OBJECTIVES: An artificial neural network model previously described by us that was based on lower urinary tract symptoms yielded a modest prediction of bladder outlet obstruction. The aim of this study was to establish another model, using more objective parameters, that could better predict for bladder outlet obstruction. METHODS: The records of 457 patients were used in the construction of the model. Of the 457 records, 300 were allocated to the training phase and 157 to the testing phase. All patients had the average flow rate, maximal flow rate, postvoid residual urine volume (PVR), and total prostate volume recorded. The results of the pressure flow study of those patients were considered the reference standard against which the artificial neural network was tested. RESULTS: Three models were tested. Models 1 and 2 were based on a three-output design (ie, nonobstructed, equivocal, and obstructed). The only difference was the number of iterations. The accuracy of the first model was 60.5% compared with 46.5% for the second. For a third model, in which the equivocal pressure flow study results were added to the nonobstructed group, the accuracy rose to 72%. Deletion of equivocal cases (around 19% of the total) was associated with an accuracy of 76% in the prediction of obstruction. CONCLUSIONS: An artificial neural network based on objective and noninvasive parameters could replace the pressure flow study in only 72% of cases. An accuracy of 76% in the detection of bladder outlet obstruction is rather impractical, because an equivocal zone has always been available on pressure flow study nomograms.
OBJECTIVES: An artificial neural network model previously described by us that was based on lower urinary tract symptoms yielded a modest prediction of bladder outlet obstruction. The aim of this study was to establish another model, using more objective parameters, that could better predict for bladder outlet obstruction. METHODS: The records of 457 patients were used in the construction of the model. Of the 457 records, 300 were allocated to the training phase and 157 to the testing phase. All patients had the average flow rate, maximal flow rate, postvoid residual urine volume (PVR), and total prostate volume recorded. The results of the pressure flow study of those patients were considered the reference standard against which the artificial neural network was tested. RESULTS: Three models were tested. Models 1 and 2 were based on a three-output design (ie, nonobstructed, equivocal, and obstructed). The only difference was the number of iterations. The accuracy of the first model was 60.5% compared with 46.5% for the second. For a third model, in which the equivocal pressure flow study results were added to the nonobstructed group, the accuracy rose to 72%. Deletion of equivocal cases (around 19% of the total) was associated with an accuracy of 76% in the prediction of obstruction. CONCLUSIONS: An artificial neural network based on objective and noninvasive parameters could replace the pressure flow study in only 72% of cases. An accuracy of 76% in the detection of bladder outlet obstruction is rather impractical, because an equivocal zone has always been available on pressure flow study nomograms.
Authors: S Abdovic; M Cuk; N Cekada; M Milosevic; A Geljic; S Fusic; M Bastic; Z Bahtijarevic Journal: World J Urol Date: 2018-12-04 Impact factor: 4.226