QRS Complexes Detection Using UNet-BiLSTM Model Combined With Adaptive Post-Processing for Multilead Wearable ECG Smart T-Shirt System

In recent years, the rapid development of wearable devices and Internet of Things (IoT) technology has made real-time, continuous dynamic electrocardiogram (ECG) monitoring possible. However, robust universal multilead QRS complex detection under noise and high-heart rate (HR) conditions remains challenging. In this study, we propose a smart T-shirt-based multilead dynamic ECG monitoring system and a high-accuracy QRS complex detection algorithm to solve the above problems. First, we develop a six-lead smart T-shirt system with integrated flexible dry electrodes for real-time acquisition of the ECG under three conditions: standing, walking, and jogging. The electrode structure and hardware circuit are designed to resist noise, while electrodes are combined with medical-grade conductive gels to replace conventional Ag/AgCl wet electrodes, ultimately realizing high-signal-to-noise ratio (SNR) signal acquisition under dynamic conditions. The T-shirt-based system design not only enhances user comfort but also facilitates use for nonmedical users, making long-term ECG monitoring more feasible. Second, we propose a novel Pro-APP algorithm combining the UNet and bidirectional long short-term memory (UNet-BiLSTM) model with adaptive post-processing (APP), which is robust and outperforms three existing QRS complex detection algorithms. The UNet-BiLSTM model can effectively extract multiscale features and capture the timing information in the ECG. The APP algorithm further optimizes the R-peak localization by dynamically adjusting parameters. The results show that the system confirms the reliability of its signal quality, HR detection, and electrode performance through the signal quality assessment (SNR $\geq $ 24 dB), ECG simulator validation (RR interval error $\leq 4$ ms), and skin-electrode impedance measurement (impedance $\leq$ 117.27 K $\Omega $ at frequencies above 10 Hz). In addition, the Pro-APP algorithm significantly improves the sensitivity (93.67%), precision (97.13%), accuracy (91.08%), and F1-score (95.30%) for detecting QRS complexes, with a mean absolute error of only 3.63 ms, which achieves universal QRS complex detection in multilead ECG signals and optimizes wearable dynamic ECG monitoring. The research shows that the smart T-shirt system combined with the QRS complex detection algorithm can provide an important carrier and technical means for the new model of wise information technology of medicine.