Abstract
Development of an artificial intelligence algorithm for adjuvant chemotherapy based on a nationwide registry of patients with gastric cancer by the Japanese Gastric Cancer Association (JGCA).
Author
person
Yasuhide Yamada
National Center for Global Health and Medicine, Tokyo, Japan
info_outline
Yasuhide Yamada, Ami Kamada, Yoshinori Kabeya, Sumito Yoshida, Hitoshi Harada, Naoki Urakawa, Shingo Kanaji, Yuma Nakamura, Kengo Nagashima, HIROYA TAKEUCHI, Yuichiro Doki, Yuko Kitagawa, Yasuhiro Kodera, Yoshihiro Kakeji
Full text
Authors
person
Yasuhide Yamada
National Center for Global Health and Medicine, Tokyo, Japan
info_outline
Yasuhide Yamada, Ami Kamada, Yoshinori Kabeya, Sumito Yoshida, Hitoshi Harada, Naoki Urakawa, Shingo Kanaji, Yuma Nakamura, Kengo Nagashima, HIROYA TAKEUCHI, Yuichiro Doki, Yuko Kitagawa, Yasuhiro Kodera, Yoshihiro Kakeji
Organizations
National Center for Global Health and Medicine, Tokyo, Japan, Healthcare & Life Sciences Services, IBM Japan, Ltd., Tokyo, Japan, Japan Medical Association Research Institute, Tokyo, Japan, Kobe University, Kobe, Japan, Biostatistics Unit, Clinical and Translational Research Center, Keio University Hospital, Tokyo, Japan, Hamamatsu University School of Medicine, Hamamatsu, Japan, Osaka University Graduate School of Medicine, Osaka, Japan, Keio University School of Medicine, Tokyo, Japan, Nagoya University School of Medicine, Nagoya, Japan, Department of Surgery, Division of Gastrointestinal Surgery, Kobe University Graduate School of Medicine, Kobe, Japan
Abstract Disclosures
Research Funding
Other
Cross-ministerial Strategic Innovation Promotion Program, Cabinet Office, Japan
Background:
Recent marked advances in machine learning have led to expectations of the clinical application of artificial intelligence (AI) to support medical care.
Methods:
A survival analysis model which consisted of 31 covariates was adopted for AI algorithms using machine learning and these were constructed using clinical data sets for training. The performance of AI algorithms was evaluated in order to determine the optimal chemotherapy including surgery alone without any adjuvant chemotherapy with the highest survival rate for each patient. This involved using clinical data for verification to compare survival of an AI-recommended treatment group, for which therapy recommended by AI was actually administered, with an AI-deprecated group, for which therapy recommended by AI was not administered.
Results:
The clinical characteristics of 23653 patients and treatment are described in the Table from 2011 to 2018 in a nationwide registry of gastric cancer patients in Japan by the Japanese Gastric Cancer Association and were made available for this study. S-1 monotherapy was used the most frequently of all adjuvant chemotherapy in this study. We used the "restricted mean overall survival time" (RMST) of all the patients as metrics. The RMST in the AI-recommended and the AI-deprecated groups were 51.4 and 47.5 months, respectively. Patient data for the verification were matched baseline characteristics by the propensity score. This model predicted effectively overall survival after gastrectomy. The RMST of over 80 years old patients were 43.9 in the AI-recommended and 38.3 months in the AI-deprecated, respectively. This AI algorithm recommended adjuvant S-1 more frequently for patients with higher age, male, American Society of Anesthesiologists – physical status 2, Eastern Cooperative Oncology Group performance status 1, pT3/pT4, pN2/pN3, more than the upper normal limit of preoperative blood urea nitrogen, macroscopic types 2/3, differentiated adenocarcinoma, Roux-en-Y reconstruction, and Clavien-Dindo classification grade II/III. The RMST for pStage IIA/IIB/IIIA/IIIB/IIIC were 55.7/53.9/50.3/45.7/42.2 months in the AI-recommended and 55.1/50.7/43.9/36.9/32.0 months in the deprecated. This AI algorithm showed a higher survival rate in pStage III patients particularly.
Conclusions:
The AI algorithm could readily be integrated into clinical practice to choose adequate adjuvant chemotherapy for each patient based on each patient's baseline data because it trained and verified the nationwide registry has good predictive performance.
No. of patients (n=23653)
%
Sex, male
16390
69.3
Age
<70
10477
44.3
70 – 80
9602
40.6
80>
3574
15.1
pStage
IA/IB
90/5397
23.2
IIA/IIB
4760/3672
35.6
IIIA/IIIB/IIIC
4224/2681/1351
34.9
Adjuvant chemotherapy
None
13614
57.6
S-1
9352
39.5
Others
697
2.9
16 organizations
1 drug
1 target
Organization
National Center for Global Health and MedicineOrganization
Tokyo, JapanOrganization
Healthcare & Life Sciences ServicesOrganization
IBM Japan, Ltd.Organization
Japan Medical Association Research InstituteOrganization
Kobe UniversityOrganization
Kobe, JapanOrganization
Biostatistics Unit, Clinical and Translational Research Center, Keio University HospitalOrganization
Hamamatsu University School of MedicineOrganization
Hamamatsu, JapanOrganization
Osaka University Graduate School of MedicineOrganization
Osaka, JapanOrganization
Keio University School of MedicineOrganization
Nagoya University School of MedicineOrganization
Nagoya, JapanOrganization
Department of Surgery, Division of Gastrointestinal Surgery, Kobe University Graduate School of MedicineDrug
S-1Target
S-1