Cao Zhen, Wang Guoqiang, Xu Ling, Li Chaowei, Hao Yuexing, Chen Qinqun, Li Xia, Liu Guiqing, Wei Hang
School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, 510006 China.
Nvogene Co., Ltd., Tianjing, China.
Health Inf Sci Syst. 2023 Mar 19;11(1):16. doi: 10.1007/s13755-023-00219-w. eCollection 2023 Dec.
Cardiotocography (CTG), which measures uterine contraction (UC) and fetal heart rate (FHR), is a crucial tool for assessing fetal health during pregnancy. However, traditional computerized cardiotocography (cCTG) approaches have non-negligible calibration errors in feature extraction and heavily rely on the expertise and prior experience to define diagnostic features from CTG or FHR signals. Although previous works have studied deep learning methods for extracting CTG or FHR features, these methods still neglect the clinical information of pregnant women.
In this paper, we proposed a multimodal deep learning architecture (MMDLA) for intelligent antepartum fetal monitoring that is capable of performing automatic CTG feature extraction, fusion with clinical data and classification. The multimodal feature fusion was achieved by concatenating high-level CTG features, which were extracted from preprocessed CTG signals via a convolution neural network (CNN) with six convolution layers and five fully connected layers, and the clinical data of pregnant women. Eventually, light gradient boosting machine (LGBM) was implemented as fetal status assessment classifier. The effectiveness of MMDLA was evaluated using a dataset of 16,355 cases, each of which includes FHR signal, UC signal and pertinent clinical data like maternal age and gestational age.
With an accuracy of 90.77% and an area under the curve (AUC) value of 0.9201, the multimodal features performed admirably. The data imbalance issue was also effectively resolved by the LGBM classifier, with a normal-F1 value of 0.9376 and an abnormal-F1 value of 0.8223.
In summary, the proposed MMDLA is conducive to the realization of intelligent antepartum fetal monitoring.
宫缩图（CTG）可测量子宫收缩（UC）和胎儿心率（FHR），是评估孕期胎儿健康的关键工具。然而，传统的计算机化宫缩图（cCTG）方法在特征提取方面存在不可忽视的校准误差，并且严重依赖专业知识和先前经验来从CTG或FHR信号中定义诊断特征。尽管先前的研究已经探讨了用于提取CTG或FHR特征的深度学习方法，但这些方法仍然忽略了孕妇的临床信息。
在本文中，我们提出了一种用于智能产前胎儿监测的多模态深度学习架构（MMDLA），该架构能够执行自动CTG特征提取、与临床数据融合以及分类。多模态特征融合是通过将从经过预处理的CTG信号经具有六个卷积层和五个全连接层的卷积神经网络（CNN）提取的高级CTG特征与孕妇的临床数据连接起来实现的。最终，采用轻梯度提升机（LGBM）作为胎儿状态评估分类器。使用包含16355个病例的数据集评估MMDLA的有效性，每个病例包括FHR信号、UC信号以及诸如产妇年龄和孕周等相关临床数据。
多模态特征表现出色，准确率达到90.77%，曲线下面积（AUC）值为0.9201。LGBM分类器也有效解决了数据不平衡问题，正常F1值为0.9376，异常F1值为0.8223。
总之，所提出的MMDLA有助于实现智能产前胎儿监测。
