Classification of Urodynamic Features Based on Deep Learning

Lower urinary tract symptoms (LUTS) are common among the elderly, significantly affecting their quality of life. Although urodynamic tests are the diagnostic standard, their high cost and complexity limit widespread use. Based on a large urodynamic dataset from Tongji Hospital, Huazhong University of Science and Technology, this paper proposes a deep learning-based model using a Transformer encoder for multivariate time-series data. With improved normalization, an Interactive Convolution Block (ICB), and a KAN dynamic weighting mechanism, the model performs well in bladder function and urine flow rate classification, offering a more effective AI solution for LUTS diagnosis, reducing misdiagnosis risks, and supporting personalized treatment.