A Model for Predicting the Amount of Urine in the Bladder Based on App-generated Tracking Data

Incontinence patients suffering from neurogenic bladder dysfunction lack information about the filling level of their urinary bladder. A real-time prediction of the filling level of their bladder could support them managing their daily routines. In this study, we developed a system that predicts the bladder filling level based on user-tracked fluid intake. The system collects and analyzes the data to predict the current filling level of the bladder. Displayed in an app, users can optimize their micturition frequency receiving an alert when a critical level is reached. In the same way users can compare the predicted- and their target filling level.