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

Abstract

Summary Purpose The main objective of our study was to determine which combination of modifiable and non‐modifiable parameters that could discriminate patients with nocturia from those without nocturia. This was a post‐hoc analysis of 3 prospective, observational studies conducted in Ghent University. Participants completed frequency volume chart (FVC) to compare characteristics between patients with and without nocturia. Method This was a post hoc analysis of three prospective, observational studies conducted in Ghent University. Participants completed frequency volume chart (FVC) to compare characteristics between adults with and without nocturia. Study 1: adults with and without nocturia (n = 148); Study 2: patients ≥65 years with and without nocturnal LUTS (n = 54); Study 3: menopausal women before and after hormone replacement therapy (n = 43). All eligible patients (n = 183) completed a FVC during 24 hours (n = 13), 48 hours (n = 30) or 72 hours (n = 140). The combination of algorithms and number of determinants obtaining the best average area under the receiver operating curve (AUC‐ROC) led to the final model. Differences between groups were assessed using the AUC‐ROC and Mann‐ Whitney‐Wilcoxon tests. Holm corrections were applied for multiple statistical testing. Also, the stability of the feature selection was evaluated. Results The best discrimination was obtained when 13 determinants were included. However, a logistic regression model based on seven determinants selected with random forest had comparable discrimination including an optimal signature stability. It was able to discriminate almost perfectly between nights with and without nocturia. Conclusion Relevant information to accomplish the excellent predictability of the model is; functional bladder capacity, 24 hours urine output, nocturnal output, age, BMI. The multivariate model used in this analysis provides new insights into combination therapy as it allows simulating the effect of different available treatment modalities and its combinations.

Management of Nocturia and Nocturnal Polyuria

“…The potential of algorithms to substitute definitions for the diagnosis of nocturia has been explored in a post-hoc analysis of 3 prospective, observational studies. 21 The analysis showed that cut-off values depending on multiple factors could be replaced by statistical models that could possibly render voiding diaries redundant for many patients. The multivariate model that was used consisted of factors including voided volume, 24-hour diuresis, age, and body mass index; however, the model requires confirmation in other databases and ideally in databases that include a therapeutic arm.…”

Assessment of the Most Impactful Combination of Factors Associated with Nocturia and to Define Nocturnal Polyuria by Multivariate Modelling

“…This suggests multiple causes of nocturia in co-existence, and therefore, the pathophysiology of nocturia should not be reduced to one of a handful of basic mechanisms. Because of the multifactorial etiology, we hypothesized that statistical multivariate modeling [15] may be relevant as a tool to explain clinically significant nocturia. We aimed to determine which factors were accurately associated with nocturia.…”

It's All About the Urine, Dad

“…Olesen and others have made an ambitious attempt in the next article titled Development of a Multivariate Prediction Model for Nocturia, Based on Urinary Tract Etiologies . I applaud this effort and the many variables that they evaluated, but even more so I appreciate their honesty.…”