Development and Validation of a Deep Learning System for Sound-based Prediction of Urinary Flow.

BACKGROUND: Uroflowmetry remains an important tool for the assessment of patients with lower urinary tract symptoms (LUTS), but accuracy can be limited by within-subject variation of urinary flow rates. Voiding acoustics appear to correlate well with conventional uroflowmetry and show promise as a convenient home-based alternative for the monitoring of urinary flows. OBJECTIVE: To evaluate the ability of a sound-based deep learning algorithm (Audioflow) to predict uroflowmetry parameters and identify abnormal urinary flow patterns. DESIGN, SETTING, AND PARTICIPANTS: In this prospective open-label study, 534 male participants recruited at Singapore General Hospital between December 1, 2017 and July 1, 2019 voided into a uroflowmetry machine, and voiding acoustics were recorded using a smartphone in close proximity. The Audioflow algorithm consisted of two models-the first model for the prediction of flow parameters including maximum flow rate (Qmax), average flow rate (Qave), and voided volume (VV) was trained and validated using leave-one-out cross-validation procedures; the second model for discrimination of normal and abnormal urinary flows was trained based on a reference standard created by three senior urologists. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Lin's correlation coefficient was used to evaluate the agreement between Audioflow predictions and conventional uroflowmetry for Qmax, Qave, and VV. Accuracy of the Audioflow algorithm in the identification of abnormal urinary flows was assessed with sensitivity analyses and the area under the receiver operating curve (AUC); this algorithm was compared with an external panel of graders comprising six urology residents/general practitioners who separately graded flow patterns in the validation dataset. RESULTS AND LIMITATIONS: A total of 331 patients were included for analysis. Agreement between Audioflow and conventional uroflowmetry for Qmax, Qave, and VV was 0.77 (95% confidence interval [CI], 0.72-0.80), 0.85 (95% CI, 0.82-0.88) and 0.84 (95% CI, 0.80-0.87), respectively. For the identification of abnormal flows, Audioflow achieved a high rate of agreement of 83.8% (95% CI, 77.5-90.1%) with the reference standard, and was comparable with an external panel of six residents/general practitioners. AUC was 0.892 (95% CI, 0.834-0.951), with high sensitivity of 87.3% (95% CI, 76.8-93.7%) and specificity of 77.5% (95% CI, 61.1-88.6%). CONCLUSIONS: The results of this study suggest that a deep learning algorithm can predict uroflowmetry parameters and identify abnormal urinary voids based on voiding sounds, and shows promise as a simple home-based alternative to uroflowmetry in the management of patients with LUTS. PATIENT SUMMARY: In this study, we trained a deep learning-based algorithm to measure urinary flow rates and identify abnormal flow patterns based on voiding sounds. This may provide a convenient, home-based alternative to conventional uroflowmetry for the assessment and monitoring of patients with lower urinary tract symptoms.

A Systemic Review and Meta-analysis of Transabdominal Intravesical Prostatic Protrusion Assessment in Determining Bladder Outlet Obstruction and Unsuccessful Trial Without Catheter.

CONTEXT: Urodynamic study (UDS) provides the most objective assessment of bladder outlet obstruction (BOO) but is impractical to be recommended routinely in outpatient services. Intravesical prostatic protrusion (IPP) had been described to obstruct urinary flow by creating an anatomical ball-valve effect, but there remains a lack of pooled evidence that can objectively correlate with BOO in benign prostatic hyperplasia. OBJECTIVE: To update the current evidence on the predictive role of IPP in determining BOO and unsuccessful trial without catheter (TWOC). EVIDENCE ACQUISITION: A comprehensive literature search was performed to identify studies that evaluated IPP in diagnosing UDS-determined BOO and TWOC. The search included the PubMed/MEDLINE, EMBASE, and Cochrane Library up to January 2021. An updated systemic review and meta-analysis was performed. EVIDENCE SYNTHESIS: A total of 18 studies with 4128 patients were examined. Eleven studies with 1478 patients examined the role of IPP in UDS-determined BOO. The pooled area under the curve (AUC) was 0.83 (95% confidence interval [CI]: 0.79-0.86), and at a cut-off of >10 mm, the sensitivity (Sn) and specificity (Sp) were 0.71 (95% CI: 0.61-0.78) and 0.77 (95% CI: 0.68-0.84), respectively. The probability-modifying plot revealed positive and negative likelihood ratios of 3.34 (95% CI: 2.56-4.36) and 0.35 (95% CI: 0.26-0.45), respectively. Seven studies with 2650 patients examined IPP in predicting unsuccessful TWOC, with a pooled AUC of 0.74 (95% CI: 0.70-0.84), with Sn of 0.51 (95% CI: 0.43-0.60) and Sp of 0.79 (95% CI: 0.73-0.84) at an IPP cut-off of >10 mm. Five studies compared prostate volume (PV) and IPP and revealed a lower AUC of PV at 0.71 (95% CI: 0.67-0.75), which was an inferior parameter in diagnosing BOO (p < 0.001). CONCLUSIONS: This systemic review provided evidence that IPP is a reliable clinical parameter that correlates strongly with underlying BOO and unsuccessful TWOC. PATIENT SUMMARY: In this review, we comprehensively reviewed all the literature to date on evaluating the clinical utility of intravesical prostatic protrusion (IPP). We have demonstrated that IPP correlates strongly with urodynamic study (UDS)-determined bladder outlet obstruction and failure of trial without catheter (TWOC). Outpatient IPP measurement is a quick, inexpensive, and reproducible clinical parameter that can determine the severity of benign prostatic hyperplasia. The clinical role of IPP in predicting failure of TWOC selects patients who are best treated with aggressive surgical approaches rather than conservative medical therapies. More importantly, IPP can facilitate the discriminatory use of invasive UDS, reserved for patients with a strong suspicion of concomitant detrusor abnormalities.

A 3D Printed Implantable Device for Voiding the Bladder Using Shape Memory Alloy (SMA) Actuators.

Underactive bladder or detrusor underactivity (DU) is defined as a reduction of contraction strength or duration of the bladder wall. Despite the serious healthcare implications of DU, there are limited solutions for affected individuals. A flexible 3D printed implantable device driven by shape memory alloys (SMA) actuators is presented here for the first time to physically contract the bladder to restore voluntary control of the bladder for individuals suffering from DU. This approach is used initially in benchtop experiments with a rubber balloon acting as a model for the rat bladder to verify its potential for voiding, and that the operating temperatures are safe for the eventual implantation of the device in a rat. The device is then implanted and tested on an anesthetized rat, and a voiding volume of more than 8% is successfully achieved for the SMA-based device without any surgical intervention or drug injection to relax the external sphincter.

Early outcome of transurethral enucleation and resection of the prostate versus transurethral resection of the prostate.

INTRODUCTION: Recurrent prostate adenoma is a long-term complication following transurethral resection of the prostate (TURP). Transurethral enucleation and resection of the prostate (TUERP) is more appealing, since the nodular adenoma can be completely removed through endoscopy. TUERP is also hypothesised to result in a lower frequency of recurrent adenoma. This study aimed to compare the early outcomes of TUERP and TURP, and assess the feasibility and safety of TUERP. METHODS: We compared the outcome of 81 patients who underwent TUERP with that of 85 patients who underwent TURP. International prostate symptom score, quality of life score, prostate volume, degree of intravesical prostatic protrusion, maximum flow rate, post-void residual volume and prostate-specific antigen (PSA) level were obtained pre- and postoperatively. Complications (e.g. transfusion rate, incontinence, infection and urethral stricture) were analysed. RESULTS: Operative time was significantly longer in the TUERP group compared to the TURP group (85.3 minutes vs. 51.6 minutes). After TUERP, the maximum flow rate was significantly higher (21.1 mL/s vs. 17.1 mL/s) and PSA level was significantly lower (1.2 ng/mL vs. 1.9 ng/mL) than after TURP. The rates of infection, transfusion and urethral stricture were similar for both groups, but the TUERP group had a higher rate of temporary incontinence (13.6% vs. 4.7%). CONCLUSION: The lower PSA level and better maximum flow rate achieved following TUERP suggest that prostate adenoma removal was more complete with TUERP. Long-term follow-up is required to establish whether TUERP results in fewer resections for recurrent adenoma.