’an, Shaanxi 710061, People’s Republic of ChinaTel +86-13572206784Fax +86-29-85324086Email tiantao0607@163.comJun LyuClinical Research Center, The First Affiliated Hospital of Xi’an Jiaotong University, No. 277 West Yanta Road, Xi’an, Shaanxi 710061, People’s Republic of ChinaTel +86 29 8532 3614Fax +86 29 8532 3473Email lujun2006@xjtu.edu.cnObjective: The disease complexity of metastatic non-small-cell lung cancer (mNSCLC) makes it difficult for physicians to make clinical decisions efficiently and accurately. The Watson for Oncology (WFO) system of artificial intelligence might help physicians by providing fast and precise treatment regimens. This study measured the concordance of the medical treatment regimens of the WFO system and actual clinical regimens, with the aim of determining the suitability of WFO recommendations for Chinese patients with mNSCLC.Methods: Retrospective data of mNSCLC patients were input to the WFO, which generated a treatment regimen (WFO regimen). The actual regimen was made by physicians in a medical team for patients (medical-team regimen). The factors influencing the consistency of the two treatment options were analyzed by univariate and multivariate analyses.Results: The concordance rate was 85.16% between the WFO and medical-team regimens for mNSCLC patients. Logistic regression showed that the concordance differed significantly for various pathological types and gene mutations in two treatment regimens. Patients with adenocarcinoma had a lower rate of “recommended” regimen than those with squamous cell carcinoma. There was a statistically significant difference in EGFR-mutant patients for “not recommended” regimens with inconsistency rate of 18.75%. In conclusion, the WFO regimen has 85.16% consistency rate with medical-team regimen in our treatment center. The different pathological type and different gene mutation markedly influenced the agreement rate of the two treatment regimens.Conclusion: WFO recommendations have high applicability to mNSCLC patients in our hospital. This study demonstrates that the valuable WFO system may assist the doctors better to determine the accurate and effective treatment regimens for mNSCLC patients in the Chinese medical setting.Keywords: metastatic non-small-cell lung cancer, Watson for Oncology, concordance, artificial intelligence, treatment recommendations
