Construction of postoperative prognostic model for primary liver cancer based on SMOTE and machine learning

Bi PAN; Jinghua YU; Yixian HUANG; Yazhou WU; Fang LI

doi:10.16016/j.2097-0927.202310052

您当前的位置：

首页 >

文章列表页 >

Construction of postoperative prognostic model for primary liver cancer based on SMOTE and machine learning

Clinical Medicine | 更新时间：2026-01-09

- Construction of postoperative prognostic model for primary liver cancer based on SMOTE and machine learning
- Journal of Army Medical University Vol. 46, Issue 19, Pages: 2236-2240(2024)
- 作者机构：
  
  400038 重庆，陆军军医大学(第三军医大学)军事预防医学系军队卫生统计学教研室
- 作者简介：
- 基金信息：
  
  the National Natural Science Foundation of China(82173621);the National Natural Science Foundation of China(81872716)
- DOI：10.16016/j.2097-0927.202310052
  CLC： R319;R730.7;R735.7
- Received：13 October 2023，
  
  Revised：2024-07-02，
  
  Published：15 October 2024
- 稿件说明：
移动端阅览
Bi PAN, Jinghua YU, Yixian HUANG, et al. Construction of postoperative prognostic model for primary liver cancer based on SMOTE and machine learning[J]. Journal of Army Medical University, 2024, 46(19): 2236-2240.
DOI：

Bi PAN, Jinghua YU, Yixian HUANG, et al. Construction of postoperative prognostic model for primary liver cancer based on SMOTE and machine learning[J]. Journal of Army Medical University, 2024, 46(19): 2236-2240. DOI： 10.16016/j.2097-0927.202310052.

摘要

目的

基于合成少数类过采样技术(synthetic minority over-sampling technique

SMOTE)算法和机器学习模型构建原发性肝癌术后的预后预测模型。

方法

选取美国国立癌症研究所的监测、流行病学及最终结果(Surveillance

Epidemiology

and End Results

SEER)数据库中4 297例患者进行回顾性队列研究，通过独热编码和平均值插补法进行数据预处理，利用SMOTE算法解决数据类别不平衡问题，将临床变量纳入机器学习模型，基于决策树(decision tree

DT)、随机森林(random forest

RF)、梯度提升决策树(gradient boosting decision tree

GBDT)、极限梯度提升算法(eXtreme Gradient Boosting

XGBoost)方法构建预后预测模型(SMOTE+DT/RF/GBDT/XGBoost)，通过比较多种模型的性能，筛选出最佳的预测模型。

结果

组合模型SMOTE+RF展示出最优的预测性能，受试者工作特征曲线(receiver operating characteristic curve

ROC)下的面积(area under the curve

AUC)、准确率和精确率均高于其他模型，分别为0.895、0.811、0.806。

结论

基于SMOTE+RF算法的原发性肝癌的预后预测模型可有效预测原发性肝癌患者的生存结局。

Abstract

Objective

To construct a prognosis prediction model of primary liver cancer after surgical treatment based on synthetic minority over-sampling technique(SMOTE) algorithm and machine learning model.

Methods

A retrospective cohort study was conducted on 4 297 patients with primary liver cancer from the surveillance

epidemiology

and end results(SEER) database. One-Hot Encoding and Multiple Imputation were used to preprocess the collect data

and SMOTE algorithm was employed to solve the imbalance of data categories. The obtained clinical variables were included in the machine learning model. Based on decision tree(DT)

random forest(RF)

gradient boosting decision tree(GBDT) and eXtreme Gradient Boosting(XGBoost)

a prognostic prediction model(SMOTE+DT/RF/GBDT/XGBoost) was build

and then the best prediction model was determined by comparing the performance of various models. Finally

a prognostic analysis system for primary liver cancer was developed based on the optimal model

which was then visualized.

Results

The combination model SMOTE+RF showed the best predictive performance

with higher area under the curve(0.895)

accuracy(0.811) and precision(0.806) than those of other models in receiver operating characteristic curve(ROC) analysis.

Conclusion

The SMOTE+RF prognostic prediction model can effectively predict the survival outcome of patients with primary liver cancer.

关键词

Keywords

references

中华人民共和国国家卫生和计划生育委员会. 原发性肝癌诊疗规范(2017年版)[J]. 临床肝胆病杂志. 2017;33(8): 1419-1431. DOI: 10.3969/j.issn.1001-5256.2017.08.003.

National Health and Family Planning Commission of the People's Republic of China. Diagnosis, management, and treatment of hepatocellular carcinoma(V2017)[J]. Journal of Clinical Hepatology, 2017, 33(8): 1419-1431. DOI: 10.3969/j.issn.1001-5256.2017.08.003.

FORNER A, REIG M, BRUIX J. Hepatocellular carcinoma[J]. Lancet(London, England), 2018, 391(10127): 1301-1314. DOI: 10.1016/s0140-6736(18)30010-2.

DING J, WEN Z. Survival improvement and prognosis for hepatocellular carcinoma: analysis of the SEER database[J]. BMC Cancer, 2021, 21(1): 1157. DOI: 10.1186/s12885-021-08904-3.

LIN E, ZOU B, ZENG G, et al . The impact of liver fibrosis on microvascular invasion and prognosis of hepatocellular carcinoma with a solitary nodule: a Surveillance, Epidemiology, and End Results(SEER) database analysis[J ] . Annals of Translational Medicine, 2021, 9(16): 1310. DOI: 10.21037/atm-21-3731.

SHEN X H, LI H K, WANG F, et al . Clinical significance of lymph node metastasis in patients undergoing partial hepatectomy for hepatocellular carcinoma[J ] . World J Surg, 2010, 34(5): 1028-1033. DOI: 10.1007/s00268-010-0400-0.

ZHANG K, TAO C C, WU F, et al . A practical nomogram from the SEER database to predict the prognosis of hepatocellular carcinoma in patients with lymph node metastasis[J ] . Ann Palliat Med, 2021, 10(4): 3847-3863. DOI: 10.21037/apm-20-1876.

ZHENG Y S, ZHANG X, LU J S, et al . Association between socioeconomic status and survival in patients with hepatocellular carcinoma[J ] . Cancer Med, 2021, 10(20): 7347-7359. DOI: 10.1002/cam4.4223.

CHIU C C, LEE K T, LEE H H, et al . Comparison of models for predicting quality of life after surgical resection of hepatocellular carcinoma: a prospective study[J ] . J Gastrointest Surg, 2018, 22(10): 1724-1731. DOI: 10.1007/s11605-018-3833-7.

HO W H, LEE K T, CHEN H Y, et al . Disease-free survival after hepatic resection in hepatocellular carcinoma patients: a prediction approach using artificial neural network[J ] . PLoS One, 2012, 7(1): e29179. DOI: 10.1371/journal.pone.0029179.

NOH B, PARK Y M, KWON Y, et al . Machine learning-based survival rate prediction of Korean hepatocellular carcinoma patients using multi-center data[J ] . BMC Gastroenterol, 2022, 22(1): 85. DOI: 10.1186/s12876-022-02182-4.

SHI H Y, LEE K T, LEE H H, et al . Comparison of artificial neural network and logistic regression models for predicting in-hospital mortality after primary liver cancer surgery[J ] . PLoS One, 2012, 7(4): e35781. DOI: 10.1371/journal.pone.0035781.

SATRIANO L, LEWINSKA M, RODRIGUES P M, et al . Metabolic rearrangements in primary liver cancers: cause and consequences[J ] . Nat Rev Gastroenterol Hepatol, 2019, 16(12): 748-766. DOI: 10.1038/s41575-019-0217-8.

ZHENG Y Y, LI Y, FENG J, et al . Cellular based immunotherapy for primary liver cancer[J ] . J Exp Clin Cancer Res, 2021, 40(1): 250. DOI: 10.1186/s13046-021-02030-5.

MCGLYNN K A, PETRICK J L, EL-SERAG H B. Epidemiology of hepatocellular carcinoma[J]. Hepatology, 2021, 73(Suppl 1): 4-13. DOI: 10.1002/hep.31288.

RICH N E, MURPHY C C, YOPP A C, et al . Sex disparities in presentation and prognosis of 1110 patients with hepatocellular carcinoma[J ] . Aliment Pharmacol Ther, 2020, 52(4): 701-709. DOI: 10.1111/apt.15917.

WANG T, ZHANG K H. New blood biomarkers for the diagnosis of AFP-negative hepatocellular carcinoma[J]. Front Oncol, 2020, 10: 1316. DOI: 10.3389/fonc.2020.01316.

LI W, LIU K, CHEN Y, et al . Role of alpha-fetoprotein in hepatocellular carcinoma drug resistance[J ] . Curr Med Chem, 2021, 28(6): 1126-1142. DOI: 10.2174/0929867327999200729151247.

JEONG S, LUO G J, GAO Q, et al . A combined Cox and logistic model provides accurate predictive performance in estimation of time-dependent probabilities for recurrence of intrahepatic cholangiocarcinoma after resection[J ] . Hepatobiliary Surg Nutr, 2021, 10(4): 464-475. DOI: 10.21037/hbsn.2020.01.07.

MAVROS M N, ECONOMOPOULOS K P, ALEXIOU V G, et al . Treatment and prognosis for patients with intrahepatic cholangiocarcinoma: systematic review and meta-analysis[J ] . JAMA Surg, 2014, 149(6): 565-574. DOI: 10.1001/jamasurg.2013.5137.

Chawla N V, Bowyer K W, Hall L O, et al . SMOTE: synthetic minority over-sampling technique[J ] . Journal of artificial intelligence research, 2002, 16: 321-357. DOI: 10.1613/jair.953

NI Z, ZHU Y, QIAN Y, et al . Synthetic minority over-sampling technique-enhanced machine learning models for predicting recurrence of postoperative chronic subdur al hematoma[J ] . Front Neurol, 2024, 15: 1305543. DOI: 10.3389/fneur.2024.1305543.

Views

392

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Risk factors for postoperative respiratory failure in patients undergoing cardiovascular surgery and construction of a prediction model

Construction and validation of a prediction model for central lymph node metastasis of papillary thyroid carcinoma based on contrast-enhanced venous phase CT radiomics

Pregnancy probability prediction models based on 5 machine learning algorithms and comparison of their performance

Construction and validation of a risk prediction model for high altitude de-acclimatization syndrome

Construction of a prediction model of histologic chorioamnionitis based on machine learning

Related Author

ZHOU Fuchao

LIU Xiang

LU Kaizhi

SHAO Jianliang

HE Xingyun

LIU Chen

DU Junze

LI Qian

Related Institution

Department of Anesthesiology， First Affiliated Hospital， Army Medical University （Third Military Medical University）

Department of Radiology

Department of Breast and Thyroid Surgery， First Affiliated Hospital， Army Medical University （Third Military Medical University）， Chongqing

Department of Radiology， No. 9

Hospital of PLA Army

⁰