摘要
采用深度森林框架构建基于不平衡电子胎心宫缩监护数据的多分类判别模型,验证模型有效性,结果表明该模型预测性能较好,极大降低误判率,在产前胎儿健康状况智能评估中有良好应用前景。
The multi-classification discrimination model based on unbalanced Cardiotocography(CTG) data is built by Deep Forest(DF) framework. The validity of the model is verified,and the results show that the prediction performance of the model is good,the misjudgment rate is greatly reduced,and the model has a good application prospect in the intelligent assessment of antenatal fetal health status.
作者
郭傲
陈妍荻
魏航
陈沁群
洪佳明
李琼娜
郝志峰
GUO Ao;CHEN Yandi;WEI Hang;CHEN Qinqun;HONG Jiaming;LI Qiongna;HAO Zhifeng(School of Medical Information Engineering,Guangzhou University of Chinese Medicine,Guangzhou 510006,China;School of Computers,Guangdong University of Technology,Guangzhou 510006,China;Guangzhou Dongren Hospital,Guangzhou 510442;Guangzhou Sunray Medical Apparatus Co.Ltd.,Guangzhou 510520,China;School of Mathematics and Big Data,Foshan University,Foshan 528000,China)
出处
《医学信息学杂志》
CAS
2021年第3期43-49,共7页
Journal of Medical Informatics
基金
国家自然科学基金资助项目“高阶网络模体聚类算法与应用研究”(项目编号:61976052)
广东省医学科研基金资助项目“基于不平衡CTG数据的产前智能胎儿监护评价模型的研究”(项目编号:A2019428)。
关键词
产前胎儿监护
不平衡多分类
深度森林
胎心宫缩监护
antenatal fetal monitoring
imbalanced multi-classification
Deep Forest(DF)
Cardiotocography(CTG)
