Toward Efficient ECG-Based Pain Intensity Recognition: An End-to-End Neural Network Using Multiple Temporal Feature Compression and Fusion

Wearable single-lead electrocardiogram (ECG) devices exhibit significant advantage for capturing subtle variations in cardiac activity, offering new potential for the continuous assessment and management of chronic pain. An essential task of ECG-based monitoring is the accurate recognition of pain intensity. However, developing an online pain intensity recognition method presents several critical challenges, including high computational complexity, limited robustness to noise, etc. To address these challenges, this article proposes an end-to-end neural network by integrating multiple temporal feature compression and fusion strategies. The proposed algorithm comprises three primary sequential stuctures: 1) feature compression module (FCM); 2) pain-related feature extraction module (PFEM); and 3) hidden feature fusion complementary module (HFFCM). First, FCM utilizes a Resnet compression to exploit the latent information embedded in the autocorrelation of ECG time series. Subsequently, PFEM extracts the hidden pain features through self-attention. Finally, HFFCM dynamically integrates and complements these features through a cross-attention mechanism built upon large-kernel convolutions. Evaluated on the public biovid dataset, the proposed algorithm outperforms state-of-the-art methods, achieving accuracy of 72.41%, in pain tolerance stimulus or no pain state classification. In addition, the proposed algorithm simplifies the attention mechanism through large-kernel convolutional modulation, reducing the model’s computational complexity to only 0.43 GFLOPs, which is 65.6% less than the existing transformer-based approaches. Overall, this article proposes an efficient online method for pain intensity recognition, offering a reliable solution that enhances chronic pain monitoring in the field of Internet of Things (IoT).