USING ARTIFICIAL INTELLIGENCE TO PREDICT TREATMENT OUTCOMES IN PATIENTS WITH NEUROGENIC OVERACTIVE BLADDER AND...

Area of Science:

• Neurology
• Urology
• Medical Imaging
• Machine Learning

Background:

• Neurogenic overactive bladder (NOAB) significantly impacts women with multiple sclerosis (MS), causing urinary frequency, urgency, and incontinence.
• Predicting treatment success for NOAB in MS patients is challenging, necessitating advanced analytical approaches.

Purpose of the Study:

• To develop and evaluate machine learning (ML) models for predicting treatment success in female MS patients with NOAB.
• To stratify predictions based on different treatment modalities: behavioral, medication, and minimally invasive therapies.

Main Methods:

• Retrospective cohort study of 110 female MS patients diagnosed with NOAB (2017-2022).
• Clinical and MRI brain/spine imaging data were analyzed.
• LASSO-regularized logistic regression (LR) and extreme gradient-boosted tree (XGB) models were trained on 70% of data and tested on 30%, using top-ranked features.

Main Results:

• The study included 110 female patients (mean age 59) with MS and NOAB.
• Logistic regression models demonstrated strong predictive performance, with Area Under the Curve (AUC) values of 0.74 for behavioral therapy, 0.76 for medication therapy, and 0.83 for minimally invasive therapies.
• MRI revealed significant lesion burden in the brain and cervical spine for most patients.

Conclusions:

• Machine learning models, particularly logistic regression, show significant potential in predicting NOAB treatment success in women with MS.
• The developed models achieved high AUC scores, indicating their utility in guiding personalized treatment decisions.
• Further prospective studies are recommended to validate these findings and refine predictive capabilities.