Pathological Analysis of Stress Urinary Incontinence in Females using Artificial Neural Networks
This work addresses urinary incontinence diagnosis for clinicians, but it is incremental as it applies an existing neural network method to new medical data.
The study tackled stress urinary incontinence in women by modeling urethral pressure using an artificial neural network, finding it more efficient than conventional methods for clinical analysis, with results showing low-pressure zones in elderly patients indicating higher incontinence.
Objectives: To mathematically investigate urethral pressure and influencing parameters of stress urinary incontinence (SUI) in women, with focus on the clinical aspects of the mathematical modeling. Method: Several patients' data are extracted from UPP and urodynamic documents and their relation and affinities are modeled using an artificial neural network (ANN) model. The studied parameter is urethral pressure as a function of two variables: the age of the patient and the position in which the pressure was measured across the urethra (normalized length). Results: The ANN-generated surface, showing the relation between the chosen parameters and the urethral pressure in the studied patients, is more efficient than the surface generated by conventional mathematical methods for clinical analysis, with multi-sample analysis being obtained. For example, in elderly people, there are many low-pressure zones throughout the urethra length, indicating that there is more incontinence in old age. Conclusion: The predictions of urethral pressure made by the trained neural network model in relation to the studied effective parameters can be used to build a medical assistance system in order to help clinicians diagnose urinary incontinence problems more efficiently.