Diagnostic study of machine learning model based on combinatorial optimization to predict postoperative infectious complications of gastric cancer_Chinese Journal of Evidence-Based Medicine

Authors：

TIAN Yuan ¹ , LIN Zhihao ¹ , LI Rui ¹ , WANG Guanlong ¹ , LI Hongxia ² ,  HE Lei ¹

1. Gastrointestinal Surgery of the Third Affiliated Hospital of Anhui Medical University, Hefei 230061, P. R. China;
2. Oncology Department of the Third Affiliated Hospital of Anhui Medical University, Hefei 230061, P. R. China;

Corresponding author：

HE Lei, Email: hfyysoncology@163.com

Keywords：

Gastric cancer; Machine learning; MGA-XGBoost; Postoperative infectious complications

DOI：

10.7507/1672-2531.202310069

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To explore the application of combined optimized machine learning algorithm for predicting the risk model of postoperative infectious complications of gastric cancer and to compare the accuracy with other algorithms, so as to find reliable biomarkers for early diagnosis of postoperative infection of gastric cancer. Methods The clinical data of 420 patients with gastric cancer at the Third Affiliated Hospital of Anhui Medical University from May 2018 to April 2023 were retrospectively analyzed and the patients were randomly divided into training set and validation set. Univariate analysis was used to determine the risk factors of postoperative infectious complications. Six conventional machine learning models are constructed using the training set: linear regression, random forest, SVM, BP, LGBM, XGBoost, and MGA-XGBoost model. The validation set was used to evaluate the seven models through evaluation indicators such as ACC, precision, ROC and AUC. Results Postoperative infectious complications were significantly correlated with age, operation time, diabetes, extent of resection, combined resection, stage, preoperative albumin, perioperative blood transfusion, preoperative PNI, LCR and LMR. Among the seven machine learning models, the MGA-XGBoost model performed best. Among the seven machine learning models, the MGA-XGBoost model performed best, with AUC of 0.936, ACC of 0.889, recall of 0.6, F1-score of 0.682, and precision of 0.79 on the validation set. Diabetes had the greatest influence on the internal structure of the model. Conclusion This study proves that the MGA-XGBoost model incorporating comprehensive inflammation indicators can predict postoperative infectious complications in patients with gastric cancer.

Citation： TIAN Yuan, LIN Zhihao, LI Rui, WANG Guanlong, LI Hongxia, HE Lei. Diagnostic study of machine learning model based on combinatorial optimization to predict postoperative infectious complications of gastric cancer. Chinese Journal of Evidence-Based Medicine, 2024, 24(9): 993-1003. doi: 10.7507/1672-2531.202310069 Copy

1.	Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 2021, 71(3): 209-249.
2.	Yang W, Chen X, Zhang P, et al. Procalcitonin as an early predictor of intra-abdominal infections following gastric cancer resection. J Surg Res, 2021, 258: 352-361.
3.	Xiao Y, Wei G, Ma M, et al. Association among prognostic nutritional index, post-operative infection and prognosis of stage II/III gastric cancer patients following radical gastrectomy. Eur J Clin Nutr, 2022, 76(10): 1449-1456.
4.	Maezawa Y, Aoyama T, Ju M, et al. The impact of severe infectious complications on long-term prognosis for gastric cancer. Anticancer Res, 2020, 40(7): 4067-4074.
5.	Greten FR, Grivennikov SI. Inflammation and cancer: triggers, mechanisms, and consequences. Immunity, 2019, 51(1): 27-41.
6.	Ding P, Guo H, Sun C, et al. Combined systemic immune-inflammatory index (SII) and prognostic nutritional index (PNI) predicts chemotherapy response and prognosis in locally advanced gastric cancer patients receiving neoadjuvant chemotherapy with PD-1 antibody sintilimab and XELOX: a prospective study. BMC Gastroenterol, 2022, 22(1): 121.
7.	Mouchli M, Reddy S, Gerrard M, et al. Usefulness of neutrophil-to-lymphocyte ratio (NLR) as a prognostic predictor after treatment of hepatocellular carcinoma. Ann Hepatol, 2021, 22: 100249.
8.	Okugawa Y, Toiyama Y, Yamamoto A, et al. Lymphocyte-C-reactive protein ratio as promising new marker for predicting surgical and oncological outcomes in colorectal cancer. Ann Surg, 2020, 272(2): 342-351.
9.	Wang C, Huang HZ, He Y, et al. A new nomogram based on early postoperative NLR for predicting infectious complications after gastrectomy. Cancer Manag Res, 2020, 12: 881-889.
10.	姚晶, 李鸿, 夏东. 预后营养指数对原发性肝癌肝切除术后感染性并发症的预测价值. 现代肿瘤医学, 2022, 30(16): 2961-2964.
11.	Nudel J, Bishara AM, de Geus SWL, et al. Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery: an analysis of the MBSAQIP database. Surg Endosc, 2021, 35(1): 182-191.
12.	中华人民共和国卫生部. 医院感染诊断标准(试行). 中华医学杂志, 2001, 81(5): 314-320.
13.	Chen C, Yang D, Gao S, et al. Development and performance assessment of novel machine learning models to predict pneumonia after liver transplantation. Respir Res, 2021, 22(1): 94.
14.	Jiang J, Pan H, Li M, et al. Predictive model for the 5-year survival status of osteosarcoma patients based on the SEER database and XGBoost algorithm. Sci Rep, 2021, 11(1): 5542.
15.	Tey SF, Liu CF, Chien TW, et al. Predicting the 14-day hospital readmission of patients with pneumonia using artificial neural networks (ANN). Int J Environ Res Public Health, 2021, 18(10): 5110.
16.	Ma RN, He YX, Bai FP, et al. Machine learning model for predicting acute respiratory failure in individuals with moderate-to-severe traumatic brain injury. Front Med (Lausanne), 2021, 8: 793230.
17.	Bradley M, Dente C, Khatri V, et al. Advanced modeling to predict pneumonia in combat trauma patients. World J Surg, 2020, 44(7): 2255-2262.
18.	Xue B, Li D, Lu C, et al. Use of machine learning to develop and evaluate models using preoperative and intraoperative data to identify risks of postoperative complications. JAMA Netw Open, 2021, 4(3): e212240.
19.	Xi X, Yang MX, Wang XY, et al. Predictive value of prognostic nutritional index on infection after radical gastrectomy: a retrospective study. J Gastrointest Oncol, 2022, 13(2): 569-580.
20.	茅伟达, 凃威伟, 孙筱虹. 胃癌根治术后感染的病原菌及影响因素. 中华医院感染学杂志, 2020, 30(14): 2179-2183.
21.	Kunisaki C, Sato S, Tsuchiya N, et al. Systemic review and meta-analysis of impact of splenectomy for advanced gastric cancer. In Vivo, 2020, 34(6): 3115-3125.
22.	Wei C, Gu A, Almeida ND, et al. Operation time effect on rates of perioperative complications after operative treatment of distal radius fractures. J Orthop, 2021, 24: 82-85.
23.	夏初, 许向华, 黄怡. 糖尿病合并侵袭性肺真菌感染的研究进展. 中华结核和呼吸杂志, 2021, 44(2): 128-131.
24.	永佳, 韩晓丽, 永雪薇, 等. 2型糖尿病患者并发尿路感染的病原菌分布、氧化应激指标检测及相关因素分析. 中国病原生物学杂志, 2019, 14(10): 1219-1222.
25.	Okabayashi T, Maeda H, Sun ZL, et al. Perioperative insulin therapy using a closed-loop artificial endocrine pancreas after hepatic resection. World J Gastroenterol, 2009, 15(33): 4116-4121.
26.	Yoshida R, Gohara S, Sakata J, et al. Onodera's prognostic nutritional index correlates with tumor immune environment and survival in patients with oral squamous cell carcinoma undergoing chemoradiotherapy. Transl Oncol, 2020, 13(12): 100850.
27.	Ostroumov D, Fekete-Drimusz N, Saborowski M, et al. CD4 and CD8 T lymphocyte interplay in controlling tumor growth. Cell Mol Life Sci, 2018, 75(4): 689-713.
28.	Jiang P, Li X, Wang S, et al. Prognostic significance of PNI in patients with pancreatic head cancer undergoing laparoscopic pancreaticoduodenectomy. Front Surg, 2022, 9: 897033.
29.	Bailón-Cuadrado M, Pérez-Saborido B, Sánchez-González J, et al. Prognostic nutritional index predicts morbidity after curative surgery for colorectal cancer. Cir Esp (Engl Ed), 2019, 97(2): 71-80.
30.	Matsuda T, Umeda Y, Matsuda T, et al. Preoperative prognostic nutritional index predicts postoperative infectious complications and oncological outcomes after hepatectomy in intrahepatic cholangiocarcinoma. BMC Cancer, 2021, 21(1): 708.
31.	Lee JY, Kim HI, Kim YN, et al. Clinical significance of the prognostic nutritional index for predicting short- and long-term surgical outcomes after gastrectomy: a retrospective analysis of 7781 gastric cancer patients. Medicine (Baltimore), 2016, 95(18): e3539.
32.	Rizo-Téllez SA, Sekheri M, Filep JG. C-reactive protein: a target for therapy to reduce inflammation. Front Immunol, 2023, 14: 1237729.
33.	Okugawa Y, Toiyama Y, Yamamoto A, et al. Lymphocyte-to-C-reactive protein ratio and score are clinically feasible nutrition-inflammation markers of outcome in patients with gastric cancer. Clin Nutr, 2020, 39(4): 1209-1217.
34.	Cheng CB, Zhang QX, Zhuang LP, et al. Prognostic value of lymphocyte-to-C-reactive protein ratio in patients with gastric cancer after surgery: a multicentre study. Jpn J Clin Oncol, 2020, 50(10): 1141-1149.

1. Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 2021, 71(3): 209-249.
2. Yang W, Chen X, Zhang P, et al. Procalcitonin as an early predictor of intra-abdominal infections following gastric cancer resection. J Surg Res, 2021, 258: 352-361.
3. Xiao Y, Wei G, Ma M, et al. Association among prognostic nutritional index, post-operative infection and prognosis of stage II/III gastric cancer patients following radical gastrectomy. Eur J Clin Nutr, 2022, 76(10): 1449-1456.
4. Maezawa Y, Aoyama T, Ju M, et al. The impact of severe infectious complications on long-term prognosis for gastric cancer. Anticancer Res, 2020, 40(7): 4067-4074.
5. Greten FR, Grivennikov SI. Inflammation and cancer: triggers, mechanisms, and consequences. Immunity, 2019, 51(1): 27-41.
6. Ding P, Guo H, Sun C, et al. Combined systemic immune-inflammatory index (SII) and prognostic nutritional index (PNI) predicts chemotherapy response and prognosis in locally advanced gastric cancer patients receiving neoadjuvant chemotherapy with PD-1 antibody sintilimab and XELOX: a prospective study. BMC Gastroenterol, 2022, 22(1): 121.
7. Mouchli M, Reddy S, Gerrard M, et al. Usefulness of neutrophil-to-lymphocyte ratio (NLR) as a prognostic predictor after treatment of hepatocellular carcinoma. Ann Hepatol, 2021, 22: 100249.
8. Okugawa Y, Toiyama Y, Yamamoto A, et al. Lymphocyte-C-reactive protein ratio as promising new marker for predicting surgical and oncological outcomes in colorectal cancer. Ann Surg, 2020, 272(2): 342-351.
9. Wang C, Huang HZ, He Y, et al. A new nomogram based on early postoperative NLR for predicting infectious complications after gastrectomy. Cancer Manag Res, 2020, 12: 881-889.
10. 姚晶, 李鸿, 夏东. 预后营养指数对原发性肝癌肝切除术后感染性并发症的预测价值. 现代肿瘤医学, 2022, 30(16): 2961-2964.
11. Nudel J, Bishara AM, de Geus SWL, et al. Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery: an analysis of the MBSAQIP database. Surg Endosc, 2021, 35(1): 182-191.
12. 中华人民共和国卫生部. 医院感染诊断标准(试行). 中华医学杂志, 2001, 81(5): 314-320.
13. Chen C, Yang D, Gao S, et al. Development and performance assessment of novel machine learning models to predict pneumonia after liver transplantation. Respir Res, 2021, 22(1): 94.
14. Jiang J, Pan H, Li M, et al. Predictive model for the 5-year survival status of osteosarcoma patients based on the SEER database and XGBoost algorithm. Sci Rep, 2021, 11(1): 5542.
15. Tey SF, Liu CF, Chien TW, et al. Predicting the 14-day hospital readmission of patients with pneumonia using artificial neural networks (ANN). Int J Environ Res Public Health, 2021, 18(10): 5110.
16. Ma RN, He YX, Bai FP, et al. Machine learning model for predicting acute respiratory failure in individuals with moderate-to-severe traumatic brain injury. Front Med (Lausanne), 2021, 8: 793230.
17. Bradley M, Dente C, Khatri V, et al. Advanced modeling to predict pneumonia in combat trauma patients. World J Surg, 2020, 44(7): 2255-2262.
18. Xue B, Li D, Lu C, et al. Use of machine learning to develop and evaluate models using preoperative and intraoperative data to identify risks of postoperative complications. JAMA Netw Open, 2021, 4(3): e212240.
19. Xi X, Yang MX, Wang XY, et al. Predictive value of prognostic nutritional index on infection after radical gastrectomy: a retrospective study. J Gastrointest Oncol, 2022, 13(2): 569-580.
20. 茅伟达, 凃威伟, 孙筱虹. 胃癌根治术后感染的病原菌及影响因素. 中华医院感染学杂志, 2020, 30(14): 2179-2183.
21. Kunisaki C, Sato S, Tsuchiya N, et al. Systemic review and meta-analysis of impact of splenectomy for advanced gastric cancer. In Vivo, 2020, 34(6): 3115-3125.
22. Wei C, Gu A, Almeida ND, et al. Operation time effect on rates of perioperative complications after operative treatment of distal radius fractures. J Orthop, 2021, 24: 82-85.
23. 夏初, 许向华, 黄怡. 糖尿病合并侵袭性肺真菌感染的研究进展. 中华结核和呼吸杂志, 2021, 44(2): 128-131.
24. 永佳, 韩晓丽, 永雪薇, 等. 2型糖尿病患者并发尿路感染的病原菌分布、氧化应激指标检测及相关因素分析. 中国病原生物学杂志, 2019, 14(10): 1219-1222.
25. Okabayashi T, Maeda H, Sun ZL, et al. Perioperative insulin therapy using a closed-loop artificial endocrine pancreas after hepatic resection. World J Gastroenterol, 2009, 15(33): 4116-4121.
26. Yoshida R, Gohara S, Sakata J, et al. Onodera's prognostic nutritional index correlates with tumor immune environment and survival in patients with oral squamous cell carcinoma undergoing chemoradiotherapy. Transl Oncol, 2020, 13(12): 100850.
27. Ostroumov D, Fekete-Drimusz N, Saborowski M, et al. CD4 and CD8 T lymphocyte interplay in controlling tumor growth. Cell Mol Life Sci, 2018, 75(4): 689-713.
28. Jiang P, Li X, Wang S, et al. Prognostic significance of PNI in patients with pancreatic head cancer undergoing laparoscopic pancreaticoduodenectomy. Front Surg, 2022, 9: 897033.
29. Bailón-Cuadrado M, Pérez-Saborido B, Sánchez-González J, et al. Prognostic nutritional index predicts morbidity after curative surgery for colorectal cancer. Cir Esp (Engl Ed), 2019, 97(2): 71-80.
30. Matsuda T, Umeda Y, Matsuda T, et al. Preoperative prognostic nutritional index predicts postoperative infectious complications and oncological outcomes after hepatectomy in intrahepatic cholangiocarcinoma. BMC Cancer, 2021, 21(1): 708.
31. Lee JY, Kim HI, Kim YN, et al. Clinical significance of the prognostic nutritional index for predicting short- and long-term surgical outcomes after gastrectomy: a retrospective analysis of 7781 gastric cancer patients. Medicine (Baltimore), 2016, 95(18): e3539.
32. Rizo-Téllez SA, Sekheri M, Filep JG. C-reactive protein: a target for therapy to reduce inflammation. Front Immunol, 2023, 14: 1237729.
33. Okugawa Y, Toiyama Y, Yamamoto A, et al. Lymphocyte-to-C-reactive protein ratio and score are clinically feasible nutrition-inflammation markers of outcome in patients with gastric cancer. Clin Nutr, 2020, 39(4): 1209-1217.
34. Cheng CB, Zhang QX, Zhuang LP, et al. Prognostic value of lymphocyte-to-C-reactive protein ratio in patients with gastric cancer after surgery: a multicentre study. Jpn J Clin Oncol, 2020, 50(10): 1141-1149.

Previous Article
Application of machine learning models for survival data with non-proportional hazard and case study

Chinese Journal of Evidence-Based Medicine

Diagnostic study of machine learning model based on combinatorial optimization to predict postoperative infectious complications of gastric cancer

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Format

Content