Characteristics of uroflowmetry patterns in men with detrusor underactivity revealed by artificial intelligence
Yoshihisa Matsukawa, Yoshitaka Kameya, Tomoichi Takahashi, Atsuki Shimazu, Shohei Ishida, Muneo Yamada, Naoto Sassa, Tokunori Yamamoto
Abstract
Objectives To elucidate the characteristics of uroflowmetry (UFM) observed in men with detrusor underactivity (DU) using our developed artificial intelligence (AI) diagnostic algorithm to distinguish between DU and bladder outlet obstruction (BOO). Methods Subjective and objective parameters, including four UFM parameters (first peak flow rate, time to first peak, gradient to first peak, and the ratio of first peak flow rate to maximum flow rate [ Q max ]) selected by analyzing the judgment basis of the AI diagnostic system, were compared in 266 treatment‐naive men with lower urinary tract symptoms (LUTS). Patients were divided into the DU (70; 26.32%) and non‐DU (196; 73.68%) groups, and the UFM parameters for predicting the presence of DU were determined by multivariate analysis and receiver operating characteristic (ROC) curve analysis. Detrusor underactivity was defined as a bladder contractility index <100 and a BOO index <40. Results Most parameters on the first peak flow of UFM were significantly lower in the DU group. On multivariate analysis, lower first peak flow rate and lower ratio of first peak flow rate to Q max were significant parameters to predict DU. In the ROC analysis, the ratio of the first peak flow rate to Q max showed the highest area under the curve (0.848) and yielded sensitivities of 76% and specificities of 83% for DU diagnosis, with cutoff values of 0.8. Conclusions Parameters on the first peak flow of UFM, especially the ratio of the first peak flow rate to Q max , can diagnose DU with high accuracy in men with LUTS.