Machine learning-based prediction of 5-year survival in diffuse-type gastric cancer patients from Harbin

Abstract

Objective: Globally, over 1.1 million new cases of gastric cancer (GC) were diagnosed in 2020, with approximately 800,000 related deaths. GC exhibits significant regional variability, particularly in extremely cold regions, where unique climate conditions and lifestyle factors may impact disease progression and prognosis. This study aimed to predict the 5-year all-cause mortality of patients with diffuse gastric cancer (DGC) living in such regions using multiple machine learning algorithms. Methods: We retrospectively analyzed 249 DGC cases and developed six machine learning models—extreme gradient boosting (XGBoost), logistic regression, decision tree, support vector machine, k-nearest neighbors, and random forest. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), precision-recall curve, F1 score, and Brier score. Results: The XGBoost model achieved the highest F1 scores (0.830 and 0.781, respectively) and the second-best Brier score (0.172). Conclusion: This study highlights the potential of machine learning approaches to enhance prognostic assessment in GC. Although limited by single-center data and the absence of multi-center external validation, the results offer valuable insights that may inform future research and guide risk-stratified management strategies in extremely cold regions.

Keywords

gastric cancer / XGBoost / cold region

Acknowledgements

The authors gratefully acknowledge the Harbin Medical University Cancer Hospital for providing the clinical data used in this study.

Research ethics

This study was conducted in accordance with the principles of the Declaration of Helsinki and was approved by the Medical Ethics Committee of Harbin Medical University Cancer Hospital (KY2021-09).

Informed consent

Informed consent was obtained from all patients prior to treatment.

Author contributions

Zhang Y L and Wang C designed and conceptualized the study, drafted the manuscript, and contributed equally to this work. Zhang Y L, Wang C, Fan J L and Gao H Y were responsible for data collection. Zhu X Q and Song H B conducted the final critical review of the manuscript. All authors contributed to the article and approved the final submitted version.

Use of large language models, AI and machine learning tools

No large language models or AI-assisted writing tools were used in the preparation of this manuscript.

Conflict of interests

All authors declare that they have no conflicts of interest related to this study.

Research funding

This research was supported by the Fund for Independent Innovation of Hypoglycemic Drugs from Basic Research to Clinical Application (070500020373) and Heilongjiang Provincial Natural Science Foundation (PL2025H169).

Data availability

Patient data were stored in the Gastric Cancer Information Management System v1.2, developed by the Harbin Medical University Cancer Hospital (Copyright No. 2013SR087424, http://www.sgihmu.com).

References

[1] No authors listed. Erratum: Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 2020; 70(4): 313.

[2] Brenner H , Rothenbacher D , Arndt V . Epidemiology of stomach cancer. Methods Mol Biol, 2009; 472: 467-477.

[3] Thrift A P , Wenker T N , El—Serag H B . Global burden of gastric cancer: epidemiological trends, risk factors, screening and prevention. Nat Rev Clin Oncol, 2023; 20(5): 338-349.

[4] Hartgrink H H , van de Velde C J , Putter H , et al. Extended lymph node dissection for gastric cancer: who may benefit? Final results of the randomized Dutch gastric cancer group trial. J Clin Oncol, 2004; 22(11): 2069-2077.

[5] Kinoshita T , Uyama I , Terashima M , et al. Long—term outcomes of laparoscopic versus open surgery for clinical stage II/III gastric cancer: a multicenter cohort study in Japan (LOC—A Study). Ann Surg, 2019; 269(5): 887-894.

[6] Liu F , Huang C , Xu Z , et al. Morbidity and mortality of laparoscopic vs open total gastrectomy for clinical stage i gastric cancer: the CLASS02 multicenter randomized clinical trial. JAMA Oncol, 2020; 6(10): 1590-1597.

[7] Siegel R L , Miller K D , Jemal A . Cancer statistics, 2016. CA Cancer J Clin, 2016; 66(1): 7-30.

[8] Lauren P A . The two histological main types of gastric carcinoma: diffuse and so—called intestinal—type carcinoma: an attempt at a histo—clinical classification. Acta Pathol Microbiol Scand, 1965; 64(1): 31-49.

[9] Chen Y C , Fang W L , Wang R F , et al. Clinicopathological variation of lauren classification in gastric cancer. Pathol Oncol Res, 2016; 22(1): 197-202.

[10] Qiu M Z , Cai M Y , Zhang D S , et al. Clinicopathological characteristics and prognostic analysis of Lauren classification in gastric adenocarcinoma in China. J Transl Med, 2013; 11: 58.

[11] Li R , Zhang H , Cao Y , et al. Lauren classification identifies distinct prognostic value and functional status of intratumoral CD8(+) T cells in gastric cancer. Cancer Immunol Immunother, 2020; 69(7): 1327-1336.

[12] Chandra R , Balachandar N , Wang S , et al. The changing face of gastric cancer: epidemiologic trends and advances in novel therapies. Cancer Gene Ther, 2021; 28(5): 390-399.

[13] Richa , Sharma N , Sageena G J T M C . Dietary factors associated with gastric cancer—a review. Transl Med Commun, 2022; 7(1): 7.

[14] Huang B , Liu J , Ding F , et al. Epidemiology, risk areas and macro determinants of gastric cancer: a study based on geospatial analysis. Int J Health Geogr, 2023; 22(1): 32.

[15] Deo R C . Machine Learning in Medicine. Circulation, 2015; 132(20): 1920-1930.

[16] Komura D , Ishikawa S . Machine learning approaches for pathologic diagnosis. Virchows Arch, 2019; 475(2): 131-138.

[17] Tran N K , Albahra S , May L , et al. Evolving applications of artificial intelligence and machine learning in infectious diseases testing. Clin Chem, 2021; 68(1): 125-133.

[18] Gao Y , Xin L , Lin H , et al. Machine learning—based automated sponge cytology for screening of oesophageal squamous cell carcinoma and adenocarcinoma of the oesophagogastric junction: a nationwide, multicohort, prospective study. Lancet Gastroenterol Hepatol, 2023; 8(5): 432-445.

[19] AlJame M , Ahmad I , Imtiaz A , et al. Ensemble learning model for diagnosing COVID—19 from routine blood tests. Inform Med Unlocked, 2020; 21: 100449.

[20] Okada S , Ohzeki M , Taguchi S . Efficient partition of integer optimization problems with one—hot encoding. Sci Rep, 2019; 9(1): 13036.

[21] Yuan K C , Tsai L W , Lee K H , et al. The development an artificial intelligence algorithm for early sepsis diagnosis in the intensive care unit. Int J Med Inform, 2020; 141: 104176.

[22] Nick T G , Campbell K M . Logistic regression. Methods Mol Biol, 2007; 404: 273-301.

[23] Uddin S , Khan A , Hossain M E , et al. Comparing different supervised machine learning algorithms for disease prediction. BMC Med Inform Decis Mak, 2019; 19(1): 281.

[24] Jiang H , Mao H , Lu H , et al. Machine learning—based models to support decision—making in emergency department triage for patients with suspected cardiovascular disease. Int J Med Inform, 2021; 145: 104326.

[25] Youssef Ali Amer A . Global—local least—squares support vector machine (GLocal—LS—SVM). PLoS One, 2023; 18(4): e0285131.

[26] Salvador—Meneses J , Ruiz—Chavez Z , Garcia—Rodriguez J . Compressed kNN: K—nearest neighbors with data compression. Entropy (Basel), 2019; 21(3): 234.

[27] Park J C , Lee Y C , Kim J H , et al. Clinicopathological aspects and prognostic value with respect to age: an analysis of 3 362 consecutive gastric cancer patients. J Surg Oncol, 2009; 99(7): 395-401.

[28] Fang C , Wang W , Deng J Y , et al. Proposal and validation of a modified staging system to improve the prognosis predictive performance of the 8th AJCC/UICC pTNM staging system for gastric adenocarcinoma: amulticenter study with external validation. Cancer Commun (Lond), 2018; 38(1): 67.

[29] Wang Y , Zhang J , Guo S , et al. Implication of lymph node staging in migration and different treatment strategies for stage T2N0M0 and T1N1M0 resected gastric cancer: a SEER population analysis. Clin Transl Oncol, 2019; 21(11): 1499-1509.

[30] Bang C S , Ahn J Y , Kim J H , et al. Establishing machine learning models to predict curative resection in early gastric cancer with undifferentiated histology: development and usability study. J Med Internet Res, 2021; 23(4): e25053.

[31] Zhou C , Hu J , Wang Y , et al. A machine learning—based predictor for the identification of the recurrence of patients with gastric cancer after operation. Sci Rep, 2021; 11(1): 1571.

[32] Zhou C , Wang Y , Ji M H , et al. Predicting peritoneal metastasis of gastric cancer patients based on machine learning. Cancer Control, 2020; 27(1): 1073274820968900.

[33] Turkki R , Byckhov D , Lundin M , et al. Breast cancer outcome prediction with tumour tissue images and machine learning. Breast Cancer Res Treat, 2019; 177(1): 41-52.

[34] Wentzensen N , Lahrmann B , Clarke M A , et al. Accuracy and efficiency of deep—learning—based automation of dual stain cytology in cervical cancer screening. J Natl Cancer Inst, 2021; 113(1): 72-79.

[35] Gehrung M , Crispin—Ortuzar M , Berman A G , et al. Triage—driven diagnosis of Barrett's esophagus for early detection of esophageal adenocarcinoma using deep learning. Nat Med, 2021; 27(5): 833-841.

[36] Wang L , Wang X , Chen A , et al. Prediction of type 2 diabetes risk and its effect evaluation based on the XGBoost model. Healthcare (Basel), 2020; 8(3): 247.

[37] Filik L . Ulcer size and gastric cancer prognosis. Dig Surg, 2010; 27(3): 248-249.

[38] Kemi N , Ylitalo O , Väyrynen J P , et al. Tertiary lymphoid structures and gastric cancer prognosis. Apmis, 2023; 131(1): 19-25.