Non-Invasive Clinical Parameters for the Prediction of Urodynamic Bladder Outlet Obstruction: Analysis Using Causal Bayesian Networks

• Published in: PloS one Vol. 9; no. 11; p. e113131
• Main Authors: Kim, Myong, Cheeti, Abhilash, Yoo, Changwon, Choo, Minsoo, Paick, Jae-Seung, Oh, Seung-June
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 14.11.2014; Public Library of Science (PLoS)
• Subjects: Aged; Bayes Theorem; Bayesian analysis; Bladder; Data processing; Flow velocity; Humans; Hyperplasia; Independent variables; Logistic Models; Male; Medicine and Health Sciences; Middle Aged; Model accuracy; Neural networks; Parameter identification; Patients; Performance prediction; Probability; Prostate; Prostate - physiopathology; Prostate cancer; Prostate specific antigen; Prostate-Specific Antigen - blood; Prostatic Hyperplasia - complications; Prostatic Hyperplasia - diagnosis; Regression analysis; Regression models; Severity of Illness Index; Statistical methods; Studies; Urinary bladder; Urinary Bladder Neck Obstruction - complications; Urinary Bladder Neck Obstruction - diagnosis; Urinary Bladder Neck Obstruction - pathology; Urodynamics; Urogenital system; Urology; Variables; Florida; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0113131

To identify non-invasive clinical parameters to predict urodynamic bladder outlet obstruction (BOO) in patients with benign prostatic hyperplasia (BPH) using causal Bayesian networks (CBN). From October 2004 to August 2013, 1,381 eligible BPH patients with complete data were selected for analysis. The following clinical variables were considered: age, total prostate volume (TPV), transition zone volume (TZV), prostate specific antigen (PSA), maximum flow rate (Qmax), and post-void residual volume (PVR) on uroflowmetry, and International Prostate Symptom Score (IPSS). Among these variables, the independent predictors of BOO were selected using the CBN model. The predictive performance of the CBN model using the selected variables was verified through a logistic regression (LR) model with the same dataset. Mean age, TPV, and IPSS were 6.2 (±7.3, SD) years, 48.5 (±25.9) ml, and 17.9 (±7.9), respectively. The mean BOO index was 35.1 (±25.2) and 477 patients (34.5%) had urodynamic BOO (BOO index ≥40). By using the CBN model, we identified TPV, Qmax, and PVR as independent predictors of BOO. With these three variables, the BOO prediction accuracy was 73.5%. The LR model showed a similar accuracy (77.0%). However, the area under the receiver operating characteristic curve of the CBN model was statistically smaller than that of the LR model (0.772 vs. 0.798, p = 0.020). Our study demonstrated that TPV, Qmax, and PVR are independent predictors of urodynamic BOO.