Can we improve the prediction of stone-free status after extracorporeal shock wave lithotripsy for ureteral stones? A neural network or a statistical model?

PURPOSE We evaluated whether an artificial neural network (ANN) can improve the prediction of stone-free status after extracorporeal shock wave lithotripsy (ESWL) (Dornier Medical Systems, Inc., Marietta, Georgia) for ureteral stones compared to a logistic regression (LR) model. MATERIALS AND METHODS Between February 1989 and December 1998, 984 patients with ureteral stones, including 780 males and 204 females with a mean age +/- SD of 40.85 +/- 10.33 years, were treated with ESWL. Stone-free status at 3 months was determined by urinary tract plain x-ray and excretory urography. Of all patients 919 (93.3%) were free of stones. The impact of 10 factors on stone-free status was studied using an LR model and ANN. These factors were patient age and sex, renal anatomy, stone location, side, number, length and width, whether stones were de novo or recurrent, and stent use. An LR model was constructed and ANN was trained on 688 randomly selected patients (70%) to predict stone-free status at 3 months. The 10 factors were used as covariates in the LR model and as input parameters to ANN. Performance of the trained net and developed logistic model was evaluated in the remaining 296 patients (30%), who served as the test set. The sensitivity (percent of correctly predicted stone-free cases), specificity (percent of correctly predicted nonstonefree cases), positive predictive value, overall accuracy and average classification rate of the 2 techniques were compared. Relevant variables influencing the construction of the 2 models were compared. RESULTS Evaluating the performance of the LR and ANN models on the test set revealed a sensitivity of 100% and 77.9%, a specificity of 0.0% and 75%, a positive predictive value of 93.2% and 97.2%, an overall accuracy of 93.2% and 77.7%, and an average classification rate of 50% and 76.5%, respectively. LR failed to predict any nonstone free cases. LR and ANN identified stone location and stent use as important factors in determining the outcome, while ANN also identified stone length and width as influential factors. CONCLUSIONS ANN and LR could predict adequately those who would be stone-free after ESWL for ureteral stones. The neural network has a higher ability to predict those who fail to respond to ESWL.

[1]  Lucila Ohno-Machado,et al.  Diagnosing Breast Cancer from FNAs: Variable Relevance in Neural Network and Logistic Regression Models , 1998, MedInfo.

[2]  T. Yagisawa,et al.  Factors associated with failure of extracorporeal shock‐wave lithotripsy for ureteral stones using Dornier lithotripter U/50 , 2002, International journal of urology : official journal of the Japanese Urological Association.

[3]  K. Sheir,et al.  Prognostic factors for extracorporeal shock‐wave lithotripsy of ureteric stonesA multivariate analysis study , 2003, Scandinavian journal of urology and nephrology.

[4]  H. Danuser,et al.  Extracorporeal shock wave lithotripsy in situ or after push-up for upper ureteral calculi: a prospective randomized trial. , 1993, The Journal of urology.

[5]  John Galletly,et al.  Neural Networks: : An Introduction ‐ 2nd edition , 1998 .

[6]  K. Pace,et al.  Low success rate of repeat shock wave lithotripsy for ureteral stones after failed initial treatment. , 2000, The Journal of urology.

[7]  Mesut Remzi,et al.  An artificial neural network for prostate cancer staging when serum prostate specific antigen is 10 ng./ml. or less. , 2003, The Journal of urology.

[8]  D. Lamb,et al.  Artificial intelligence in medicine and male infertility , 2004, World Journal of Urology.

[9]  S. Izenberg,et al.  Prediction of spontaneous ureteral calculous passage by an artificial neural network. , 2000, The Journal of urology.

[10]  Berndt Müller,et al.  Neural networks: an introduction , 1990 .

[11]  E. Crawford,et al.  Impact of different variables on the outcome of patients with clinically confined prostate carcinoma: prediction of pathologic stage and biochemical failure using an artificial neural network. , 2001, Cancer.

[12]  R. Golden,et al.  Use of a neural network to predict stone growth after shock wave lithotripsy. , 1998, Urology.

[13]  P. Dahm,et al.  Prediction of lower pole stone clearance after shock wave lithotripsy using an artificial neural network. , 2003, The Journal of urology.

[14]  J W Moul,et al.  Neural network analysis of quantitative histological factors to predict pathological stage in clinical stage I nonseminomatous testicular cancer. , 1995, The Journal of urology.

[15]  A. Hendrikx,et al.  Treatment of mid- and lower ureteric calculi: extracorporeal shock-wave lithotripsy vs laser ureteroscopy. A comparison of costs, morbidity and effectiveness. , 1998, British journal of urology.

[16]  A. Mandal,et al.  Computerized tomography attenuation value of renal calculus: can it predict successful fragmentation of the calculus by extracorporeal shock wave lithotripsy? A preliminary study. , 2002, The Journal of urology.

[17]  M. Aron,et al.  Impact of power index, hydroureteronephrosis, stone size, and composition on the efficacy of in situ boosted ESWL for primary proximal ureteral calculi. , 2001, Urology.

[18]  J. Lingeman,et al.  Calcium stone fragility is predicted by helical CT attenuation values. , 2000, Journal of endourology.

[19]  H. Singh,et al.  Artificial neural networks in predicting optimum renal stone fragmentation by extracorporeal shock wave lithotripsy: a preliminary study , 2003, BJU international.

[20]  M. Orvieto,et al.  Extracorporeal shockwave lithotripsy of 2000 urinary calculi with the modulith SL-20: success and failure according to size and location of stones. , 2000, Journal of endourology.