Machine Learning for Urodynamic Detection of Detrusor Overactivity

Hobbs, Kevin T.; Choe, Nathaniel; Aksenov, Leonid; Reyes, Lourdes; Aquino, Wilkins; Routh, Jonathan C.; Hokanson, Jim

doi:10.1016/j.urology.2021.09.027

Cited by 25 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior studies have successfully applied machine learning algorithms to VUDS tracings to identify detrusor overactivity. 11,12 However, our model is the first to assess a composite of a VUDS study (pressure-volume relationship and fluoroscopic images) and translate these data into a clinically important outcome-severity of bladder dysfunction. We chose this outcome because of its important role in predicting renal deterioration in patients with neurogenic bladder.…”

Section: Discussionmentioning

confidence: 99%

“…Second, we considered only the first 10 minutes of each study for the urodynamic tracing pressure-volume models as has been used in prior machine learning studies evaluating urodynamics tracings. 11,12 Third, we included electromyography data in the 75% EBC urodynamic tracing pressure-volume model. Next, we built a baseline random forest model that used only pressure measurements at 25%, 50%, and 75% of EBC to predict degree of bladder dysfunction.…”

Section: Sensitivity Analysesmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning of Videourodynamics to Classify Bladder Dysfunction Severity in Patients With Spina Bifida

et al. 2023

View full text Add to dashboard Cite

Purpose:Urologists rely heavily on videourodynamics to identify patients with neurogenic bladders who are at risk of upper tract injury, but their interpretation has high interobserver variability. Our objective was to develop deep learning models of videourodynamics studies to categorize severity of bladder dysfunction.Materials and Methods:We performed a cross-sectional study of patients aged 2 months to 28 years with spina bifida who underwent videourodynamics at a single institution between 2019 and 2021. The outcome was degree of bladder dysfunction, defined as none/mild, moderate, and severe, defined by a panel of 5 expert reviewers. Reviewers considered factors that increase the risk of upper tract injury, such as poor compliance, elevated detrusor leak point pressure, and detrusor sphincter dyssynergia, in determining bladder dysfunction severity. We built 4 models to predict severity of bladder dysfunction: (1) a random forest clinical model using prospectively collected clinical data from videourodynamics studies, (2) a deep learning convolutional neural network of raw data from the volume-pressure recordings, (3) a deep learning imaging model of fluoroscopic images, (4) an ensemble model averaging the risk probabilities of the volume-pressure and fluoroscopic models.Results:Among 306 videourodynamics studies, the accuracy and weighted kappa of the ensemble model classification of bladder dysfunction when at least 75% expected bladder capacity was reached were 70% (95% CI 66%,76%) and 0.54 (moderate agreement), respectively. The performance of the clinical model built from data extracted by pediatric urologists was the poorest with an accuracy of 61% (55%, 66%) and a weighted kappa of 0.37.Conclusions:Our models built from urodynamic pressure-volume tracings and fluoroscopic images were able to automatically classify bladder dysfunction with moderately high accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Sensitivity Analysesmentioning

confidence: 99%

Deep Learning of Videourodynamics to Classify Bladder Dysfunction Severity in Patients With Spina Bifida

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The ML model presented an overall accuracy of 81.3%, a sensitivity of 76.9%, and a specificity of 81.4% in detecting detrusor activity. A ML algorithm to detect detrusor overactivity in patients with spina bifida was developed using data windowing, dimensionality reduction, and SVM techniques [92]. In total, 805 urodynamic studies from 546 patients were used to train the model, which achieved a good performance in both time-based (AUC 0.919, sensitivity of 84.2% and specificity of 86.4%) and frequency-based (AUC 0.905, sensitivity of 68.3% and specificity of 92.9%) approaches.…”

Section: Urogynecologymentioning

confidence: 99%

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

Brandão,

Mendes,

Martins

et al. 2024

JCM

View full text Add to dashboard Cite

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.

show abstract

“…2 Machine learning is a rapidly growing subject of study across medical disciplines and has begun to gain favor as a potential tool for standardizing VUDS interpretation. 3 However, in pediatric urology, this technology remains in its early stages with limited practical clinical application.…”

mentioning

confidence: 99%