Abstract
BackgroundBirthweight is an important indicator during the fetal development process to protect the maternal and infant safety. However, birthweight is difficult to be directly measured, and is usually roughly estimated by the empirical formulas according to the experience of the doctors in clinical practice.MethodsThis study attempts to combine multiple electronic medical records with the B-ultrasonic examination of pregnant women to construct a hybrid birth weight predicting classifier based on long short-term memory (LSTM) networks. The clinical data were collected from 5,759 Chinese pregnant women who have given birth, with more than 57,000 obstetric electronic medical records. We evaluated the prediction by the mean relative error (MRE) and the accuracy rate of different machine learning classifiers at different predicting periods for first delivery and multiple deliveries. Additionally, we evaluated the classification accuracies of different classifiers respectively for the Small-for-Gestational-age (SGA), Large-for-Gestational-Age (LGA) and Appropriate-for-Gestational-Age (AGA) groups.ResultsThe results show that the accuracy rate of the prediction model using Convolutional Neuron Networks (CNN), Random Forest (RF), Linear-Regression, Support Vector Regression (SVR), Back Propagation Neural Network(BPNN), and the proposed hybrid-LSTM at the 40th pregnancy week for first delivery were 0.498, 0.662, 0.670, 0.680, 0.705 and 0.793, respectively. Among the groups of less than 39th pregnancy week, the 39th pregnancy week and more than 40th week, the hybrid-LSTM model obtained the best accuracy and almost the least MRE compared with those of machine learning models. Not surprisingly, all the machine learning models performed better than the empirical formula. In the SGA, LGA and AGA group experiments, the average accuracy by the empirical formula, logistic regression (LR), BPNN, CNN, RF and Hybrid-LSTM were 0.780, 0.855, 0.890, 0.906, 0.916 and 0.933, respectively.ConclusionsThe results of this study are helpful for the birthweight prediction and development of guidelines for clinical delivery treatments. It is also useful for the implementation of a decision support system using the temporal machine learning prediction model, as it can assist the clinicians to make correct decisions during the obstetric examinations and remind pregnant women to manage their weight.
Highlights
Birthweight is an important indicator during the fetal development process to protect the maternal and infant safety
On average, compared with neonates born appropriate for gestational age (AGA), small for gestational age (SGA) and LGA infants are more likely to need extra medical care during the delivery admission and readmission within two weeks of delivery
Since the weight changes are time series data, this paper proposes a time series birthweight prediction model based on the long short-term memory (LSTM) networks
Summary
The estimation of fetal weight in China is generally based on existing regression models that use multiple parameters established by foreign scholars. The input predictor set of temporal prediction model is comprised of pregnant women parameters, Fig. 1 The proposed birthweight prediction based on Hybrid-LSTM the fetal parameters and the weight change series. The average relative error rate of the fitting result was 2.14% Using this method, we acquired a set of maternal body weight sequences { weight_changet }, and the missing value processing was completed. After obtaining the output of the LSTM layers, the multibranch input layer is used to divide the physiological parameters into different categories, the model merges with the related pregnant women and fetal physiological parameters and uses them as the input for several FC layers (Hidden layer). The first one is the mean relative error (MRE) This index can be used as a common evaluation standard in regression analysis, which well reflects the prediction accuracy and performance of the prediction model. I=1 where y is the true value of the sample, yis the predicted value of the model and n is the total sample size
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
