Abstract
Electrohysterography (EHG) has emerged as an alternative technique to predict preterm labor, which still remains a challenge for the scientific-technical community. Based on EHG parameters, complex classification algorithms involving non-linear transformation of the input features, which clinicians found difficult to interpret, were generally used to predict preterm labor. We proposed to use genetic algorithm to identify the optimum feature subset to predict preterm labor using simple classification algorithms. A total of 203 parameters from 326 multichannel EHG recordings and obstetric data were used as input features. We designed and validated 3 base classifiers based on k-nearest neighbors, linear discriminant analysis and logistic regression, achieving F1-score of 84.63 ± 2.76%, 89.34 ± 3.5% and 86.87 ± 4.53%, respectively, for incoming new data. The results reveal that temporal, spectral and non-linear EHG parameters computed in different bandwidths from multichannel recordings provide complementary information on preterm labor prediction. We also developed an ensemble classifier that not only outperformed base classifiers but also reduced their variability, achieving an F1-score of 92.04 ± 2.97%, which is comparable with those obtained using complex classifiers. Our results suggest the feasibility of developing a preterm labor prediction system with high generalization capacity using simple easy-to-interpret classification algorithms to assist in transferring the EHG technique to clinical practice.
Highlights
Premature delivery is defined as one that occurs before 37 weeks of gestation
We found that the EHG features computed from the 3 channels contained complementary information: 22, 25 and 23 features computed from S1, S2 and S3 respectively were included in at least one of the three optimized feature subsets
It can be seen that a subset of 11 and 8 features was shared by logistic regression (LR) and linear discriminant analysis (LDA), and by LR and k-nearest neighbors (KNN) classifiers, respectively
Summary
Over 9– 12% of children are born prematurely every year, this being the leading cause of new-born deaths and the second-leading cause of death after pneumonia in children under the age of 5 [1]. Preterm births are associated with long-term morbidity consequences such as learning disabilities, attention deficit disorder, emotional problems, respiratory distress and intraventricular hemorrhage [1]. The costs derived from premature pregnancy are significant for national healthcare systems. In the United States, the economic cost in 2005 (combined medical, educational and lost productivity) associated with preterm birth amounted to at least $26.2 billion [1]. The average first-year medical costs, including both inpatient and outpatient care, were about 10 times greater for preterm ($32,325) than for term infants ($3325) [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
