Feasibility of a deep learning-based diagnostic platform to evaluate lower urinary tract disorders in men using simple uroflowmetry

Abstract

Purpose To diagnose lower urinary tract symptoms (LUTS) in a noninvasive manner, we created a prediction model for bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using simple uroflowmetry. In this study, we used deep learning to analyze simple uroflowmetry. Materials and Methods We performed a retrospective review of 4,835 male patients aged ≥40 years who underwent a urodynamic study at a single center. We excluded patients with a disease or a history of surgery that could affect LUTS. A total of 1,792 patients were included in the study. We extracted a simple uroflowmetry graph automatically using the ABBYY Flexicapture ® image capture program (ABBYY, Moscow, Russia). We applied a convolutional neural network (CNN), a deep learning method to predict DUA and BOO. A 5-fold cross-validation average value of the area under the receiver operating characteristic (AUROC) curve was chosen as an evaluation metric. When it comes to binary classification, this metric provides a richer measure of classification performance. Additionally, we provided the corresponding average precision-recall (PR) curves. Results Among the 1,792 patients, 482 (26.90%) had BOO, and 893 (49.83%) had DUA. The average AUROC scores of DUA and BOO, which were measured using 5-fold cross-validation, were 73.30% (mean average precision [mAP]=0.70) and 72.23% (mAP=0.45), respectively. Conclusions Our study suggests that it is possible to differentiate DUA from non-DUA and BOO from non-BOO using a simple uroflowmetry graph with a fine-tuned VGG16, which is a well-known CNN model.

Can we use machine learning to improve the interpretation and application of urodynamic data?: ICI‐RS 2023

“…showing an AUC of 0.73 and 0.72, respectively. 16 A different approach used raw data from male LUTS patients' uroflowmetries to predict DU, applying the partial least squares regression algorithm, with an AUC of 0.80 and an optimum sensitivity of 73% and specificity of 85%. 17 Such studies have used both flow curve shape and standard uroflowmetry parameters, but these algorithms still have not reached adequate robustness and reliability to substitute for conventional uroflowmetry and pressure-flow studies.…”

“…A convolutional neural network (VGG16 model) was applied to conventional uroflowmetries of a cohort of male patients with LUTS to predict bladder outlet obstruction (BOO) and detrusor underactivity (DU), showing an AUC of 0.73 and 0.72, respectively 16 . A different approach used raw data from male LUTS patients' uroflowmetries to predict DU, applying the partial least squares regression algorithm, with an AUC of 0.80 and an optimum sensitivity of 73% and specificity of 85% 17 .…”

Are Excessive Daytime Sleepiness and Lower Urinary Tract Symptoms the Triggering Link for Mental Imbalance? An Exploratory Post Hoc Analysis

“…Hence, LUTS had a negative impact on sleep efficiency, increasing daytime sleepiness [3]. Several comorbidities could be associated with these two realities, such as obstructive sleep apnea syndrome that has a hidden prevalence in the general population up to 50% [5,6]. Specifically, subjects are often unaware of the disorder, and the diagnosis may be performed after those symptoms occurred [5,6].…”

“…Several comorbidities could be associated with these two realities, such as obstructive sleep apnea syndrome that has a hidden prevalence in the general population up to 50% [5,6]. Specifically, subjects are often unaware of the disorder, and the diagnosis may be performed after those symptoms occurred [5,6]. However, both EDS and LUTS lead to increased perceived psychological distress [7][8][9].…”