Key result
ECG-based deep learning detects microstress in pregnant mothers with a ~77% F1 score.
Why the study?
Elevated stress during pregnancy increases adverse birth outcomes, but capturing distinct physiological responses to micro-ecological momentary assessment remains challenging.
Does an optimized deep network using ECG sensing accurately detect microstress in pregnant mothers?
Does an optimized deep network using ECG sensing accurately detect microstress in pregnant mothers?
A deep learning approach with fine-tuning using ECG signals can detect stress in pregnant mothers with an F1 score of 76.50%, enabling potential real-time monitoring.
May enable ECG-based microstress monitoring in pregnancy; hypothesis-generating pending larger validation.
Elevated stress levels during pregnancy increase the risk of delivering a premature or low-birthweight infant. Recently, microecological momentary assessment (micro-EMA) has been explored extensively. However, capturing more distinct physiological responses to micro-EMA is still challenging. In this letter, we propose a methodology for micro-EMA-based stress detection using feature extraction and classifiers. For this, an online publicly available micro-EMA database (N=18) is considered. The ECG signals are preprocessed. Ten features are extracted and applied to the classifiers, namely, support vector machine, decision tree, gradient boosting (GradB), adaptive boosting, 1-D convolution network (DL), and, DL with fine-tuning (DLFT). Performance is evaluated using leave-one-subject-out cross-validation. The proposed approach is able to discriminate stress in pregnant mothers. Using DLFT, the approach yields an average classification F1 score, precision, and recall of 76.50 %, 72.40%, and 86.25%, respectively. Thus, the proposed approach could be extended for integrated monitoring systems, enabling real-time stress detection during pregnancy.
No takes yet. Share an insight, caveat, or question.
Mehta et al. (2024) conducted a letter in Stress during pregnancy (n=18). Micro-EMA-based stress detection using ECG sensing and deep learning with fine-tuning (DLFT) vs. Other classifiers (SVM, decision tree, gradient boosting, adaptive boosting, 1-D DL) was evaluated on Stress detection performance (F1 score). A deep learning approach with fine-tuning using ECG sensing successfully detected microstress in pregnant mothers, yielding an average F1 score of 76.50%, precision of 72.40%, and recall of 86.25%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: