Deep learning-based approach for accurate detection of fetal QRS complexes in abdominal ECG signals

Nov 10, 2025Scientific reports

Using deep learning to accurately detect fetal heartbeats in abdominal ECG signals

AI simplified

Abstract

The proposed framework achieved 96.79% accuracy in detecting fetal QRS complexes from abdominal electrocardiogram signals.

A one-dimensional Convolutional Neural Network (1D-CNN) was developed to identify fetal heart signals in non-invasive readings.
The system demonstrated 97.91% sensitivity, 92.79% specificity, and 97.88% precision in its evaluations.
Only 20 abdominal electrocardiogram signals were needed for training, marking a notable reduction compared to traditional methods.
The architecture eliminated the requirement for extracting maternal ECG components, simplifying the computational process.
High-precision detection was achieved with a novel labeling strategy at 100-millisecond intervals, minimizing preprocessing needs.

AI simplified

Congenital heart defects are the leading cause of mortality related to birth defects, making early monitoring of fetal electrocardiogram (FECG) vital for the detection of abnormal fetal heart rate (FHR) patterns. Accurate detection in FECG is crucial for assessing fetal health, including heart rate and the early identification of congenital conditions. This study presents a novel automated framework using a one-dimensional Convolutional Neural Network (1D-CNN) to detect fetal QRS complexes from abdominal electrocardiogram () signals, sourced from the PhysioNet Non-Invasive FECG Database (NI-FECGDB). The proposed CNN architecture comprises five convolutional layers, seven batch normalization layers, three dropout layers, and three dense layers. In the initial phase to generate annotations tailored for the proposed network, each AECG signal was partitioned into overlapping 1-second windows, facilitating data augmentation. Binary annotations were generated for each 100-millisecond segment based on the presence or absence of fetal QRS complexes. Subsequently, after performing preprocessing steps, the developed algorithm was applied, and its performance was evaluated using metrics such as accuracy, mean squared error, F1-score, sensitivity, specificity, and precision. The results were compared with those from previous studies utilizing the NI-FECGDB database. The proposed lightweight 1D-CNN architecture demonstrated exceptional performance, achieving 96.79% accuracy, 97.91% sensitivity, 92.79% specificity and 97.88% precision while requiring only 20 AECG signals for training - a significant improvement over existing methods that typically demanded larger datasets. This framework's innovative design eliminated the need for maternal ECG component extraction, thereby reducing computational complexity and potential signal decomposition artifacts. The combination of a simplified five-layer architecture with our novel 100 ms resolution labeling strategy enabled high-precision fetal QRS detection while maintaining minimal preprocessing requirements. These advances position our method as a robust and efficient solution for clinical fetal monitoring applications.

Key numbers

96.79%

Accuracy

Percentage of correct detections.

20 signals

Training Signals

Number of abdominal ECG signals used for training.

Full Text

We can’t show the full text here under this license. Use the link below to read it at the source.

View full text (PDF) ↗View full text (HTML) ↗

Abstract

Key numbers

Full Text

what lands in your inbox each week: