Development and Validation of a Machine Learning Algorithm for Predicting Response to Anticholinergic Medications for Overactive Bladder Syndrome

Applications of machine learning in urodynamics: A narrative review

BACKGROUND

Machine learning algorithms as a research tool, including traditional machine learning and deep learning, are increasingly applied to the field of urodynamics. However, no studies have evaluated how to select appropriate algorithm models for different urodynamic research tasks.

METHODS

We undertook a narrative review evaluating how the published literature reports the applications of machine learning in urodynamics. We searched PubMed up to December 2023, limited to the English language. We selected the following search terms: artificial intelligence, machine learning, deep learning, urodynamics, and lower urinary tract symptoms. We identified three domains for assessment in advance of commencing the review. These were the applications of urodynamic studies examination, applications of diagnoses of dysfunction related to urodynamics, and applications of prognosis prediction.

RESULTS

The machine learning algorithm applied in the field of urodynamics can be mainly divided into three aspects, which are urodynamic examination, diagnosis of urinary tract dysfunction and prediction of the efficacy of various treatment methods. Most of these studies were single-center retrospective studies, lacking external validation, requiring further validation of model generalization ability, and insufficient sample size. The relevant research in this field is still in the preliminary exploration stage; there are few high-quality multi-center clinical studies, and the performance of various models still needs to be further optimized, and there is still a distance from clinical application.

CONCLUSIONS

At present, there is no research to summarize and analyze the machine learning algorithms applied in the field of urodynamics. The purpose of this review is to summarize and classify the machine learning algorithms applied in this field and to guide researchers to select the appropriate algorithm model for different task requirements to achieve the best results.

Revolutionizing Women's Health: A Comprehensive Review of Artificial Intelligence Advancements in Gynecology

Artificial intelligence has yielded remarkably promising results in several medical fields, namely those with a strong imaging component. Gynecology relies heavily on imaging since it offers useful visual data on the female reproductive system, leading to a deeper understanding of pathophysiological concepts. The applicability of artificial intelligence technologies has not been as noticeable in gynecologic imaging as in other medical fields so far. However, due to growing interest in this area, some studies have been performed with exciting results. From urogynecology to oncology, artificial intelligence algorithms, particularly machine learning and deep learning, have shown huge potential to revolutionize the overall healthcare experience for women's reproductive health. In this review, we aim to establish the current status of AI in gynecology, the upcoming developments in this area, and discuss the challenges facing its clinical implementation, namely the technological and ethical concerns for technology development, implementation, and accountability.

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

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.

A treatment prediction strategy for overactive bladder using a machine learning algorithm that utilized data from the FAITH study

AIMS

To use machine learning algorithms to develop a model to accurately predict treatment responses to mirabegron or antimuscarinic agents in patients with overactive bladder (OAB), using real-world data from the FAITH registry (NCT03572231).

METHODS

The FAITH registry data included patients who had been diagnosed with OAB symptoms for at least 3 months and were due to initiate monotherapy with mirabegron or any antimuscarinic. For the development of the machine learning model, data from patients were included if they had completed the 183-day study period, had data for all timepoints and had completed the overactive bladder symptom scores (OABSS) at baseline and end of study. The primary outcome of the study was a composite outcome combining efficacy, persistence, and safety outcomes. Treatment was deemed "more effective" if the composite outcome criteria for "successful," "no treatment change," and "safe" were met, otherwise treatment was deemed "less effective." To explore the composite algorithm, a total of 14 clinical risk factors were included in the initial data set and a 10-fold cross-validation procedure was performed. A range of machine learning models were evaluated to determine the most effective algorithm.

RESULTS

In total, data from 396 patients were included (266 [67.2%] treated with mirabegron and 130 [32.8%] treated with an antimuscarinic). Of these, 138 (34.8%) were in the "more effective" group and 258 (65.2%) were in the "less effective" group. The groups were comparable in terms of their characteristic distributions across patient age, sex, body mass index, and Charlson Comorbidity Index. Of the six models initially selected and tested, the decision tree (C5.0) model was chosen for further optimization, and the receiver operating characteristic of the final optimized model had an area under the curve result of 0.70 (95% confidence interval: 0.54-0.85) when 15 was used for the min n parameter.

CONCLUSIONS

This study successfully created a simple, rapid, and easy-to-use interface that could be further refined to produce a valuable educational or clinical decision-making aid.

Current developments in artificial intelligence from obstetrics and gynecology to urogynecology

In today's medical practice clinicians need to struggle with a huge amount of data to improve the outcomes of the patients. Sometimes one clinician needs to deal with thousands of ultrasound images or hundred papers of laboratory results. To overcome this shortage, computers get in help of human beings and they are educated under the term "artificial intelligence." We were using artificial intelligence in our daily lives (i.e., Google, Netflix, etc.), but applications in medicine are relatively new. In obstetrics and gynecology, artificial intelligence models mostly use ultrasound images for diagnostic purposes but nowadays researchers started to use other medical recordings like non-stress tests or urodynamics study results to develop artificial intelligence applications. Urogynecology is a developing subspecialty of obstetrics and gynecology, and articles about artificial intelligence in urogynecology are limited but in this review, we aimed to increase clinicians' knowledge about this new approach.

National Trends in Third-Line Treatment for Overactive Bladder Among Commercially Insured Women, 2010-2019

OBJECTIVE

To investigate whether the 2010 introduction of percutaneous tibial nerve stimulation and the 2013 introduction of intradetrusor onabotulinumtoxinA were associated with an increase in overall utilization of third-line treatments.

METHODS

Using medical claims data from IBM Marketscan database 2010-2019, diagnosis codes were used to identify adult women with overactive bladder. Procedure codes were used to identify third-line treatments. The annual proportion of patients receiving third-line treatments was calculated, as well as the proportion of each treatment received. These were modeled as a function of treatment year using linear regression; a regression coefficient significantly different from 0 was considered evidence of a significant change in utilization over time.

RESULTS

We identified 3,067,515 unique individuals with a diagnosis of overactive bladder, including 14,652 who initiated third-line treatments. The annual percentage of women with overactive bladder who initiated third-line treatment was 0.18% and did not change significantly over 10 years (P = .82). However, the proportion receiving sacral neuromodulation decreased significantly (P <.001), with a compensatory increase in intradetrusor onabotulinumtoxinA. Within 6 years of its introduction, onabotulinumtoxinA accounted for almost half of third-line treatments initiated.

CONCLUSION

Overall, third-line therapies for non-neurogenic overactive bladder are utilized infrequently among privately insured women. Over the past decade, the introduction of new treatment options has led to a shift in the type of treatment initiated, rather than to an increase in the overall utilization of third-line therapies.

Mitigating urinary incontinence condition using machine learning

Background

Urinary incontinence (UI) is the inability to completely control the process of releasing urine. UI presents a social, medical, and mental issue with financial consequences.

Objective

This paper proposes a framework based on machine learning for predicting urination time, which can benefit people with various degrees of UI.

Method

A total of 850 data points were self-recorded by 51 participants to investigate how different factors impact urination time. The participants were instructed to record input data (such as the time of consumption and the number of drinks) and output data (i.e., the time the individual urinated). Other factors, such as age and BMI, were also considered. The study was conducted in two phases: (1) data was prepared for modeling, including missing values, data encoding, and scaling; and (2) a classification model was designed with four output classes of the next urination time: <  = 30 min, 31–60 min, 61–90 min, > 90 min. The model was built in two steps: (1) feature selection and (2) model training and testing. Feature selection methods such as lasso regression, decision tree, random forest, and chi-square were used to select the best features, which were then used to train an extreme gradient boosting (XGB) algorithm model to predict the class of the next urination time.

Result

The feature selection steps resulted in nine features considered the most important features affecting UI. The accuracy, precision, recall, and F1 score of the XGB predictive model are 0.70, 0.73, 0.70, and 0.71, respectively.

Conclusion

This research is the first step in developing a machine learning model to predict when a person will need to urinate. A precise predictive instrument can enable healthcare providers and caregivers to assist people with various forms of UI in reliable, prompted voiding. The insights from this predictive model can allow future apps to go beyond current UI-related apps by predicting the time of urination using the most relevant factors that impact voiding frequency.

Introduction to Machine Learning in Obstetrics and Gynecology

In the digital age of the 21st century, we have witnessed an explosion in data matched by remarkable progress in the field of computer science and engineering, with the development of powerful and portable artificial intelligence-powered technologies. At the same time, global connectivity powered by mobile technology has led to an increasing number of connected users and connected devices. In just the past 5 years, the convergence of these technologies in obstetrics and gynecology has resulted in the development of innovative artificial intelligence-powered digital health devices that allow easy and accurate patient risk stratification for an array of conditions spanning early pregnancy, labor and delivery, and care of the newborn. Yet, breakthroughs in artificial intelligence and other new and emerging technologies currently have a slow adoption rate in medicine, despite the availability of large data sets that include individual electronic health records spanning years of care, genomics, and the microbiome. As a result, patient interactions with health care remain burdened by antiquated processes that are inefficient and inconvenient. A few health care institutions have recognized these gaps and, with an influx of venture capital investments, are now making in-roads in medical practice with digital products driven by artificial intelligence algorithms. In this article, we trace the history, applications, and ethical challenges of the artificial intelligence that will be at the forefront of digitally transforming obstetrics and gynecology and medical practice in general.

Delivering patient-centered care through shared decision making in overactive bladder

Introduction

Men and women living with overactive bladder (OAB) face many treatment decisions as they progress through the treatment pathway. Decisions to pursue specific therapies are highly preference sensitive and ideal for shared decision making (SDM). The aim of this narrative review is to provide urologists with a practical summary of methods to elicit preferences and facilitate SDM to promote patient‐centered care for OAB.

Methods

We explore OAB as a preference sensitive condition through a review of treatment outcomes and present available data on prediction tools, patient preferences, and decision aids. We propose a paradigm for applying Everyday SDM to OAB care.

Results

Clinical outcome data points to equipoise (balanced outcomes) between options for first‐, second‐, and third‐line OAB therapies, making OAB preference sensitive and appropriate for SDM. Methods to personalize care through individualized outcome prediction calculators and tools to elicit patient preferences are emerging. While patient information about OAB is readily available, we identified few OAB decision aids that facilitate patient preference elicitation and SDM.

Conclusions

OAB is a preference sensitive condition, where treatment is largely based on the patient's preferences and values. SDM is an ideal approach to supporting patients through these treatment decisions. We propose the application of Everyday SDM, a personalized, clinically efficient methodology as a method to support patient‐centered OAB care.

Machine learning methods to predict presence of residual cancer following hysterectomy

Surgical management for gynecologic malignancies often involves hysterectomy, often constituting the most common gynecologic surgery worldwide. Despite maximal surgical and medical care, gynecologic malignancies have a high rate of recurrence following surgery. Current machine learning models use advanced pathology data that is often inaccessible within low-resource settings and are specific to singular cancer types. There is currently a need for machine learning models to predict non-clinically evident residual disease using only clinically available health data. Here we developed and tested multiple machine learning models to assess the risk of residual disease post-hysterectomy based on clinical and operative parameters. Data from 3656 hysterectomy patients from the NSQIP dataset over 14 years were used to develop models with a training set of 2925 patients and a validation set of 731 patients. Our models revealed the top postoperative predictors of residual disease were the initial presence of gross abdominal disease on the diaphragm, disease located on the bowel mesentery, located on the bowel serosa, and disease located within the adjacent pelvis prior to resection. There were no statistically significant differences in performances of the top three models. Extreme gradient Boosting, Random Forest, and Logistic Regression models had comparable AUC ROC (0.90) and accuracy metrics (87–88%). Using these models, physicians can identify gynecologic cancer patients post-hysterectomy that may benefit from additional treatment. For patients at high risk for disease recurrence despite adequate surgical intervention, machine learning models may lay the basis for potential prospective trials with prophylactic/adjuvant therapy for non-clinically evident residual disease, particularly in under-resourced settings.

Artificial Intelligence Applications in Urology: Reporting Standards to Achieve Fluency for Urologists

The growth and adoption of artificial intelligence has led to impressive results in urology. As artificial intelligence grows more ubiquitous, it is important to establish artificial intelligence literacy in the workforce. To this end, we present a narrative review of the literature of artificial intelligence and machine learning in urology and propose a checklist of reporting standards to improve readability and evaluate the current state of the literature. The listed article demonstrated heterogeneous reporting of methodologies and outcomes, limiting generalizability of research. We hope that this review serves as a foundation for future evaluation of medical research in artificial intelligence.

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

Adverse drug events (ADEs) represent one of the most prevalent types of health-care-related harm, and there is substantial room for improvement in the way that they are currently predicted and detected. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged to reduce the frequency of ADEs. We focused on modern machine learning techniques and natural language processing. 78 articles were included in the scoping review. Studies were heterogeneous and applied various AI techniques covering a wide range of medications and ADEs. We identified several key use cases in which AI could contribute to reducing the frequency and consequences of ADEs, through prediction to prevent ADEs and early detection to mitigate the effects. Most studies (73 [94%] of 78) assessed technical algorithm performance, and few studies evaluated the use of AI in clinical settings. Most articles (58 [74%] of 78) were published within the past 5 years, highlighting an emerging area of study. Availability of new types of data, such as genetic information, and access to unstructured clinical notes might further advance the field.

Artificial intelligence in functional urology: how it may shape the future

PURPOSE OF REVIEW

The aim of the present manuscript is to provide an overview on the current state of artificial intelligence (AI) tools in either decision making, diagnosis, treatment options, or outcome prediction in functional urology.

RECENT FINDINGS

Several recent studies have shed light on the promising potential of AI in functional urology to investigate lower urinary tract dysfunction pathophysiology but also as a diagnostic tool by enhancing the existing evaluations such as dynamic magnetic resonance imaging or urodynamics. AI may also improve surgical education and training because of its automated performance metrics recording. By bringing prediction models, AI may also have strong therapeutic implications in the field of functional urology in the near future. AI may also be implemented in innovative devices such as e-bladder diary and electromechanical artificial urinary sphincter and could facilitate the development of remote medicine.

SUMMARY

Over the past decade, the enthusiasm for AI has been rising exponentially. Machine learning was well known, but the increasing power of processors and the amount of data available has provided the platform for deep learning tools to expand. Although the literature on the applications of AI technology in the field of functional urology is relatively sparse, its possible uses are countless especially in surgical training, imaging, urodynamics, and innovative devices.

Anticholinergic prescribing pattern changes of urogynecology providers in response to evidence of potential dementia risk

INTRODUCTION AND HYPOTHESIS

Recent publications show an association between exposure to anticholinergic medications and the risk of developing dementia. We hypothesized that urogynecology providers have changed their overactive bladder syndrome treatment as a result of this literature.

METHODS

This was an anonymous, cross-sectional, web-based survey of American Urogynecologic Society members. Survey questions queried awareness of the referenced literature, prescribing practices, the impact of insurance on treatment plans, and demographics. Our primary outcome measured the change in prescribing practice in response to literature linking anticholinergic medications with the risk of dementia. Descriptive statistics were used.

RESULTS

A total of 222 urogynecology providers completed the survey. Nearly all respondents (99.1%) were aware of the recent literature, and, as a result, 90.5% reported changing their practice. Prior to the publication of recent literature, a "non-CNS-sparing" anticholinergic (e.g., oxybutynin) was most commonly prescribed (64.4%), whereas after the literature was published, this shifted to ß₃-adrenoceptor agonists (58.5%, p < 0.001). A majority of respondents (96.6%) reported that insurance restrictions led to a change in treatment for some patients, with 73.5% describing the prior-authorization process as difficult. Many providers (61.8%) reported that a trial of anticholinergics was required by insurance companies prior to authorizing mirabegron.

CONCLUSIONS

The recent literature associating anticholinergic medications with the development of dementia has changed practice patterns among survey respondents, with a shift away from anticholinergic medications and toward ß₃-adrenoceptor agonists. The majority of respondents report insurance barriers to non-anticholinergic therapies, resulting in alteration of their preferred practices.