Predicting High-Risk Preterm Birth Using Artificial Neural Networks

Abstract

A reengineered approach to the early prediction of preterm birth is presented as a complimentary technique to the current procedure of using costly and invasive clinical testing on high-risk maternal populations. Artificial neural networks (ANNs) are employed as a screening tool for preterm birth on a heterogeneous maternal population; risk estimations use obstetrical variables available to physicians before 23 weeks gestation. The objective was to assess if ANNs have a potential use in obstetrical outcome estimations in low-risk maternal populations. The back-propagation feedforward ANN was trained and tested on cases with eight input variables describing the patient's obstetrical history; the output variables were: 1) preterm birth; 2) high-risk preterm birth; and 3) a refined high-risk preterm birth outcome excluding all cases where resuscitation was delivered in the form of free flow oxygen. Artificial training sets were created to increase the distribution of the underrepresented class to 20%. Training on the refined high-risk preterm birth model increased the network's sensitivity to 54.8%, compared to just over 20% for the nonartificially distributed preterm birth model.

Machine Learning for High Risk Pregnancies Pre-Term Birth Prediction: A Retrospective

“…(2006) employed ANN as a screening tool for preterm birth. ANNs trained using obstetrical data have been found to be a potentially useful clinical decision support tool in the early estimation of PTB [3]. This work does not merely attempt to replace the physicians intuition and judgement , but attempts to augment physicians decision making by providing a screening tool to identify mothers at high risk of deliv-ering prematurely from a heterogeneous population.…”

Does Bayes have it? Decision Support Systems in diagnostic medicine

“…That is, important connections for determining a correct diagnosis are reinforced, and irrelevant connections are attenuated with each training case fed into the system. ANNs have shown great promise in the successful prognosis (Ennett, 2003;Frize et al, 2006Frize et al, , 1995Catley et al, 2006) and in the diagnosis of medical conditions from patient symptom characteristics, for example, in the differentiation of malignant from benign tumors in medical imaging (Goggin et al, 2007). ANNs represent a complex mathematical computation between inputs and the weights in the model, but in the last decade, several methods to extract the weights of the input variables at peak performance were developed, allowing researchers to determine the minimum set of variables leading to the outcome of interest (Rybchynski, 2005;Frize et al, 2006).…”

“…Borra et al, 2007;Goggin et al, 2007) underscoring the often misguided assumption that human performance is inevitably optimal. Others provide predictions based on data mining and analysis to help physicians in making a diagnosis or decide on a course of therapy (Frize et al, , 1995Catley et al, 2006). Some authors who promote attempts to emulate human decision processes refer to this as 'soft computing' (Tung and Quek, 2005;Zadeh, 1994).…”

Modular neural network model based foetal state classification

“…A reactive NST is greatly reassuring, with a negative predictive value of 99.8% for stillbirths occurring within one week, after excluding lethal congenital anomalies and unpredictable causes of foetal death, such as sudden onset of placenta abruption, umbilical cord accidents, et al [6] II. RELATED RESEARCH WORK Application of neural networks concerns mainly the foetal outcome assessment [7] and prediction of high-risk preterm birth [8]. In the learning process of the neural networks, aimed at CTG trace classification, knowledge of clinical experts is applied, which is based on evaluation of selected parameters from the newborn description [9].…”