• 中国科学论文统计源期刊
  • 中国科技核心期刊
  • 美国化学文摘(CA)来源期刊
  • 日本科学技术振兴机构数据库(JST)
临床输血与检验

临床输血与检验 ›› 2022, Vol. 24 ›› Issue (4): 427-432.DOI: 10.3969/j.issn.1671-2587.2022.04.004

• 临床输血 • 上一篇    下一篇

基于机器学习算法建立胎母输血综合征预测模型*

范可欣, 朱鹏汇, 王云, 王勇军, 张宁洁   

  1. 410011 湖南长沙,中南大学湘雅二医院检验科（范可欣）; 中南大学湘雅二医院输血科（朱鹏汇,王云,王勇军,张宁洁）
  • 收稿日期:2022-05-26 出版日期:2022-08-20 发布日期:2022-08-19
  • 通讯作者: 张宁洁,主要从事输血免疫学研究,（E-mail）znj_123188@csu.edu.cn。
  • 作者简介:范可欣（1995-）,女,技师,硕士,主要从事医疗大数据分析研究,（E-mail）fffankexin@163.com。
  • 基金资助:
    *本课题受国家自然科学基金项目（No.82102281）和湖南省自然科学基金项目（No.2021JJ40893）资助

The Prediction Model of Fetomaternal Hemorrhage was Established on Machine Learning Algorithm

FAN Ke-xin, ZHU Peng-hui, WANG Yun, et al   

  1. Department of Laboratory Medicine, The Second Xiangya Hospital, Central South University, Changsha 410011
  • Received:2022-05-26 Online:2022-08-20 Published:2022-08-19

RichHTML

4

PDF

748

摘要： 目的 基于机器学习算法建立胎母输血综合征（fetomaternal hemorrhage syndrome,FMH）预测模型,以辅助临床医生早期发现、诊断FMH并进行干预治疗。方法 本研究纳入2019年6月~2020年12月于本院产科进行产检的1 933例孕妇（孕6~42周）进行分析,使用递归特征消除法对FMH预测中的关键特征变量进行筛选,采用包括极端梯度提升决策树（XGBoost）模型等8种机器学习算法和传统回归方法构建FMH预测模型,并对其进行比较,择优选出最佳预测模型,采用十折交叉验证评价模型性能。结果 XGBoost模型表现出明显的预测优势,其训练集AUC为0.827,测试集AUC为0.808,准确率达0.76,其性能明显优于AUC仅为0.681的传统逻辑回归模型和其他7个机器学习模型。结论 本研究成功构建一款基于XGBoost算法的FMH预测模型,其预测性能良好。

关键词: 胎母输血综合征, 机器学习算法, 预测模型, XGBoost, K-B试验

Abstract: Objective To establish a prediction model of fetomaternal hemorrhage syndrome on machine learning algorithm, so as to assist clinicians in early detection,diagnosis and intervention of FMH. Methods This study was based on the data of pregnant women at 6~42 weeks of gestation who have received antenatal examinations in the Second Xiangya Hospital between June 2019 and December 2020. The recursive feature elimination algorithm was used to select key variables and developed eight kinds of machine learning algorithms and traditional regression model,and the model with the best performance was selected. Besides,the ten-fold cross-validation method was used to verify the model.Results The AUC of XGBoost model is 0.827,the AUC of test set is 0.808,and the accuracy is 0.76. The performance of XGBoost model is significantly better than that of traditional logistic regression model with AUC of 0.681 and other seven machine learning models.Conclusion In this study,a prediction model of FMH based on XGBoost algorithm was successfully constructed and its prediction performance is good.

Key words: Fetomaternal hemorrhage syndrome, Machine learning algorithm, Prediction model, XGBoost, K-B test

中图分类号: