A Prediction Model Using Machine Learning Algorithm for Assessing Stone-Free Status after Single Session Shock Wave Lithotripsy to Treat Ureteral Stones

No AccessJournal of UrologyNew Technology and Techniques1 Dec 2018A Prediction Model Using Machine Learning Algorithm for Assessing Stone-Free Status after Single Session Shock Wave Lithotripsy to Treat Ureteral Stones Min Soo Choo, Saangyong Uhmn, Jong Keun Kim, Jun Hyun Han, Dong-Hoi Kim, Jin Kim, and Seong Ho Lee Min Soo ChooMin Soo Choo , Saangyong UhmnSaangyong Uhmn , Jong Keun KimJong Keun Kim , Jun Hyun HanJun Hyun Han , Dong-Hoi KimDong-Hoi Kim , Jin KimJin Kim , and Seong Ho LeeSeong Ho Lee View All Author Informationhttps://doi.org/10.1016/j.juro.2018.06.077AboutFull TextPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract Purpose: The aim of this study was to develop and validate a decision support model using a machine learning algorithm to predict treatment success after single session shock wave lithotripsy in ureteral stone cases. Materials and Methods: Of the 1,803 patients treated with shock wave lithotripsy we selected those with ureteral stones who had preoperative computerized tomography available. Treatment success after single session shock wave lithotripsy was defined as freedom from stones or residual stone fragments less than 2 mm long on computerized tomography or plain x-ray of the kidneys, ureters and bladder 2 weeks later. Decision tree analysis was done using a machine learning algorithm to identify relevant parameters. A decision support model was developed to calculate the probability of treatment success. Results: A total of 791 patients were enrolled in study. Mean ± SD stone length was 5.9 ± 2.3 mm and mean stone volume was 89.3 ± 140.0 mm3. The overall treatment success rate after SWL was 64.4% (509 cases). The rate for upper, middle and lower ureter stones was 59.8%, 65.5% and 69.6%, respectively. On decision tree analysis the top 3 performance criteria factors were volume, length and HU. Decision models were constructed with all possible combinations of factors. The model with 15 factors had greater than 92% accuracy and an average ROC AUC of 0.951. Conclusions: We applied a machine learning algorithm, a subfield of artificial intelligence, to predict the outcome after single session shock wave lithotripsy for ureteral stones. A 92.29% accurate decision model was developed with 15 factors and an average ROC AUC of 0.951. References 1 : A clinical nomogram to predict the successful shock wave lithotripsy of renal and ureteral calculi. J Urol2011; 186: 556. Link, Google Scholar 2 : Prognostic factors for extracorporeal shock-wave lithotripsy of ureteric stones—a multivariate analysis study. Scand J Urol Nephrol2003; 37: 413. Google Scholar 3 : Preoperative nomograms for predicting stone-free rate after extracorporeal shock wave lithotripsy. J Urol2006; 176: 1453. Link, Google Scholar 4 : Factors predicting the success of extracorporeal shock wave lithotripsy in the treatment of ureteric calculi. Br J Med Surg Urol2011; 4: 243. Google Scholar 5 : Predictive factors of the outcome of extracorporeal shockwave lithotripsy for ureteral stones. Korean J Urol2012; 53: 424. Google Scholar 6 : Optimal skin-to-stone distance is a positive predictor for successful outcomes in upper ureter calculi following extracorporeal shock wave lithotripsy: a Bayesian model averaging approach. PLoS One2015; 10: e0144912. Google Scholar 7 : Clinical nomograms to predict stone-free rates after shock-wave lithotripsy: development and internal-validation. PLoS One2016; 11: e0149333. Google Scholar 8 : A practical formula to predict the stone-free rate of patients undergoing extracorporeal shock wave lithotripsy. Urol Sci2017; 28: 215. Google Scholar 9 : Computed tomography-based novel prediction model for the outcome of shockwave lithotripsy in proximal ureteral stones. J Endourol2016; 30: 810. Google Scholar 10 : Predicting early mortality after acute variceal hemorrhage based on classification and regression tree analysis. Clin Gastroenterol Hepatol2009; 7: 1347. Google Scholar 11 : Machine learning to identify multigland disease in primary hyperparathyroidism. J Surg Res2017; 219: 173. Google Scholar 12 : Computerized tomography magnified bone windows are superior to standard soft tissue windows for accurate measurement of stone size: an in vitro and clinical study. J Urol2009; 181: 1710. Link, Google Scholar 13 : A prospective multivariate analysis of factors predicting stone disintegration by extracorporeal shock wave lithotripsy: the value of high-resolution noncontrast computed tomography. Eur Urol2007; 51: 1688. Google Scholar 14 : Shock wave lithotripsy success determined by skin-to-stone distance on computed tomography. Urology2005; 66: 941. Google Scholar 15 : C4.5: Programs for Machine Learning. San Francisco: Morgan Kaufmann Publishers1993: 302. Google Scholar 16 : C50: C5.0 Decision Trees and Rule-Based Models. Available at https://CRAN.R-project.org/package=C50. Accessed June 20, 2018. Google Scholar 17 : Body size, body composition and fat distribution: comparative analysis of European, Maori, Pacific Island and Asian Indian adults. Br J Nutr2009; 102: 632. Google Scholar 18 : Artificial intelligence for decision making. In: Knowledge-Based Intelligent Information and Engineering Systems. Edited by . Berlin: Springer2006: 531. Google Scholar 19 : Applying artificial intelligence technology to support decision-making in nursing: a case study in Taiwan. Health Informatics J2015; 21: 137. Google Scholar 20 : Avoiding overfitting of decision trees. In: Principles of Data Mining. London: Springer2013: 121. Google Scholar 21 : Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. PLoS Negl Trop Dis2008; 2: e196. Google Scholar © 2018 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 200Issue 6December 2018Page: 1371-1377Supplementary Materials Advertisement Copyright & Permissions© 2018 by American Urological Association Education and Research, Inc.Keywordsdecision support techniqueslithotripsyclinical decision-makingureteral calculimachine learningMetricsAuthor Information Min Soo Choo More articles by this author Saangyong Uhmn More articles by this author Jong Keun Kim More articles by this author Jun Hyun Han More articles by this author Dong-Hoi Kim More articles by this author Jin Kim More articles by this author Seong Ho Lee More articles by this author Expand All Advertisement PDF downloadLoading ...