A discrimination model by machine learning to avoid gastrectomy for early gastric cancer
Abstract Aim Gastrectomy is recommended for patients with early gastric cancer (EGC) because the possibility of lymph node metastasis (LNM) cannot be completely denied. The aim of this study was to develop a discrimination model to select patients who do not require surgery using machine learning. M...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-11-01
|
Series: | Annals of Gastroenterological Surgery |
Subjects: | |
Online Access: | https://doi.org/10.1002/ags3.12714 |
_version_ | 1797639370452238336 |
---|---|
author | Tsutomu Hayashi Ken Takasawa Takaki Yoshikawa Taiki Hashimoto Shigeki Sekine Takeyuki Wada Yukinori Yamagata Haruhisa Suzuki Seiichirou Abe Shigetaka Yoshinaga Yutaka Saito Nobuji Kouno Ryuji Hamamoto |
author_facet | Tsutomu Hayashi Ken Takasawa Takaki Yoshikawa Taiki Hashimoto Shigeki Sekine Takeyuki Wada Yukinori Yamagata Haruhisa Suzuki Seiichirou Abe Shigetaka Yoshinaga Yutaka Saito Nobuji Kouno Ryuji Hamamoto |
author_sort | Tsutomu Hayashi |
collection | DOAJ |
description | Abstract Aim Gastrectomy is recommended for patients with early gastric cancer (EGC) because the possibility of lymph node metastasis (LNM) cannot be completely denied. The aim of this study was to develop a discrimination model to select patients who do not require surgery using machine learning. Methods Data from 382 patients who received gastrectomy for gastric cancer and who were diagnosed with pT1b were extracted for developing a discrimination model. For the validation of this discrimination model, data from 140 consecutive patients who underwent endoscopic resection followed by gastrectomy, with a diagnosis of pT1b EGC, were extracted. We applied XGBoost to develop a discrimination model for clinical and pathological variables. The performance of the discrimination model was evaluated based on the number of cases classified as true negatives for LNM, with no false negatives for LNM allowed. Results Lymph node metastasis was observed in 95 patients (25%) in the development cohort and 11 patients (8%) in the validation cohort. The discrimination model was developed to identify 27 (7%) patients with no indications for additional surgery due to the prediction of an LNM‐negative status with no false negatives. In the validation cohort, 13 (9%) patients were identified as having no indications for additional surgery and no patients with LNM were classified into this group. Conclusion The discrimination model using XGBoost algorithms could select patients with no risk of LNM from patients with pT1b EGC. This discrimination model was considered promising for clinical decision‐making in relation to patients with EGC. |
first_indexed | 2024-03-11T13:15:52Z |
format | Article |
id | doaj.art-a8f0717fa6984d06993db12cd6e180b0 |
institution | Directory Open Access Journal |
issn | 2475-0328 |
language | English |
last_indexed | 2024-03-11T13:15:52Z |
publishDate | 2023-11-01 |
publisher | Wiley |
record_format | Article |
series | Annals of Gastroenterological Surgery |
spelling | doaj.art-a8f0717fa6984d06993db12cd6e180b02023-11-03T13:04:50ZengWileyAnnals of Gastroenterological Surgery2475-03282023-11-017691392110.1002/ags3.12714A discrimination model by machine learning to avoid gastrectomy for early gastric cancerTsutomu Hayashi0Ken Takasawa1Takaki Yoshikawa2Taiki Hashimoto3Shigeki Sekine4Takeyuki Wada5Yukinori Yamagata6Haruhisa Suzuki7Seiichirou Abe8Shigetaka Yoshinaga9Yutaka Saito10Nobuji Kouno11Ryuji Hamamoto12Department of Gastric Surgery National Cancer Center Hospital Tokyo JapanDivision of Medical AI Research and Development National Cancer Center Research Institute Tokyo JapanDepartment of Gastric Surgery National Cancer Center Hospital Tokyo JapanDepartment of Diagnostic Pathology National Cancer Center Hospital Tokyo JapanDepartment of Diagnostic Pathology National Cancer Center Hospital Tokyo JapanDepartment of Gastric Surgery National Cancer Center Hospital Tokyo JapanDepartment of Gastric Surgery National Cancer Center Hospital Tokyo JapanEndoscopy Division National Cancer Center Hospital Tokyo JapanEndoscopy Division National Cancer Center Hospital Tokyo JapanEndoscopy Division National Cancer Center Hospital Tokyo JapanEndoscopy Division National Cancer Center Hospital Tokyo JapanDivision of Medical AI Research and Development National Cancer Center Research Institute Tokyo JapanDivision of Medical AI Research and Development National Cancer Center Research Institute Tokyo JapanAbstract Aim Gastrectomy is recommended for patients with early gastric cancer (EGC) because the possibility of lymph node metastasis (LNM) cannot be completely denied. The aim of this study was to develop a discrimination model to select patients who do not require surgery using machine learning. Methods Data from 382 patients who received gastrectomy for gastric cancer and who were diagnosed with pT1b were extracted for developing a discrimination model. For the validation of this discrimination model, data from 140 consecutive patients who underwent endoscopic resection followed by gastrectomy, with a diagnosis of pT1b EGC, were extracted. We applied XGBoost to develop a discrimination model for clinical and pathological variables. The performance of the discrimination model was evaluated based on the number of cases classified as true negatives for LNM, with no false negatives for LNM allowed. Results Lymph node metastasis was observed in 95 patients (25%) in the development cohort and 11 patients (8%) in the validation cohort. The discrimination model was developed to identify 27 (7%) patients with no indications for additional surgery due to the prediction of an LNM‐negative status with no false negatives. In the validation cohort, 13 (9%) patients were identified as having no indications for additional surgery and no patients with LNM were classified into this group. Conclusion The discrimination model using XGBoost algorithms could select patients with no risk of LNM from patients with pT1b EGC. This discrimination model was considered promising for clinical decision‐making in relation to patients with EGC.https://doi.org/10.1002/ags3.12714discrimination modelearly gastric cancerlymph node metastasismachine learningsurgical indication |
spellingShingle | Tsutomu Hayashi Ken Takasawa Takaki Yoshikawa Taiki Hashimoto Shigeki Sekine Takeyuki Wada Yukinori Yamagata Haruhisa Suzuki Seiichirou Abe Shigetaka Yoshinaga Yutaka Saito Nobuji Kouno Ryuji Hamamoto A discrimination model by machine learning to avoid gastrectomy for early gastric cancer Annals of Gastroenterological Surgery discrimination model early gastric cancer lymph node metastasis machine learning surgical indication |
title | A discrimination model by machine learning to avoid gastrectomy for early gastric cancer |
title_full | A discrimination model by machine learning to avoid gastrectomy for early gastric cancer |
title_fullStr | A discrimination model by machine learning to avoid gastrectomy for early gastric cancer |
title_full_unstemmed | A discrimination model by machine learning to avoid gastrectomy for early gastric cancer |
title_short | A discrimination model by machine learning to avoid gastrectomy for early gastric cancer |
title_sort | discrimination model by machine learning to avoid gastrectomy for early gastric cancer |
topic | discrimination model early gastric cancer lymph node metastasis machine learning surgical indication |
url | https://doi.org/10.1002/ags3.12714 |
work_keys_str_mv | AT tsutomuhayashi adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT kentakasawa adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT takakiyoshikawa adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT taikihashimoto adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT shigekisekine adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT takeyukiwada adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT yukinoriyamagata adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT haruhisasuzuki adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT seiichirouabe adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT shigetakayoshinaga adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT yutakasaito adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT nobujikouno adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT ryujihamamoto adiscriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT tsutomuhayashi discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT kentakasawa discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT takakiyoshikawa discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT taikihashimoto discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT shigekisekine discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT takeyukiwada discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT yukinoriyamagata discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT haruhisasuzuki discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT seiichirouabe discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT shigetakayoshinaga discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT yutakasaito discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT nobujikouno discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer AT ryujihamamoto discriminationmodelbymachinelearningtoavoidgastrectomyforearlygastriccancer |