Development of a multivariate prediction model for nocturia, based on urinary tract etiologies

Area of Science:

• Urology
• Medical Diagnostics
• Predictive Modeling

Background:

• Nocturia, or nighttime urination, affects a significant portion of the population.
• Identifying predictors of nocturia is crucial for effective management and treatment strategies.

Purpose of the Study:

• To determine which combination of modifiable and non-modifiable parameters can discriminate patients with nocturia from those without.
• To develop a predictive model for nocturia using frequency volume charts (FVC).

Main Methods:

• Post-hoc analysis of three prospective, observational studies.
• Utilized frequency volume charts (FVC) to compare characteristics between patients with and without nocturia.
• Employed logistic regression and random forest algorithms to identify key determinants for discrimination.

Main Results:

• A logistic regression model with seven determinants demonstrated high accuracy in discriminating between nights with and without nocturia.
• Functional bladder capacity, 24-hour urine output, nocturnal output, age, and BMI were identified as key predictors.
• The model achieved excellent predictability, comparable to models with more determinants.

Conclusions:

• The developed multivariate model offers significant insights into the prediction of nocturia.
• The model's ability to simulate treatment effects provides a basis for personalized combination therapy strategies.
• Key factors identified can guide clinical assessment and therapeutic interventions for nocturia.