Predictive Factors for High Post-void Residual Volume in Older Females After OnabotulinumA Treatment for Severe Overactive Bladder Using a Machine Learning Model

Nobuo Okui; Tadashi Ikegami; Tatsuo Hashimoto; Yuko Kouno; Kaori Nakano; Machiko Aurora Okui

doi:10.7759/cureus.42668

Predictive Factors for High Post-void Residual Volume in Older Females After OnabotulinumA Treatment for Severe Overactive Bladder Using a Machine Learning Model

Cureus. 2023 Jul 29;15(7):e42668. doi: 10.7759/cureus.42668. eCollection 2023 Jul.

Authors

Nobuo Okui¹, Tadashi Ikegami², Tatsuo Hashimoto³, Yuko Kouno⁴, Kaori Nakano⁴, Machiko Aurora Okui⁵

Affiliations

¹ Dentistry, Kanagawa Dental University, Kanagawa, JPN.
² Diagnostic Imaging, Kanagawa Dental University, Kanagawa, JPN.
³ Internal Medicine, Kanagawa Dental University, Kanagawa, JPN.
⁴ Urology, Dr Okui's Urogynecology and Urology, Kanagawa, JPN.
⁵ Urogynecology, Yokosuka Urogynecology Clinic, Kanagawa, JPN.

Abstract

Introduction Intravesical onabotulinumA injection is actively used for the treatment of overactive bladder (OAB). However, it occasionally results in significant post-void residual urine (PVR) volume, which can lead to complications and can further impair the activities of daily living in older people. Therefore, this study aimed to identify the predictors of a high post-onabotulinumA injection PVR volume in older women with severe OAB. Methods An observational study was conducted on older women who had previously received intravesical onabotulinumA injections to treat OAB between 2020 and 2022. Urodynamic studies and symptom assessments were conducted, and machine learning models, including random forest and support vector machine (SVM) models, were developed using the R code generated by Chat Generative Pre-trained Transformer 4 (ChatGPT, OpenAI, San Francisco, USA). Results Among 128 patients with OAB, 23 (18.0%) had a PVR volume of > 200 mL after receiving onabotulinumA injections. The factors associated with a PVR volume of > 200 mL were investigated using univariate and multivariate analyses. Age, frailty, OAB-wet, daytime frequency, and nocturia were significant predictors. Random forest analysis highlighted daytime frequency, frailty, and voiding efficiency as important factors. An SVM model incorporating daytime frequency, frailty, and voiding efficiency improved PVR volume prediction. Logit(p) estimation yielded an area under the receiver operating characteristic curve of 0.926294. Conclusion The study found daytime frequency, frailty, and voiding inefficiency to be significant factors associated with a PVR volume of > 200 mL, in older women with severe OAB. Utilizing advanced machine learning techniques and following the guidance of ChatGPT, this research emphasizes the relevance of considering multiple intersecting factors for predicting PVR volume. The findings contribute to our understanding of onabotulinumA injection treatment for OAB and support evidence-based decision-making using readily available information.

Keywords: ai & robotics in healthcare; frailty; machine learning models; onabotulinuma; overactive bladder; post-void residual volume; random forest; support vector machine; urodynamic studies.