Cancer Research and Treatment

Original Articles

Gastrointestinal cancer

A Machine Learning Risk Prediction Model for Gastric Cancer with SHapley Additive exPlanations: Bomi Park, Chung Ho Kim, Jae Kwan Jun, Mina Suh, Kui Son Choi, Il Ju Choi, Hyun Jin Oh; Cancer Res Treat. 2025;57(3):821-829. Published online December 16, 2024; DOI: https://doi.org/10.4143/crt.2024.843

Abstract PDF Supplementary Material PubReader ePub

Purpose
Gastric cancer (GC) prediction models hold potential for enhancing early detection by enabling the identification of high-risk individuals, facilitating personalized risk-based screening, and optimizing the allocation of healthcare resources.
Materials and Methods
In this study, we developed a machine learning-based GC prediction model utilizing data from the Korean National Health Insurance Service, encompassing 10,515,949 adults who had not been diagnosed with GC and underwent GC screening during 2013-2014, with a follow-up period of 5 years. The cohort was divided into training and test datasets at an 8:2 ratio, and class imbalance was mitigated through random oversampling.
Results
Among various models, logistic regression demonstrated the highest predictive performance, with an area under the receiver operating characteristic curve (AUC) of 0.708, which was consistent with the AUC obtained in external validation (0.669). Importantly, the outcomes were robust to missing data imputation and variable selection. The SHapley Additive exPlanations (SHAP) algorithm enhanced the explainability of the model, identifying advancing age, being male, Helicobacter pylori infection, current smoking, and a family history of GC as key predictors of elevated risk.
Conclusion
This predictive model could significantly contribute to the early identification of individuals at elevated risk for GC, thereby enabling the implementation of targeted preventive strategies. Furthermore, the integration of noninvasive and cost-effective predictors enhances the clinical utility of the model, supporting its potential application in routine healthcare settings.

Citations

Citations to this article as recorded by

Liver cancer risk stratification using deep learning on nationwide longitudinal health screening data: a retrospective cohort study
Yewon Choi, Sungmin Cho, Changdai Gu, Chungho Kim, Bomi Park, Hwiyoung Kim
BMC Medical Informatics and Decision Making.2026;[Epub] CrossRef
Development and validation of a novel blood-based biomarker for gastric cancer triage in chronic dyspepsia
Minji Seo, Ka Man Cheung, Serene J. L. Lam, Peter Y. M. Woo, Winnie W. Y. Sung, James C. H. Chow, Ada S. M. Yip, Stephen K. K. Ng, Martin S. C. Lee, Henry H. W. Liu, Daisy M. Y. Kan, Sau Shan Kao, Harry H. Y. Yiu, David C. C. Lam
npj Digital Medicine.2026;[Epub] CrossRef
Explainable machine learning model for predicting acute exacerbations of COPD combining sarcopenia index and traditional risk factors: A retrospective single-center exploratory study
Ai-Bin Zhang, Li-Wen Zhou, Yu-Fen An, Qing-Qing Qin, Jian-Tong Wei, Hao Chen
Chronic Respiratory Disease.2026;[Epub] CrossRef
Advancing Gastrointestinal Cancer Risk Prediction With Patient-Centered Machine Learning: Machine Learning Modeling Study
Daina Baublyte, Jeonghee Lee, Madhawa Gunathilake, Jeongseon Kim
JMIR Medical Informatics.2026; 14: e78931. CrossRef
Realizing personalized prediction for the reversal of chronic hepatitis B-associated liver fibrosis through machine learning
Shi-Cai Liu, Zi-Wen Wang, Han Zhang
World Journal of Gastroenterology.2026;[Epub] CrossRef
Development and validation of a prediction model for myelosuppression in lung cancer patients after platinum-based doublet chemotherapy: a multifactorial analysis approach
Xueyan Li
American Journal of Cancer Research.2025; 15(2): 470. CrossRef
Development and Validation of the Early Gastric Carcinoma Prediction Model in Post-Eradication Patients with Intestinal Metaplasia
Wulian Lin, Guanpo Zhang, Hong Chen, Weidong Huang, Guilin Xu, Yunmeng Zheng, Chao Gao, Jin Zheng, Dazhou Li, Wen Wang
Cancers.2025; 17(13): 2158. CrossRef
Field-Scale Maize Yield Estimation Using Remote Sensing with the Integration of Agronomic Traits
Shuai Bao, Yiang Wang, Shinai Ma, Huanjun Liu, Xiyu Xue, Yuxin Ma, Mingcong Zhang, Dianyao Wang
Agriculture.2025; 15(17): 1834. CrossRef
Ensemble Transfer Learning for Gastric Cancer Prediction Using Electronic Health Records in a Data-Scarce Single-Hospital Setting
Hyon Hee Kim, Ji Yeon Han, Yae Bin Lim, Young Seo Lim, Seung-In Seo, Kyung Joo Lee, Woon Geon Shin
Applied Sciences.2025; 15(23): 12428. CrossRef
Cross-Cancer Transfer Learning for Gastric Cancer Risk Prediction from Electronic Health Records
Daeyoung Hong, Jiung Kim, Jiyong Jung
Diagnostics.2025; 15(24): 3175. CrossRef
Enhancing radiotherapy for gastric cancer: A systematic review on the role of predictive models in clinical decision-making
Sh. Chen, Sh. Wei, Y. Wang, L. Chen, Zh. Lin
International Journal of Radiation Research.2025; 23(4): 1101. CrossRef

8,260 View
249 Download
10 Web of Science
11 Crossref

Overview of the National Cancer Screening Program for Colorectal Cancer in Korea over 14 Years (2004-2017): Bomi Park, Eun Young Her, Kyeongmin Lee, Fatima Nari, Jae Kwan Jun, Kui Son Choi, Mina Suh; Cancer Res Treat. 2023;55(3):910-917. Published online March 8, 2023; DOI: https://doi.org/10.4143/crt.2022.1432

Abstract PDF Supplementary Material PubReader ePub

Purpose
This study aimed to evaluate the participation and follow-up test compliance rates and key performance indicators of the National Cancer Screening Program (NCSP) for colorectal cancer (CRC) from 2004 to 2017.
Materials and Methods
The overall outcomes of the NCSP for CRC were analyzed using the NCSP data collected from 2004 to 2017 and the Korean Central Cancer Registry for CRC from 2005 to 2017. We cross-sectionally analyzed the participation and follow-up test compliance rates and performance indicators for each year. The trend of participation rates as an annual percentage change was assessed, and other statistical analyses were performed.
Results
The screening participation rates increased from 7.3% in 2004 to 30.5% in 2017. Additionally, the screening rates were higher among individuals aged 60-69 years and National Health Insurance Service beneficiaries of low-income status. However, the adherence to the follow-up test decreased from 63% in 2004 to 32% in 2017. The follow-up tests using the double-contrast barium enema method decreased from 42.2% in 2004 to 0.3% in 2017. However, follow-up tests by colonoscopy increased from 21.0% in 2004 to 31.8% in 2017. Furthermore, the positivity, false-positive, and interval CRC rates decreased, whereas the specificity increased from 2004 to 2016, indicating improved performance of CRC.
Conclusion
The participation rates and performance of the NCSP for CRC have steadily improved, whereas adherence to follow-up tests has decreased. Additionally, there is a rapid growth in colonoscopy volume as a follow-up test. Continued efforts are required to improve the follow-up rates.

Citations

Citations to this article as recorded by

Stool DNA-based SDC2 Methylation Test for the Screening of Colorectal Neoplasia in an Asymptomatic, Average-Risk Population
Hyoung Il Choi, Jae Myung Cha, Young Sang Kim, Dae Hyeon Cho, Han Ju Pack, Soo-Young Na, Ji Hye Kim, Hyun Gun Kim, Young-Jin Park, Hye Jung Kwon, Kyeong Ok Kim, Geon Ho Lee, Yoo Jin Lee
The Korean Journal of Gastroenterology.2026; 86(1): 43. CrossRef
Detección precoz del cáncer colorrectal
Alejandro J. Zárate, Suraj Samtani, Roberto Salas, Camila Leiva
Revista Médica Clínica Las Condes.2026; 37(2): 147. CrossRef
Emerging trends in the global burden of colorectal cancer
David J. Lee, Aparna Parikh, Bhawna Sirohi, Yin Cao, Andrew T. Chan
Nature Reviews Clinical Oncology.2026; 23(8): 569. CrossRef
Psoriasis and Risk of Colorectal Cancer: A Nationwide Population-Based Cohort Study in Korea
Kyeong Min Han, Dae Myoung Yoo, Ho Suk Kang, Hyo Geun Choi, Joo-Hee Kim, Nan Young Kim, Kyueng-Whan Min, Mi Jung Kwon
Diseases.2026; 14(6): 200. CrossRef
A Validation Study of Methylated Syndecan-2 in Stool DNA for the Detection of Colorectal Cancer
Hyoung Il Choi, Yoon Dae Han, Jae Myung Cha, Nam Kyu Kim
Diagnostics.2026; 16(12): 1901. CrossRef
From “When” to “Ready”: Preparing for Primary Colonoscopy in the Korean National Colorectal Cancer Screening Program
Tae Hee Lee
Journal of Korean Medical Science.2026;[Epub] CrossRef
CRC Screening, A Long Way Off
Fei Chen, Cheng Luo, Song Zhao
Diseases of the Colon & Rectum.2026; 69(9): 2356. CrossRef
Trends in Cancer-Screening Rates in Korea: Findings from the National Cancer Screening Survey, 2004-2023
EunKyo Kang, Kui Son Choi, Jae Kwan Jun, Yeol Kim, Hyeon Ji Lee, Chang Kyun Choi, Tae Hee Kim, Sun Hwa Lee, Mina Suh
Cancer Research and Treatment.2025; 57(1): 28. CrossRef
Association Between Suicidal Ideation and Cancer Screening Uptake: Results from Middle-Aged and Older Adults in Korea
Seong-Uk Baek, Jin-Ha Yoon
Cancers.2025; 17(6): 956. CrossRef
Current Status of the National Cancer Screening Program in Korea: History, Achievements, and Future Directions
Kyeongmin Lee, Mina Suh, Kui Son Choi
Journal of Preventive Medicine and Public Health.2025; 58(4): 337. CrossRef
Serum bilirubin levels and risk of colorectal cancer in Korean adults: results from the Korean Genome and Epidemiology Study-Health Examinee (KoGES-HEXA) Cohort Study
Hwayoung Noh, Jeeyoo Lee, Nazlisadat Seyed Khoei, Laia Peruchet-Noray, Daehee Kang, Beatrice Fervers, Karl-Heinz Wagner, Aesun Shin, Heinz Freisling
British Journal of Cancer.2024; 131(10): 1635. CrossRef
Association between Endoscopist Volume and Interval Cancers after Colonoscopy: Results from the National Colorectal Cancer Screening Program in Korea
Dong Jun Kim, Nan-He Yoon, Jae Kwan Jun, Mina Suh, Sunhwa Lee, Seongju Kim, Ji Eun Kim, Hooyeon Lee
Cancer Research and Treatment.2024; 56(4): 1164. CrossRef
Effectiveness of the Korean National Cancer Screening Program in Reducing Colorectal Cancer Mortality
Hyeon Ji Lee, Kyeongmin Lee, Byung Chang Kim, Jae Kwan Jun, Kui Son Choi, Mina Suh
Cancers.2024; 16(24): 4278. CrossRef
Effect of electroacupuncture on discomfort in patients undergoing colonoscopy: protocol for a multicentre, randomised, controlled clinical trial
Xiangyu Sun, Liyue Lu, Yongqiang Wang, Chunchun Wang, Chao Lin, Kuangdi Xu, Yue Yong, Wenting Chen, Jiangang Song
BMJ Open.2024; 14(12): e084628. CrossRef
National cancer screening program for colorectal cancer in Korea
Seung Min Baik, Ryung-Ah Lee
Annals of Surgical Treatment and Research.2023; 105(6): 333. CrossRef

8,380 View
197 Download
14 Web of Science
15 Crossref

First
Prev
Page of 1
Next
Last

Search