支持向量机和Logistic回归在GDM风险预测中的应用

doi:10.3969/j.issn.1000-8535.2021.03.004

广州医药 ›› 2021, Vol. 52 ›› Issue (3): 23-27.DOI: 10.3969/j.issn.1000-8535.2021.03.004

支持向量机和Logistic回归在GDM风险预测中的应用

孟艳辉¹, 李春娜², 吴瑞珊¹, 宋小燕¹, 彭红波¹

1 广东省计划生育科学技术研究所国家卫生健康委员会男性生殖与遗传重点实验室(广州 510600)
2 海南大学管理学院(海口 570563)

收稿日期:2020-09-23 发布日期:2021-11-24
基金资助:
广东省医学科学技术研究基金(B2019195)

Application of support vector machine and logistic regression in risk prediction of GDM

MENG Yanhui¹, LI Chunna², WU Ruishan¹, SONG Xiaoyan¹, PENG Hongbo¹

1 NHC Key Laboratory of Male Reproduction and Genetics, Family Planning Research Institute of Guangdong Province, Guangzhou 510600, China
2 School of Management, Hainan University, Haikou 510600, China

Received:2020-09-23 Published:2021-11-24

摘要/Abstract

摘要： 目的探讨两种不同机器学习算法在妊娠期糖尿病(gestational diabetes mellitus,GDM)风险预测中的应用。方法选取2019年7月—2020年8月在广州市妇女儿童医疗中心及广东省计划生育专科医院进行产前检查的孕早期妇女520例,其中妊娠期糖尿病孕妇200例,随机抽取同期正常孕妇320例,收集孕妇的一般资料和孕早期(8～12周)的生化指标、血常规和凝血功能等检测资料。利用这些分析变量建立支持向量机(SVM)和Logistic回归(LR)预测模型。根据模型预测能力和模型实用性,如准确率、精确率、真阳性(TP)率、假阳性(FP)率、召回率、F测度、受试者工作特征曲线(ROC)进行效果评价。结果两种预测模型的分类准确率总体为86%。SVM模型在真阳性(TP)率、假阳性(FP)率、召回率、F测度、受试者工作特征曲线(ROC)方面优于LR模型。结论在分类与预测方面,支持向量机算法比Logistic回归模型更具有实用价值。

关键词: 支持向量机, Logistic回归, 预测

Abstract: Objective To explore the application of two different machine learning algorithms in the risk prediction of gestational diabetes mellitus (GDM). Methods A total of 520 pregnant women with gestational diabetes mellitus were selected from Women and Children's Medical Center and Guangdong Family Planning Hospital from July 2019 to August 2020, including 200 cases of gestational diabetes mellitus, and 320 normal pregnant women in the same period. The general information of pregnant women and the detection data of biochemical indexes, blood routine test and coagulation function in early pregnancy (8～12 weeks) were collected. Support vector machine (SVM) and logistic regression (LR) prediction models were established by using these analysis variables. According to the predictive ability and practicability of the model, something like accuracy rate, precision ratio, true positive (TP) rate, false positive (FP) rate, recall rate, F-measure and receiver operating characteristic curve (ROC) were evaluated. Results The classification accuracy of the two models was 86%. SVM model is better than LR model in TPrate, FPrate, recall rate, F measure and ROC. Conclusion Support vector machine is more practical than logistic regression model in classification and prediction.

Key words: Support vector machine, Logistic regression, Prediction

孟艳辉, 李春娜, 吴瑞珊, 宋小燕, 彭红波. 支持向量机和Logistic回归在GDM风险预测中的应用[J]. 广州医药, 2021, 52(3): 23-27.

MENG Yanhui, LI Chunna, WU Ruishan, SONG Xiaoyan, PENG Hongbo. Application of support vector machine and logistic regression in risk prediction of GDM[J]. Guangzhou Medical Journal, 2021, 52(3): 23-27.

参考文献

[1] RODDA C P,BENSON J E,VINCENT A J,et al. Maternal vitamin D supplementation during pregnancy prevents vitamin D deficiency in the newborn:an open bel randomized controlled trial[J]. Clin Endocrinol,2015,83(3):363-368.
[2] LIN H C, SU C T, WANG P C. An application of artificial immune recognition system for prediction of diabetes following gestational diabetes[J]. J Med Syst, 2011,35(3): 283-289.
[3] 谭建奇,廖贤平,黄孝庭,等. SVM在临床医学中的应用[J]. 海南医学,2009,11(9):134-137.
[4] 赖胜圣,刘虔铖,余丽玲,等. 基于SFS-SVM的乳腺癌预测模型的构建[J]. 中国医学物理学杂志,2019,36(7):826-829.
[5] HOSMER D W, HOSMER T, LE CESSIE S, et al. A comparison of goodness-of-fit tests for the logistic regression model[J]. Statist Med, 1997,16(9):965-980.
[6] JAAFAR S F,ALI D M. Diabetes mellitus forecast using artificial neural network (ANN)[C]. Kuala Lumpur, Malaysia: Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research,2005.
[7] DUYGU Ç A,ESIN D O.An automatic diabetes diagnosis system based on LDA-wavelet support vector machine classifier[J]. Expert Syst Appl,2011,38(7): 8311-8315.
[8] FRIESEN C D, MILLER A M, RAYBURN W F. Influence of spontaneous or induced labor on delivering the macrosomic fetus[J]. Amer J Perinatol,1995,12(1):63-66.
[9] HUGHES R C,MOORE M P,GULLAM J E,et al. An early pregnancy HbA1c≥5.9%(41 mmol/mL) is optimal for detecting diabetes and identifies women at increased risk of adverse pregnancy outcomes[J]. Diabetes Care,2014,37(11):2953-2959.
[10] THERIAULT S,GIGUERE Y,MASSE J,et al. Early prediction of gestational diabetes:a practical model combining clinical and biochemical markers[J]. Clin Chem Lab Med,2016,54(3):509-518.
[11] 王爽,杨慧霞.妊娠期糖尿病发病的危险因素分析[J]. 中华妇产科杂志,2014,49(5):321-324.
[12] DREW B G, DUFFY S J, FORMOSA M F, et al. High-density lipoprotein modulates glucose metabolism in patients with type 2 diabetes mellitus[J]. Circulatio, 2009,119(15):2103-2111.
[13] VOLDNER N, QVIGSTAD E, FRØSLIE K F, et al. Increased risk of macrosomia among overweight women with high gestational rise in fasting glucose[J]. J Matern Fetal Neonatal Med, 2010,23(1):74-81.
[14] GABBAY-BENZIV R,DOYLE L E,BLITZER M,et al. First trimester prediction of maternal glycemic status[J]. J Perinat Med,2015,43(3):283-289.
[15] SAVONA-VENTURA C,VASSALLO J,MARRE M,et al. A composite risk assessment model to screen for gestational diabetes mellitusamong Mediterranean women[J]. Int J Gynaecol Obstet,2013,120(3):240-244.
[16] CHANG C Y, CHEN S J, TSAI M F. Application of supportvector-machine-based method for feature selection and classification of thyroid nodules in ultrasound images[J]. Pattern Recognit, 2010,43(10):3494-3506.
[17] YU W, LIU T, VALDEZ R, et al. Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes[J]. BMC Med Inform Decis Mak,2010,10(1):16.

支持向量机和Logistic回归在GDM风险预测中的应用

Application of support vector machine and logistic regression in risk prediction of GDM

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	古嘉基, 连泳欣, 丘福满. m6A甲基化基因风险评估模型在卵巢癌预后的临床意义[J]. 广州医药, 2021, 52(3): 1-8.
[2]	李月菊. HPV联合TCT检测对宫颈病变诊断的预测价值[J]. 广州医药, 2021, 52(3): 48-51.
[3]	孟艳辉, 高飞, 吴瑞珊, 宋小燕, 彭红波. 血清25(OH)D₃水平对妊娠期糖尿病的预测价值[J]. 广州医药, 2021, 52(1): 39-42.