现代仪器与医疗

基于机器学习构建脂肪肝预测模型

PDF下载

宋莹莹 ¹ , 张展召 ²

现代仪器与医疗 | 医学工程 2025,31(1): 43-50

收起

现代仪器与医疗 |医学工程 2025 , 31 (1) : 43 -50

基于机器学习构建脂肪肝预测模型

全屏

[Author(id=1320388845204517065, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320388845309374667, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, authorId=1320388845204517065, language=EN, stringName=Yingying Song, firstName=Yingying, middleName=null, lastName=Song, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.Xinxiang Medical University, Xinxiang 453003, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320388845384872140, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, authorId=1320388845204517065, language=CN, stringName=宋莹莹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.新乡医学院，新乡　453003, bio={"content":"

宋莹莹，女，本科，助教，研究方向：机器学习与图像处理

"}, bioImg=null, bioContent=

宋莹莹，女，本科，助教，研究方向：机器学习与图像处理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320388845028356290, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, xref=1., ext=[AuthorCompanyExt(id=1320388845040939203, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, companyId=1320388845028356290, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.Xinxiang Medical University, Xinxiang 453003, China), AuthorCompanyExt(id=1320388845049327812, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, companyId=1320388845028356290, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.新乡医学院，新乡　453003)])]), Author(id=1320388845472952526, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320388845544255696, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, authorId=1320388845472952526, language=EN, stringName=Zhanzhao Zhang, firstName=Zhanzhao, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=², address=^2.Sanquan College of Xinxiang Medical University, Xinxiang 453003, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320388845602975953, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, authorId=1320388845472952526, language=CN, stringName=张展召, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=², address=^2.新乡医学院三全学院，新乡　453003, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320388845116436677, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, xref=2., ext=[AuthorCompanyExt(id=1320388845124825286, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, companyId=1320388845116436677, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^2.Sanquan College of Xinxiang Medical University, Xinxiang 453003, China), AuthorCompanyExt(id=1320388845133213895, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388844311130303, companyId=1320388845116436677, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^2.新乡医学院三全学院，新乡　453003)])])]

宋莹莹¹, 张展召²

作者信息

^1.新乡医学院，新乡　453003

^2.新乡医学院三全学院，新乡　453003

作者简介:

宋莹莹，女，本科，助教，研究方向：机器学习与图像处理

Constructing a fatty liver prediction model based on machine learning

Yingying Song¹, Zhanzhao Zhang²

Affiliations

^1.Xinxiang Medical University, Xinxiang 453003, China

^2.Sanquan College of Xinxiang Medical University, Xinxiang 453003, China

出版时间: 2025-02-10 doi: 10.11876/mimt202501008

文章导航

摘要

收起

目的

本研究旨在利用机器学习技术构建一种高效的脂肪肝预测模型，以帮助医务人员准确识别和分类脂肪肝高危人群，从而为早期干预和个性化治疗提供支持。

方法

研究数据来自2017—2020年的美国国家和健康调查（National Health and Nutrition Examination Survey，NHANES）数据库。最终纳入11个变量进行分析。采用6种机器学习算法决策树（Decision Tree，DT）、极端梯度提算（Extreme Gradient Boosting，XGBoost）、自适应提升算法（Adaptive Boosting，Adaboost）、K最邻近（K-Nearest Neighbor，KNN）、Logistic回归、人工神经网络（Artificial neural network，ANN）模型构建脂肪肝预测模型，采用随机生成的70%作为训练集，剩下的30%作为测试集。模型评估指标包括精确率、准确率、召回率、F1值、受试者工作特征曲线（Receiver Operating Characteristic curve，ROC）及曲线下面积（Area Under Curve，AUC）。

结果

共纳入3383名受试者，其中脂肪肝患者1506例，DT、XGBoost、AdaBoost、KNN、Logistic回归、ANN模型的AUC分别为0.98838、0.94624、0.88935、0.99110、0.90047、0.98990。除了KNN模型外，其余所有模型的校准曲线均表现良好，其中AdaBoost模型在六个模型中展现出最佳的预测性能。

结论

AdaBoost模型被认为是最优的预测模型，适用于脂肪肝的预测，并能够解释特征变量之间的交互关系。体质指数、甘油三酯和低密度脂蛋白指标能够有效识别脂肪肝的高危人群。

关键词

脂肪肝 / 机器学习 / 模型预测 / 自适应提升算法 / 受试者工作特征曲线

Abstract

收起

Objective

This study aims to use machine learning technology to construct an efficient fatty liver prediction model to help medical personnel accurately identify and classify high-risk populations for fatty liver, thereby providing support for early intervention and personalized treatment.

Methods

The research data was sourced from the National Health and Nutrition Examination Survey (NHANES) database in the United States from 2017 to 2020. Finally, 11 variables were included for analysis. Using 6 machine learning algorithms, Decision Tree (DT) Extreme Gradient Boosting (XGBoost), Adaptive Boosting (Adaboost), K-Nearest Neighbor (KNN), Logistic Regression, and Artificial Neural Network (ANN) models are used to construct a fatty liver prediction model. The randomly generated 70% is used as the training set, and the remaining 30% is used as the testing set. The model evaluation metrics include accuracy, precision, recall, F1 score, Receiver Operating Characteristic curve (ROC), and Area Under Curve (AUC).

Results

A total of 3383 participants were included, including 1506 patients with fatty liver. The decision tree The AUC of XGBoost, AdaBoost, KNN, logistic regression, and ANN models are 0.98838, 0.94624, 0.88935, 0.99110, 0.90047, and 0.98990, respectively. Except for the KNN model, the calibration curves of all other models performed well, with the AdaBoost model showing the best predictive performance among the six models.

Conclusion

The AdaBoost model is considered the optimal predictive model for predicting fatty liver and can explain the interaction between feature variables. Body mass index, triglycerides, and low-density lipoprotein indicators can effectively identify high-risk populations for fatty liver.

Key words

Fatty liver / Machine learning / Model prediction / Adaptive boosting / Receiver operating characteristic curve

引用本文

宋莹莹, 张展召. 基于机器学习构建脂肪肝预测模型. 现代仪器与医疗, 2025 , 31 (1) : 43 -50 . DOI: 10.11876/mimt202501008

Yingying Song, Zhanzhao Zhang. Constructing a fatty liver prediction model based on machine learning[J]. Modern Instruments & Medical Treatment, 2025 , 31 (1) : 43 -50 . DOI: 10.11876/mimt202501008

基金

收起

河南省2022年省级专创融合特色示范课课程(195)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Lazo M, Clark JM. The epidemiology of nonalcoholic fatty liver disease: a global perspective[J]. Semin Liver Dis, 2008, 28(4): 339-350.

[2]

洪森, 张廷光, 徐慧. 非酒精性脂肪肝患者血清中同型半胱氨酸的水平及影响非酒精性脂肪肝发生的高危因素[J]. 中华养生保健, 2023, 41(20): 60-62.

[3]

Le MH, Yeo YH, Li X, et al. 2019 Global NAFLD Prevalence: A systematic review and meta-analysis[J]. Clin Gastroenterol Hepatol, 2022, 20(12): 2809-2817.e28.

[4]

Adams LA, Lymp JF, St Sauver J, et al. The natural history of nonalcoholic fatty liver disease: a population-based cohort study[J]. Gastroenterology, 2005, 129(1): 113-121.

[5]

Zhou F, Zhou J, Wang W, et al. Unexpected rapid increase in the burden of NAFLD in China from 2008 to 2018: A systematic review and meta-analysis[J]. Hepatology, 2019, 70(4): 1119-1133.

[6]

卫霞. 血脂, 血糖, 肝功能和血尿酸联合检测在老年脂肪肝诊断中的应用研究[J]. 临床医学, 2022, 42(5): 76-78.

[7]

徐景城. 脂肪肝远不只伤肝[J]. 肝博士, 2024, (5): 40.

[8]

Berger D, Desai V, Janardhan S. Con: Liver biopsy remains the gold standard to evaluate fibrosis in patients with nonalcoholic fatty liver disease[J]. Clin Liver Dis (Hoboken), 2019, 13(4): 114-116.

[9]

Castéra L, Foucher J, Bernard PH, et al. Pitfalls of liver stiffness measurement: a 5-year prospective study of 13,369 examinations[J]. Hepatology, 2010, 51(3): 828-835.

[10]

Ngiam KY, Khor IW. Big data and machine learning algorithms for health-care delivery[J]. Lancet Oncol, 2019, 20(5): e262-e273.

[11]

Handelman GS, Kok HK, Chandra R V, et al. eDoctor: machine learning and the future of medicine[J]. J Intern Med, 2018, 284(6): 603-619.

[12]

Huang L, Li J, Zhu S, et al. Machine learning-based prognostic prediction and surgical guidance for intrahepatic cholangiocarcinoma[J]. Bioscience trends, 2025, 18(6): 545-554.

[13]

Wang Z, Wang Z, Li F, et al. Construction and validation of a machine learning-based prediction model for short-term mortality in critically Ill patients with liver cirrhosis[J]. Clin Res Hepatol Gastroenterol, 2024, 49(1): 102507.

[14]

Zhao M, Wan J, Qin W, et al. A machine learning-based diagnosis modelling of type 2 diabetes mellitus with environmental metal exposure[J]. Comput Methods Programs Biomed, 2023, 235: 107537.

[15]

沈翊康, 刘海煜, 王少丽, 等. 基于机器学习方法预测胃癌前状态的比较研究[J/OL]. 中华中医药学刊, 1-10[2025-02-28]. http://kns.cnki.net/kcms/detail/21.1546.r.20241219.1524.002.html.

[16]

张博晖, 禹天同, 赵帅, 等. 基于机器学习的冠状动脉慢性完全闭塞患者术后不良心血管事件预测模型的构建[J]. 心脏杂志, 2025, (3): 264-270.

[17]

Bedogni G, Bellentani S, Miglioli L, et al. The Fatty Liver Index: A simple and accurate predictor of hepatic steatosis in the general population[J]. BMC Gastroenterol, 2006, 6: 33.

[18]

National Health and Nutrition ExaminationSurvey: questionnaires, and relateddatasets[J/OL]. https://wwwn.cdc.gov/nchs/nhanes/Default.aspx.

[19]

Carrizosa E, Molero-Río C, Romero Morales D. Mathematical optimization in classification and regression trees[J]. Top (Berl), 2021, 29(1): 5-33.

[20]

陈云樱, 吴积钦, 徐可佳. 决策树中基于基尼指数的属性分裂方法[J]. 微机发展, 2004, 14(5): 66-68.

[21]

袁焦, 王珣, 潘兆马, 等. 基于机器学习的列车设备故障预测模型研究[J]. 计算机与现代化, 2020, (12): 49-54.

[22]

胡雪梅, 李佳丽, 蒋慧凤. 机器学习方法研究肝癌预测问题[J]. 系统科学与数学, 2022, 42(2): 417-433.

[23]

许裕栗, 杨晶, 李柠, 等. Xgboost算法在区域用电预测中的应用[J]. 自动化仪表, 2018, 39(7): 1-5.

[24]

Qin Y. AdaBoost–Theory and Application[J]. Musicmcgillca, 1970.

[25]

杨新武, 马壮, 袁顺. 基于弱分类器调整的多分类Adaboost算法[J]. 电子与信息学报, 2016, 38(2): 373-380.

[26]

Schwenk H, Bengio Y. Boosting neural networks[J]. Neural Comput, 2000, 12(8): 1869-1887.

[27]

Zuo D, Yang L, Jin Y, et al. Machine learning-based models for the prediction of breast cancer recurrence risk[J]. BMC Med Inform Decis Mak, 2023, 23(1): 276.

[28]

孙岩, 吕世聘, 王秀坤, 等. 基于结构学习的KNN分类算法[J]. 计算机科学, 2007, 34(12): 184-186+237.

[29]

Sun S, Huang R. An Adaptive k-Nearest Neighbor Algorithm[C]//International Conference on Fuzzy Systems and Knowledge Discovery.2010.

[30]

顾鑫, 曹丹华, 吴裕斌, 等. 基于逻辑回归的多任务域快速分类学习算法[J]. 计算机工程与应用, 2017, 53(15): 47-56.

[31]

Song X, Liu X, Liu F, et al. Comparison of machine learning and logistic regression models in predicting acute kidney injury: A systematic review and meta-analysis[J]. Int J Med Inform, 2021, 151: 104484.

[32]

Zou J, Han Y, So SS. Overview of artificial neural networks[J]. Methods Mol Biol, 2008, 458: 15-23.

[33]

Bourquin J, Schmidli H, Van Hoogevest P, et al. Basic concepts of artificial neural networks (ANN) modeling in the application to pharmaceutical development[J]. Pharm Dev Technol, 1997, 2(2): 95-109.

[34]

Bertolaccini L, Solli P, Pardolesi A, et al. An overview of the use of artificial neural networks in lung cancer research[J]. J Thorac Dis, 2017, 9(4): 924-931.

2025年第31卷第1期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.11876/mimt202501008

首发时间：2026-10-23
出版时间：2025-02-10

补充材料

相关文章

文章信息

作者

出版历史

基金

河南省2022年省级专创融合特色示范课课程(195)

作者信息

^1.新乡医学院，新乡　453003

^2.新乡医学院三全学院，新乡　453003

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/xdyqyyl/CN/10.11876/mimt202501008

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT