基于机器学习算法构建组织学绒毛膜羊膜炎的预测模型

胡雪源; 谭美玲; 黄革; 阎萍; 陈晓霞; 郑明昱; 王丹

doi:10.16016/j.2097-0927.202307052

您当前的位置：

首页 >

文章列表页 >

基于机器学习算法构建组织学绒毛膜羊膜炎的预测模型

临床医学 | 更新时间：2026-01-09

- 基于机器学习算法构建组织学绒毛膜羊膜炎的预测模型
- Construction of a prediction model of histologic chorioamnionitis based on machine learning
- 陆军军医大学学报 2023年45卷第23期页码：2476-2484
- 作者机构：
  
  1.400038 重庆，陆军军医大学(第三军医大学)第一附属医院妇产科
  2.400038 重庆，陆军军医大学(第三军医大学)第一附属医院药学部
- 作者简介：
  
  [王丹, E-mail: swh_wang@163.com WANG Dan, E-mail: swh_wang@163.com
- 基金信息：
  
  重庆市自然科学基金(CSTB2022NSCQ-MSX0169)
- DOI：10.16016/j.2097-0927.202307052
  中图分类号： R319;R711.32;R714.52
- 收稿：2023-07-13，
  
  修回：2023-11-01，
  
  纸质出版：2023-12-15
- 稿件说明：
移动端阅览
胡雪源, 谭美玲, 黄革, 等. 基于机器学习算法构建组织学绒毛膜羊膜炎的预测模型[J]. 陆军军医大学学报, 2023,45(23):2476-2484.

Xueyuan HU, Meiling TAN, Ge HUANG, et al. Construction of a prediction model of histologic chorioamnionitis based on machine learning[J]. Journal of Army Medical University, 2023, 45(23): 2476-2484.
胡雪源, 谭美玲, 黄革, 等. 基于机器学习算法构建组织学绒毛膜羊膜炎的预测模型[J]. 陆军军医大学学报, 2023,45(23):2476-2484. DOI： 10.16016/j.2097-0927.202307052.

Xueyuan HU, Meiling TAN, Ge HUANG, et al. Construction of a prediction model of histologic chorioamnionitis based on machine learning[J]. Journal of Army Medical University, 2023, 45(23): 2476-2484. DOI： 10.16016/j.2097-0927.202307052.

摘要

目的

开发一项关于未足月胎膜早破(preterm premature rupture of membrane

PPROM)孕妇分娩后发生组织学绒毛膜羊膜炎(histologic chorioamnionitis

HCA)的机器学习预测模型。

方法

选取在我院住院分娩的孕28周~36

周胎膜早破的病例512例。收集研究对象的一般资料、孕产史、实验室数据、超声数据等共31项资料。将所有研究对象按7 ∶3随机分配为训练集(

=358)和测试集(

=154)。使用最小绝对收缩和选择算子算法(the least absolute shrinkage and selection operator

LASSO)算法在训练集中筛选出6项危险因素：生殖道感染、B超胎儿体重、破膜胎龄、使用抗生素前最高体温、既往宫腔操作次数、破膜距抗生素使用的间隔时间纳入模型。基于支持向量机(support vector machine

SVM)、逻辑回归(logistic regression

LR)、多层感知机(multilayer perceptron

MLP)、随机森林(random forest

RF)、极端梯度提升(extreme gradient boosting

XGB)、决策树(decision tree

DT)等机器学习算法绘制受试者工作特征(receiver operating characteristic

ROC)曲线，通过比较曲线下面积(area under curve

AUC)选取最佳机器学习模型。同时对最终模型的预测效益及临床适用性进行评估并计算危险因素的重要性。

结果

6种机器学习算法中SVM模型预测效能最高，在测试集中SVM的AUC为0.862，敏感度为84.0%，特异度为75.0%。其在校准曲线中辨别能力、临床决策(decision curve analysis

DCA)曲线中临床效益均获得良好评价。变量SHAP(SHapley Additive exPlanations)图按重要性依次排列呈现6项危险因素，其中最重要的是生殖道感染。

结论

基于SVM算法成功建立未足月胎膜早破孕产妇组织学绒毛膜羊膜炎的预测模型。该模型对HCA的良好预测能力可以指导临床诊疗，改善不良妊娠结局，促进母婴健康。

Abstract

Objective

To develop a machine learning prediction model for histologic chorioamnionitis (HCA) in patients with preterm premature rupture of membranes (PPROM) after delivery.

Methods

A total of 512 pregnant women who were diagnosed with PPROM at 28~36+6 weeks in our hospital were enrolled in this study. After 31 clinical items consisting of general information

maternal history

laboratory data

and imaging parameters were collected for each subject

they were randomly divided into a training set (

=358) and a testing set (

=154) in a ratio of 7:3. Least absolute shrinkage and selection operator (LASSO) algorithm was used to identify independent predictors in the training set. Based on these factors (reproductive

tract infection

ultrasound fetal weight

gestational age at PPROM

maximum body temperature before antibiotics

number of previous uterine operations

and interval between rupture of membranes and antibiotic use)

6 machine learning models

including support vector machine (SVM)

logistic regression (LR)

multilayer perceptron (MLP)

random forest (RF)

extreme gradient boosting (XGB) and decision tree (DT) were developed. Area under the curve (AUCs) value was used to compare the prediction efficiency of the built models. Then prediction efficiency and clinical applicability of optimal model were evaluated to calculate the importance of risk factors.

Results

Among 6 machine learning algorithms

the SVM model performed best with an accuracy of 0.862

sensitivity of 0.840

and specificity of 0.750 in the testing set. The predicted values derived from the model were highly consistent with the actual situations in discrimination of calibration curve and decision curve analysis. SHapley Additive exPlanations (SHAP) plot prioritized the predictive weights of 6 risk factors

and reproductive tract infection was of most significant importance.

Conclusion

An SVM prediction model of HCA occurrence in PPROM patients is successfully constructed. Its excellent predictive ability contributes to guiding clinical treatment

improving adverse pregnancy outcomes

and promoting maternal and infant health.

关键词

Keywords

references

CHOI E K, KIM S Y, HEO J M, et al . Perinatal outcomes associated with latency in late preterm premature rupture of membranes[J ] . Int J Environ Res Public Health, 2021, 18(2): 672. DOI: 10.3390/ijerph18020672.

RONZONI S, BOUCOIRAN I, YUDIN M H, et al . Guideline No. 430: diagnosis and management of preterm prelabour rupture of membranes[J ] . J D'obstetrique Gynecol Du Can, 2022, 44(11): 1193-1208. e1. DOI: 10.1016/j.jogc.2022.08.014.

CAPPELLETTI M, PRESICCE P, KALLAPUR S G. Immunobiology of acute chorioamnionitis[J]. Front Immunol, 2020, 11: 649. DOI: 10.3389/fimmu.2020.00649.

JAIN V G, WILLIS K A, JOBE A, et al . Chorioamnionitis and neonatal outcomes[J ] . Pediatr Res, 2022, 91(2): 289-296. DOI: 10.1038/s41390-021-01633-0.

SHI H N, SUN L L, WANG Z J, et al . Non-invasive prediction of histologic chorioamnionitis using maternal serum markers in women with preterm prelabour rupture of membranes[J ] . Am J Reprod Immunol, 2022, 88(3): e13594. DOI: 10.1111/aji.13594.

郭孝君, 张雪芹, 何远敏, 等. 基于ROC曲线评价血常规指标中系统性炎症参数识别硬膜外镇痛相关产时发热与组织型绒毛膜羊膜炎的临床价值[J]. 中国实用妇科与产科杂志, 2021, 37(7): 753-756. DOI: 10.19538/j.fk2021070115.

GUO X J, ZHANG X Q, HE Y M, et al . Based on ROC curve, the clinical value of systemic inflammatory parameters in blood routine indexes in identifying intrapartum fever related to epidural analgesia and tissue chorioamnionitis was evaluated[J ] . Chin J Pract Gynecol Obstet, 2021, 37(7): 753-756. DOI: 10.19538/j.fk2021070115.

BLENCOWE H, COUSENS S, OESTERGAARD M Z, et al . National, regional, and worldwide estimates of preterm birth rates in the year 2010 with time trends since 1 990 for selected countries: a systematic analysis and implications[J ] . Lancet, 2012, 379(9832): 2162-2172. DOI: 10.1016/S0140-6736(12)60820-4.

GOLDENBERG R L, CULHANE J F, IAMS J D, et al . Epidemiology and causes of preterm birth[J ] . Lancet, 2008, 371(9606): 75-84. DOI: 10.1016/S0140-6736(08)60074-4.

VENKATESH K K, JACKSON W, HUGHES B L, et al . Association of chorioamnionitis and its duration with neonatal morbidity and mortality[J ] . J Perinatol, 2019, 39(5): 673-682. DOI: 10.1038/s41372-019-0322-0.

PENG J, CHEN Y, WAN S, et al . Predictors for histological chorioamnionitis among women with preterm prelabour rupture of membranes after dexamethasone treatment: a retrospective study[J ] . BJOG, 2023, 130(9): 1072-1079. DOI: 10.1111/1471-0528.17431.

ALJERIAN K. Pathologist interobserver variability in diagnosing acute ascending intrauterine infection[J]. Ann Diagn Pathol, 2022, 56: 151874. DOI: 10.1016/j.anndiagpath.2021.151874.

YONEDA S, SHIOZAKI A, ITO M, et al . Accurate prediction of the stage of histological chorioamnionitis before delivery by amniotic f luid IL-8 level[J ] . Am J Reprod Immunol, 2015, 73(6): 568-576. DOI: 10.1111/aji.12360.

OSKOVI KAPLAN Z A, OZGU-ERDINC A S. Prediction of preterm birth: maternal characteristics, ultrasound markers, and biomarkers: an updated overview[J]. J Pregnancy, 2018, 2018: 8367571. DOI: 10.1155/2018/8367571.

张颖莹, 刘怡果, 赵丹, 等. 基于机器学习建立脓毒症心肾综合征患者早期死亡风险预测模型[J]. 中华肾脏病杂志, 2022, 38(9)785-793. DOI: 10.3760/cma.j.cn441217-20211126-00113

ZHANG Y Y, LIU Y G, ZHAO D, et al . Early mortality risk prediction models for patients with sepsis-induced cardiorenal syndrome based on machine learning[J ] . Chin J Nephrol, 2022, 38(9)785-793. DOI: 10.3760/cma.j.cn441217-20211126-00113

ALBEROLA-RUBIO J, GARCIA-CASADO J, PRATS-BOLUDA G, et al . Prediction of labor onset type: spontaneous vs induced; role of electrohysterography?[J ] . Comput Methods Programs Biomed, 2017, 144: 127-133. DOI: 10.1016/j.cmpb.2017.03.018.

REZEBERGA D, LAZDANE G, KROICA J, et al . Placental histological inflammation and reproductive tract infections in a low risk pregnant population in Latvia[J ] . Acta Obstet Gynecol Scand, 2008, 87(3): 360-365. DOI: 10.1080/00016340801936487.

李娟, 尹燕雪, 赵澄泉, 等. 胎盘炎性病变的分类、病理特征及临床意义[J]. 中华病理学杂志, 2021, 50(3): 300-304. DOI: 10.3760/cma.j.cn112151-20201228-00975.

LI J, YIN Y X, ZHAO C Q, et al . Classification, pathological features and clinical significance of placental inflammatory lesions[J ] . Chin J Pathol, 2021, 50(3): 300-304. DOI: 10.3760/cma.j.cn112151-20201228-00975.

GALLETTA M A K, SCHULTZ R, SARTORELLI M F G O P, et al . Clinical characteristics, complications, and predictive model of histological chorioamnionitis in women with preterm premature rupture of membranes[J ] . PLoS One, 2023, 18(4): e0283974. DOI: 10.1371/journal.pone.0283974.

MATULOVA J, KACEROVSKY M, HORNYCHOVA H, et al . Acute histological chorioamnionitis and birth weight in pregnancies with preterm prelabor rupture of membranes: a retrospective cohort study[J ] . Front Pharmacol, 2022, 13: 861785. DOI: 10.3389/fphar.2022.861785.

CHEN J, WANG Z Y, WU W Z, et al . Clinical analysis of 2860 cases of diabetes in pregnancy: a single-center retrospective study[J ] . BMC Pregnancy Childbirth, 2022, 22(1): 418. DOI: 10.1186/s12884-022-04712-0.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

心血管手术患者术后呼吸衰竭的危险因素及预测模型构建

基于增强静脉期CT放射组学的甲状腺乳头状癌中央区淋巴结转移预测模型构建与验证

基于5种机器学习算法构建的怀孕概率预测模型及其性能比较

高原脱适应症发生风险预测模型的构建与验证

基于机器学习算法建立非心脏手术术后认知功能障碍风险预测模型