The invention discloses a
urinary incontinence prediction device and method based on
machine learning, and relates to the technical field of
urinary incontinence prediction. The method comprises the steps that a
database is built on the basis of the device, and the
database comprises
electronic data of
urinary incontinence disease screening; preprocessing the data in the
database; selecting features related to urinary incontinence from the preprocessed data; dividing data into a
training set and a
test set, and introducing a cost function to optimize the initial XGBoost prediction model to obtain an optimized function; and performing prediction by using the optimized XGBoost function so as to solve prediction data of related urinary incontinence prediction. The device comprises a
bladder pressure monitor body, a display screen is fixedly arranged on the front face of the
bladder pressure monitor body, a pressure measuring connector is arranged at the top of the
bladder pressure monitor body, a
catheter is arranged on one side of the bladder pressure monitor body, and a cleaning device is arranged on the front face of the bladder pressure monitor body. And a first motor is arranged in the cleaning device. By arranging the first motor, the lead screw, the nut seat and the cleaning rod, the first motor drives the lead screw to rotate, the rotating lead screw drives the nut seat and the cleaning rod to vertically move, the vertically moving cleaning rod can clean the surface of the display screen, attached dust is cleaned down, and the display screen is kept clean; and dust is prevented from hindering a worker to read bladder
pressure monitoring data displayed on the display screen.