Uterine Electromyography as a new Predictor of Extremely Preterm Birth: A Multifactorial Model Integrating Clinical and Bioelectrical Parameters

Background Extremely preterm birth (EPB), defined as delivery before 28 weeks of gestation, is a major contributor to neonatal morbidity and mortality. Accurate prediction of EPB is crucial for enabling timely interventions to improve neonatal outcomes and optimize resource allocation. Uterine electromyography (uEMG) is a non-invasive method that quantifies uterine electrical activity, offering potential for early EPB risk stratification. This study investigates the predictive value of uEMG parameters combined with traditional clinical risk factors for EPB. Methods A retrospective study was conducted at Sun Yat-sen Memorial Hospital, Guangzhou, China, including 173 singleton pregnant women with threatened preterm labor (TPTL) symptoms who underwent uEMG monitoring between 20+0 and 27+6 weeks of gestation from January 2018 to May 2025.The association of uEMG parameters (contraction frequency, average peak contraction intensity, and average contraction duration) with EPB were analyzed using logistic regression. Two predictive models were developed: a traditional model, including: assisted reproductive technology (ART), prior deliveries between 12–28 weeks, and transvaginal cervical length (TVCL); an enhanced model incorporating uEMG parameters (contraction frequency, average contraction duration) and clinical risk factor. Receiver Operating Characteristic curve, precision-recall curve, calibration curve and decision curve analysis were used to assess predictive performance. Result Among the 173 patients, 36 delivered before 28 weeks. The EPB group showed significantly higher uterine contraction frequency, intensity, and duration (P < 0.05). Three uEMG parameters were significantly associated with an increased risk of EPB. The uEMG model achieved a significantly higher area under the curve (AUC) compared to the traditional model (0.859, 95% CI: 0.798–0.920 VS 0.716, 95% CI: 0.606–0.827; P < 0.05, DeLong test). Based on nomogram, high-risk patients (nomogram score >76) had significantly higher EPB rates in both training (42.9%) and validation (55.6%) sets compared to low-risk groups (10% and 0%) (P < 0.001). Conclusion uEMG parameters, particularly contraction frequency and duration, are independent predictors of EPB. The predictive model integrating uEMG with clinical factors (ART, prior deliveries history, TVCL) offers high accuracy and clinical utility for EPB risk stratification. As a non-invasive tool, uEMG enhances traditional methods, supporting its potential for routine clinical use.