Identification of human term and preterm labor using artificial neuralnetworks on uterine electromyography data
Maner,WL; Garfield,RE
Abstract OBJECTIVE: To use artificial neural networks (ANNs) on uterineelectromyography (EMG) data to classify term/preterm labor/non-labor pregnant patients. MATERIALSAND METHODS: A total of 134 term and 51 preterm women (all ultimately delivered spontaneously) wereincluded. Uterine EMG was measured trans-abdominally using surface electrodes. ”Bursts” of elevateduterine EMG, corresponding to uterine contractions, were quantified by finding the means and/orstandard deviations of the power spectrum (PS) peak frequency, burst duration, number of bursts perunit time, and total burst activity. Measurement-to-delivery (MTD) time was noted for each patient.Term and preterm patient groups were sub-divided, resulting in the following categories:[term-laboring (TL): n 75; preterm-laboring (PTL): n preterm-non-laboring (PTN): n = 38], with laborassessed using clinical determinations. ANN was then used on the calculated uterine EMG data toalgorithmically and objectively classify patients into labor and non-labor. The percent of correctlycategorized patients was found. Comparison between ANN-sorted groups was then performed usingStudent’’s t test (with p < 0.05 significant). RESULTS: In total, 59/75 (79%) of TL patients, 12/13(92%) of PTL patients, 51/59 (86%) of TN patients, and 27/38 (71%) of PTN patients were correctlyclassified. CONCLUSION: ANNs, used with uterine EMG data, can effectively classify term/pretermlabor/non-labor patients.
Keywords Labor, Obstetric; Neural Networks (Computer); Obstetric Labor, Premature
Annals of Biomedical Engineering
0090-6964, Volume 35, Issue 3, 2007, Pages 3-473
