External validation and comparison of current scoring systems in retrograde intrarenal surgery: Multi-institutional study with 949 patients

Stone decision engine accurately predicts stone removal and treatment complications for shock wave lithotripsy and laser ureterorenoscopy patients

Kidney stones form when mineral salts crystallize in the urinary tract. While most stones exit the body in the urine stream, some can block the ureteropelvic junction or ureters, leading to severe lower back pain, blood in the urine, vomiting, and painful urination. Imaging technologies, such as X-rays or ureterorenoscopy (URS), are typically used to detect kidney stones. Subsequently, these stones are fragmented into smaller pieces using shock wave lithotripsy (SWL) or laser URS. Both treatments yield subtly different patient outcomes. To predict successful stone removal and complication outcomes, Artificial Neural Network models were trained on 15,126 SWL and 2,116 URS patient records. These records include patient metrics like Body Mass Index and age, as well as treatment outcomes obtained using various medical instruments and healthcare professionals. Due to the low number of outcome failures in the data (e.g., treatment complications), Nearest Neighbor and Synthetic Minority Oversampling Technique (SMOTE) models were implemented to improve prediction accuracies. To reduce noise in the predictions, ensemble modeling was employed. The average prediction accuracies based on Confusion Matrices for SWL stone removal and treatment complications were 84.8% and 95.0%, respectively, while those for URS were 89.0% and 92.2%, respectively. The average prediction accuracies for SWL based on Area-Under-the-Curve were 74.7% and 62.9%, respectively, while those for URS were 77.2% and 78.9%, respectively. Taken together, the approach yielded moderate to high accurate predictions, regardless of treatment or outcome. These models were incorporated into a Stone Decision Engine web application (http://peteranoble.com/webapps.html) that suggests the best interventions to healthcare providers based on individual patient metrics.

Prediction of percutaneous nephrolithotomy outcomes and flexible ureteroscopy outcomes using nephrolithometry scoring systems

BACKGROUND

Kidney stones account for a high proportion of urological emergencies. The main objective of this paper is to evaluate the predictive ability of five scoring systems for overall stone-free status and postoperative complications after percutaneous nephrolithotomy and retrograde ureteroscopy.

MATERIALS AND METHODS

This study retrospectively analysed 312 cases of kidney stone patients between January 2021 and May 2022 at our centre. Multivariate logistic regression as well as ROC curves were applied to determine the ability to evaluate each scale to predict stone-free rates and postoperative complications.

RESULTS

179 patients have undergone PCNL. After multivariate logistic regression, the S.T.O.N.E score and history of ipsilateral renal surgery were predictive of stone-free status, and the predictive power of the S.T.O.N.E score was higher than that of history of ipsilateral renal surgery. Grade 1 complications were considered to be related to Guy's score and grade 2 complications were considered to be related to history of diabetes mellitus. 133 patients have undergone f-URS. After multivariate logistic regression analysis, the modified S-ReSC score, RUSS score, and R.I.R.S score were predictive of stone-free status, with the R.I.R.S score being the strongest predictor. Evidence of grade 2 complications was considered to be related to abnormal renal function.

CONCLUSION

For PCNL, the S.T.O.N.E score had the best efficacy in predicting stone-free status, and the Guy's score had the best efficacy in predicting postoperative complications; for f-URS, the R.I.R.S score had the best efficacy in predicting stone-free status, and no scoring system predicted postoperative complications.

New infundibulopelvic angle measurement method can predict stone-free rates following retrograde intrarenal surgery

To enhance the accuracy of predicting stone-free rates after retrograde intrarenal surgery, we devised a novel approach to assess the renal infundibulopelvic angle. We conducted a retrospective review of patient records for those who underwent retrograde intrarenal surgery for renal stones between April 2018 and August 2019. Patient demographics, stone characteristics, and perioperative data were recorded. Subsequently, we introduced a modified angle measurement called the pelvic stone angle and evaluated its predictive performance for stone-free rates by comparing it with the traditional method in scoring systems. A total of 43 individuals were included in this study. Notable differences in stone burden and Hounsfield unit measurements were found between stone-free and non-stone-free patients. The pelvic stone angle demonstrated a good model fit when used in scoring systems, performing equally well as the conventional approach. The area under the receiver operating characteristic curve for the R.I.R.S. scoring system using the pelvic stone angle and the conventional approach did not show a significant difference. In conclusion, the predictive ability of the pelvic stone angle for stone-free rates was comparable to the old measurement method. Moreover, scoring systems using the pelvic stone angle exhibited a better model fit than those using the conventional approach.