Towards a reliable multimodal AI monitoring system for pain detection and quantification

Towards a reliable multimodal AI monitoring system for pain detection and quantification

Accurate and robust pain intensity detection has significant implications for patient monitoring and rehabilitation, especially in per- sonalized treatment and management. Benefiting from the complemen- tarity of multiple modalities, multimodal fusion-based methods for pain intensity classification have garnered widespread attention. In this study, we propose an novel Bi-Modal Fusion framework based on Electrodermal Activity (EDA) and Electromyography (EMG) for pain classification. This framework combines LSTM with an attention module in a unified block to learn complex dynamic features from biosignals, effectively cap- turing both global and local patterns. Meanwhile, focal loss is used as the loss function to mitigate the impact of class imbalance during model training. Through extensive experiments, our method achieves an aver- age accuracy improvement of 3.31% compared to SOTA across 11 sub- datasets of X-ITE pain database, with a notable improvement of 7.20% on the Reduced Electrical Tonic sub-dataset (RETD). Our research not only validates the effectiveness of the proposed method but also high- lights its robustness across different modalities and sub-datasets. These findings lay a solid foundation for our long-term goal of developing an accurate and robust clinical multimodal AI monitoring system for pain detection and quantification.

Citing

@inproceedings{wang_pain_intens,
    title = {Towards a reliable multimodal AI monitoring system for pain detection and quantification},
    author = {Wang, Huibin and Nienaber, Sören and Dinges, Laslo and Jung, Magnus and Al-Hamadi, Ayoub},
    booktitle = {2025 International Conference on Robotics, Computer Vision and Intelligent Systems},
    year = {2025}
    }