Application of Artificial Intelligence in Early Diagnosis of Spontaneous Preterm Labor and Birth

Abstract

This study reviews the current status and future prospective of knowledge on the use of artificial intelligence for the prediction of spontaneous preterm labor and birth ("preterm birth" hereafter). The summary of review suggests that different machine learning approaches would be optimal for different types of data regarding the prediction of preterm birth: the artificial neural network, logistic regression and/or the random forest for numeric data; the support vector machine for electrohysterogram data; the recurrent neural network for text data; and the convolutional neural network for image data. The ranges of performance measures were 0.79-0.94 for accuracy, 0.22-0.97 for sensitivity, 0.86-1.00 for specificity, and 0.54-0.83 for the area under the receiver operating characteristic curve. The following maternal variables were reported to be major determinants of preterm birth: delivery and pregestational body mass index, age, parity, predelivery systolic and diastolic blood pressure, twins, below high school graduation, infant sex, prior preterm birth, progesterone medication history, upper gastrointestinal tract symptom, gastroesophageal reflux disease, Helicobacter pylori, urban region, calcium channel blocker medication history, gestational diabetes mellitus, prior cone biopsy, cervical length, myomas and adenomyosis, insurance, marriage, religion, systemic lupus erythematosus, hydroxychloroquine sulfate, and increased cerebrospinal fluid and reduced cortical folding due to impaired brain growth.

Keywords: artificial intelligence; early diagnosis; preterm birth.

Figure 1

Principle of the support vector machine. A line (or hyperplane) H₁ does not separate black and white circles while hyperplanes H₂ and H₃ separate the two groups. Here, the distance between the two groups is maximal for H₃ and the support vector machine creates such a hyperplane. Image provided by Wikipedia.

Figure 2

Structure of the artificial neural network. An artificial neural network is a network of input/output units (so called “neurons”) connected through weights. The artificial neural network usually consists of one input layer, one, two or three hidden layers, and one output layer. Neurons in a previous layer combine with “weights” in the next layer (here, the weights are numerical values showing how much effect neurons in a previous layer have on neurons in the next layer).