Automated quantification of low amplitude rhythmic contractions (LARC) during real-world urodynamics identifies a potential detrusor overactivity subgroup

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.

An automatic diagnostic system for the urodynamic study applying in lower urinary tract dysfunction

OBJECTIVE

To establish an automatic diagnostic system based on machine learning for preliminarily analysis of urodynamic study applying in lower urinary tract dysfunction (LUTD).

METHODS

The eight most common conditions of LUTDs were included in the present study. A total of 527 eligible patients with complete data, from the year of 2015 to 2020, were enrolled in this study. In total, two global parameters (patients' age and sex) and 13 urodynamic parameters were considered to be the input for machine learning algorithms. Three machine learning approaches were applied and evaluated in this study, including Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM).

RESULTS

By applying machine learning algorithms into the 8 common LUTDs, the DT models achieved the AUC of 0.63-0.98, the LR models achieved the AUC of 0.73-0.99, and the SVM models achieved the AUC of 0.64-1.00. For mutually exclusive diagnoses of underactive detrusor and acontractile detrusor, we developed a classification model that classifies the patients into either of these two diseases or double-negative class. For this classification method, the DT models achieved the AUC of 0.82-0.85 and the SVM models achieved the AUC of 0.86-0.90. Among all these models, the LR and the SVM models showed better performance. The best model of these diagnostic tasks achieved an average AUC of 0.90 (0.90 ± 0.08).

CONCLUSIONS

An automatic diagnostic system was developed using three machine learning models in urodynamic studies. This automated machine learning process could lead to promising assistance and enhancements of diagnosis and provide more useful reference for LUTD treatment.

Objective Quantification of Detrusor Overactivity Using Spectral Measures of Cystometry Data

OBJECTIVE

To develop scalable objective methods for differentiating patients with and without detrusor overactivity (DO) using quantitative Fast Fourier Transform (FFT)-based measures and routinely captured cystometry data.

METHODS

Retrospective cystometry data were collected as prevoid vesical and abdominal pressure signals from 18 DO and 10 SUI (non-DO) cystometry recordings. Data were filtered and divided into two equal-duration segments, Early and Late Fill, representing the first and second halves of filling. FFT was applied, followed by subtraction of abdominal spectra from vesical spectra. Spectral Power (SP) and Weighted Average Frequency (WAF) measures were calculated for each segment spectra within 1-6 cycles min^-1.

RESULTS

Compared to non-DO, the mean SP was significantly higher in DO patients for both Early and Late Fill segments. WAF was significantly lower in DO patients for both segments. Changes in spectral pressures appeared to be linked to the presence of detrusor contractions (DCs) and were especially visible when DCs were present in the Early Fill segments of cystometry.

CONCLUSION

FFT-based spectral measures derived from routinely captured cystometry data are significantly different between DO and non-DO patients. This preliminary method is clinically scalable and can be further developed to facilitate the detection of DO, classify disease phenotype, and capture therapeutic efficacy.

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.

Measurement and Quantification of Cystometric Bladder Pressure Spectra in an in-vivo Sheep Model: A Feasibility Study

Cystometry is a standard procedure for the clinical evaluation of lower urinary tract disorders such as detrusor overactivity (DO). The utility of this procedure for DO diagnosis, however, is limited by the use of physician observations of bladder contractions and patient reported filling sensations. Although a number of preclinical and clinical studies have observed and developed methods to characterize bladder pressure dynamics, these techniques have not been scaled for routine clinical application. The goal of this study was to evaluate the feasibility of using an awake large animal model to characterize bladder pressure signals from cystometry as bladder pressure spectra and quantify changes in spectra during bladder filling. Two adult female sheep were trained for quiet catheterization in a minimally supportive sling and underwent multiple awake and limited anesthetized cystometry tests. In each test, bladder pressure was measured during continuous filling or with filling that included periods of no filling (constant volume). A Fast-Fourier Transform (FFT)-based algorithm was then used to quantify changes in pre-voiding bladder pressure spectra. Changes in Spectral Power (SP) and Weighted Average Frequency (WAF) were calculated during filling. To visualize temporal changes in bladder pressure frequencies during filling, Continuous Wavelet Transform (CWT) was also applied to cystometry data. Results showed that a significant increase in SP and decrease in WAF were both associated with bladder filling. However, during awake constant volume tests, SP significantly increased while changes in WAF were nonsignificant. Anesthetized tests demonstrated comparable values to awake tests for WAF while SP was considerably reduced. CWT facilitated visualization of spectral changes associated with SP and WAF as well as apparent non-voiding contractions during awake and anesthetized volume tests.Clinical Relevance-Bladder pressure spectra during cystometry are detectable in sheep and the changes during filling are similar to those observed in human retrospective clinical data. Sheep cystometry may be a valuable testbed for establishing and testing quantitative pressure spectra for use as a clinical diagnostic tool.

Detrusor overactivity assessment using ultrasound bladder vibrometry

Objective. Detrusor overactivity (DO) is a urodynamic observation characterized by fluctuations in detrusor pressure (Pdet) of the bladder. Although detecting DO is important for the management of bladder symptoms, the invasive nature of urodynamic studies (UDS) makes it a source of discomfort and morbidity for patients. Ultrasound bladder vibrometry (UBV) could provide a direct and noninvasive means of detecting DO, due to its sensitivity to changes in elasticity and load in the bladder wall. In this study, we investigated the feasibility and applying UBV toward detecting DO.Approach. UBV and urodynamic study (UDS) measurements were collected in 76 neurogenic bladder patients (23 with DO). Timestamped group velocity squared (cg2) data series were collected from UBV measurements. ConcurrentPdetdata series were identically analyzed for comparison and validation. A processing approach is developed to separate transient fluctuations in the data series from the larger trend of the data and a DO index is proposed for characterizing the transient peaks observed in the data.Main Results.Applying the DO index as a classifier for DO produced sensitivities and specificities of 0.70 and 0.75 forcg2data series and 0.70 and 0.83 forPdetdata series respectively.Significance. It was found that DO can be feasibly detected from data series of timestamped UBV measurements. Collectively, these initial results are promising, and further refinement to the UBV measurement process is likely to improve and clarify its capabilities for noninvasive detection of DO.

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.

Biomechanics of the urinary bladder: spontaneous contraction activity and micromotions related to accommodation

PURPOSE

Knowledge of the fundamental properties of the urinary bladder is required to better understand its pathological conditions. Research on the passive and active properties of the bladder during stretching and contraction is important. The bladder is not passive during the filling phase. Spontaneous contractions are observed as variations in pressure, which are mostly related to urgency and/or incontinence and sometimes to pelvic pain. The purpose of this study was to describe distributed spontaneous contractions and micromotions (MMs), which besides being related to symptoms, are crucial in the physiological process of accommodation, and to express accommodation in a concept.

METHOD

After describing MMs in the bladder wall as the type of spontaneous activity that may not be reflected in detrusor pressure and as a source of afferent nerve activity, its biomechanical effects are considered. In a simple mechanical model, contractions and elongations are related to the plastic elongated state of the bladder. The changing distributed character of contractions and elongations in the bladder wall is represented in a modular scheme.

RESULTS

Distributed transient contractions and MMs yield a balanced dynamic plastic state of the regions of the bladder wall. An almost constant detrusor pressure can be attributed to the active accommodation of detrusor pressure to changes in bladder volume.

CONCLUSION

Localized contractile activity and MMs that change the plastic elongated state of varying bladder regions are biomechanically effective in the active accommodation of detrusor pressure to changes in bladder volume. According to this concept, autonomous bladder wall activity as a source of nerve activity, also is crucial for active accommodation.

Bladder wall micromotion measured by non-invasive ultrasound: initial results in women with and without overactive bladder

OBJECTIVE

Rhythmic contractions of the bladder wall during filling result from the synchronization of bladder wall micromotion and are often observed in the urodynamic tracings of individuals with urinary overactive bladder (OAB). This study's objective was to develop a novel, non-invasive method to measure bladder wall micromotion and to conduct an initial study to test the hypothesis that elevated micromotion is associated with OAB.

METHODS

This prospective study enrolled women with OAB and asymptomatic volunteers as measured by the ICIQ-OAB survey. After filling the bladder to 40% cystometric capacity, 85 second cine-loops were obtained using a GE Voluson E8 ultrasound system with an 8 MHz curved, abdominal probe. A custom correlation-based texture tracking MATLAB algorithm was used to measure changes in the bladder wall thickness over time and correlate with changes in vesical pressure. Significant bladder wall micromotion was defined as changes in wall thickness with amplitudes higher than 0.1 mm in the frequency range of 1.75-6 cycles/minute as calculated from Fast Fourier Transform (FFT) analysis. The micromotion algorithm was tested on 30 women including 17 with OAB and 13 asymptomatic volunteers.

RESULTS

Micromotion was identified in 41% of subjects with OAB and 0% of asymptomatic volunteers, indicating a significant association of micromotion with OAB (Fisher's exact test, P=0.010). Micromotion was also found to have a significant association with a clinical diagnosis of detrusor overactivity (Fisher's exact test, P=0.031). Frequencies with elevated micromotion correlated with frequencies of vesical pressure fluctuations.

CONCLUSIONS

The feasibility of a non-invasive method to measure bladder wall micromotion was demonstrated using transabdominal anatomical motion mode (M-mode) ultrasound. Presence of micromotion was significantly associated with OAB and with urodynamic-identified rhythm.

Comparative-fill urodynamics in individuals with and without detrusor overactivity supports a conceptual model for dynamic elasticity regulation

AIMS

Dynamic elasticity was previously identified in individuals with overactive bladder (OAB) using comparative-fill urodynamics (UD) and is a biomechanical mechanism for acutely regulating detrusor wall tension. On the basis of this data, a conceptual model of dynamic elasticity regulation mediated through a balance of passive mechanisms and active contractions was constructed. The present study tested this model by determining whether individuals with detrusor overactivity (DO) exhibit less dynamic elasticity than individuals without DO.

METHODS

Individuals with and without urgency based on International Consultation on Incontinence Questionnaire-OAB surveys were prospectively enrolled in a comparative-fill UD study. An initial fill defined the presence or absence of DO and determined cystometric capacity. Three additional fills were employed with either passive emptying via a catheter or active voiding. To identify dynamic elasticity, average filling pressures (P_ves ) were compared for fill 1 (before strain softening), fill 2 (after strain softening), and fill 3 (after active void). A dynamic elasticity index was defined.

RESULTS

From 28 participants, those without DO showed decreased P_ves during filling after strain softening and restored P_ves during filling following active voiding, revealing dynamic elasticity. Participants with DO did not show dynamic elasticity. A dynamic elasticity index less than 1.0 cmH₂ O/40% capacity was identified in 2 out of 13 participants without DO and 9 out of 15 with DO, revealing a significant association between DO and reduced/absent dynamic elasticity (P = .024).

CONCLUSIONS

This study supports a conceptual model for dynamic elasticity, a mechanism to acutely regulate detrusor wall tension through a balance of competing active contractile and passive strain mechanisms. Improved understanding of this mechanistic model may help us to identify novel treatment strategies for OAB.

Are there different patterns of detrusor overactivity which are clinically relevant? ICI-RS 2018

INTRODUCTION

Different patterns of detrusor overactivity (DO) have been described and included in several standardization terminology documents. However, it is unclear if these different patterns have any clinical significance.

METHODS

This is a report of the proceedings of Proposal 3: "Are there different patterns of detrusor overactivity which are clinically relevant?" from the annual International Consultation on Incontinence-Research Society (ICIRS) meeting, which took place from 14 to 16 June 2018, in Bristol, UK.

RESULTS

We have collected and discussed, as a committee, the evidence about different urodynamic (UD) patterns of detrusor overactivity and their potential clinical significance. We reviewed the important previous basic research and clinical studies and compiled summaries. The discussion focused on clinical relevance of different UD patterns of DO and what further research is required.

CONCLUSIONS

There are several UD definitions of patterns of detrusor overactivity, however the clinical relevance of these definitions remains unclear. Future research should concentrate on defining the pattern of DO in relation to clinical diagnosis, gender, age, and treatment outcomes.

New Diagnostics for Male Lower Urinary Tract Symptoms

PURPOSE OF REVIEW

Lower urinary tract symptoms (LUTS) is a common constellation of symptoms that affect the aging male population with an astonishing prevalence. New technology and new uses of established technology are being used to help further evaluate LUTS in the male population and help guide treatment options. This review focuses on the developments and future directions in diagnostic modalities for evaluation of male LUTS, focusing on evaluation of both the filling and voiding phases of micturition.

RECENT FINDINGS

New techniques in evaluating the voiding phase include penile cuff test, external pressure sensing condom catheter, ultrasound measurement of detrusor wall thickness, ultrasound measurement of intravesical prostatic protrusion, doppler ultrasound and NIRS technology. Evaluation of the filling phase is still undergoing much development and requires additional validation studies. The techniques undergoing evaluation include sensation meters during UDS, assessing bladder micromotion and wall rhythm, assessing detrusor wall biomechanics, ultrasound measurement of detrusor wall thickness, pelvic doppler ultrasound, as well as functional brain imaging including fNIRS and fMRI.

SUMMARY

The development of novel, non-invasive, diagnostic tools have the potential for better evaluation of LUTS with earlier and enhanced treatments. This will likely improve the quality of life for men with LUTS.

Pharmacological modulation of the spatiotemporal disposition of micromotions in the intact resting urinary bladder of the rabbit; their pattern is under both myogenic and autonomic control

OBJECTIVES

To explore and characterize the disposition and dynamics of micromotions in the wall of the intact resting teradotoxinized urinary bladder of the rabbit before and after the administration of adrenergic and cholinergic pharmaceutical agents.

METHODS

Spatiotemporal maps and related intravesical pressure were used to analyse propagating patches of contractions (PPCs) and their component individual myogenic contractions [propagating individual contractions (PICs)] in the wall of the tetradotoxinized urinary bladder.

RESULTS

The bladder wall exhibited two contractile states that were of similar frequencies to those of the two types of electrophysiological discharge described in previous studies; the first, in which cyclic PPCs predominated, the second in which small irregular PICs predominated. The addition of carbachol increased the size, frequency, speed and distance of propagation of PPCs, whereas the addition of isoprenaline temporarily halted the incorporation of PICs into PPCs, and reduced patch size and total area undergoing contraction. The RhoA kinase (ROCK) inhibitor Y-27632 reduced both largest patch index and mean patch size. Both carbenoxolone and ROCK inhibition decreased the duration of PPCs. Carbenoxolone also prolonged duration and accelerated PPC propagation velocity. The authors postulate that these differences arise from differing effects of these agents on myocytes and interstitial cells within the stress environment of the bladder, influencing the development, coordination and propagation of PPCs.

CONCLUSIONS

The timings and structure of spontaneous micromotions in the wall of the isolated bladder change when it is treated with sympathetic/parasympathetic agonists and with myogenically active agents. Correspondingly, disorders of bladder wall contraction may result from disorders of either neurogenic or myogenic signalling and may be amenable to treatment with combinations of agents that influence both.