Key result
Combined piezo-ECG model achieves ~92% accuracy for automated sleep stage classification in preterm infants.
Why the study?
Polysomnography is invasive and labour-intensive, limiting continuous sleep monitoring in preterm infants in the NICU.
Does an automatic sleep stage classification model using combined ECG and piezo mat data accurately classify sleep stages in preterm infants compared to expert annotations?
Cross-Sectional (n=28)
Does an automatic sleep stage classification model using combined ECG and piezo mat data accurately classify sleep stages in preterm infants compared to expert annotations?
Effect estimate: Cohen's kappa = 0.83
A machine learning approach combining routinely available ECG and piezo mat data provides a highly accurate, unobtrusive method for continuous sleep stage monitoring in preterm infants.
Enables continuous unobtrusive sleep staging in preterm infants; leaves open prospective validation for clinical adoption and outcome impact.
In the neonatal intensive care unit (NICU), preterm infants are usually unable to fulfil their sleep demands due to frequent disruptions. Real-time sleep monitoring could be an essential tool not only to shift elective care to their wake periods but also to track their developmental sleep profile as an indicator of healthy brain maturation. The current gold standard for sleep measurement, polysomnography, is invasive and labour-intensive, limiting its applicability for continuous monitoring. We propose an automatic sleep stage classification method using only the routinely available electrocardiogram (ECG) and patient movement data recorded with a piezo mat. For this study we recorded data from 28 preterm infants (13 females and 15 males) at 35.7 ± 0.5 weeks postmentrual age. We employed a support vector machine (SVM) to classify sleep stages into wakefulness (W), active sleep (AS), and quiet sleep (QS). The combined piezo + ECG model demonstrated superior accuracy (92 %) and strong agreement with expert annotations (Cohen’s kappa = 0.83) compared to ECG-only or piezo-only models. This approach offers a reliable, unobtrusive solution for continuous sleep monitoring in NICUs, facilitating individualised, sleep-based medical care for preterm infants.
No takes yet. Share an insight, caveat, or question.
Demme et al. (2025) conducted a cross-sectional in Preterm infants requiring sleep monitoring (n=28). Combined piezo mat and ECG machine learning model (SVM) vs. ECG-only or piezo-only models, and expert annotations was evaluated on Accuracy of sleep stage classification (wakefulness, active sleep, quiet sleep) (Cohen's kappa = 0.83). An automatic sleep stage classification model combining piezo and ECG data achieved 92% accuracy and strong agreement (Cohen's kappa = 0.83) with expert annotations in preterm infants.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: