Urinary incontinence is closely related to the motor ability and toileting tasks. Some nursing home residents with limited mobility who cannot reach the bathroom in time highly depend on caregivers for toileting assistance. However, nursing home staffing is often insufficient to meet the needs of all residents. Monitoring the desire to urinate is vital to minimize functional dependence and improve the quality of life of older people. Improved reliability of the desire to void monitoring requires exploring more effective monitoring methods. In this paper, we observed the changes in heart rate variability (HRV) during bladder filling, established the mapping relationship between normal bladder filling degree and HRV, and evaluated the performance of different classification models in predicting the degree of desire to void using HRV characteristics at different bladder filling degrees. The results showed that the autonomic nervous system gradually shifted to sympathetic nerve activity with increased bladder filling. Meanwhile, the classification accuracy of the wide neural network model for the degree of desire to void was >
98 %. HRV shows a significant application prospect in predicting the desire to void, which provides a new direction for the research and development of non-invasive voiding intention monitoring and intelligent rehabilitation equipment and is expected to promote technical progress and development in related fields.