External Validation and Comparisons of the Scoring Systems for Predicting Percutaneous Nephrolithotomy Outcomes: A Single Center Experience with 506 Cases

External validation of a nomogram for outcome prediction in management of medium-sized (1-2 cm) kidney stones

BACKGROUND

Stone nomogram by Micali et al., able topredict treatment failure of shock-wave lithotripsy (SWL), retrograde intrarenal surgery (RIRS) and percutaneous nephrolithotomy (PNL) in the management of single 1-2 cm renal stones, was developed on 2605 patients and showed a high predictive accuracy, with an area under ROC curve of 0.793 at internal validation. The aim of the present study is to externally validate the model to assess whether it displayed a satisfactory predictive performance if applied to different populations.

METHODS

External validation was retrospectively performed on 3025 patients who underwent an active stone treatment from December 2010 to June 2021 in 26 centers from four countries (Italy, USA, Spain, Argentina). Collected variables included: age, gender, previous renal surgery, preoperative urine culture, hydronephrosis, stone side, site, density, skin-to-stone distance. Treatment failure was the defined outcome (residual fragments >4 mm at three months CT-scan).

RESULTS

Model discrimination in external validation datasets showed an area under ROC curve of 0.66 (95% 0.59-0.68) with adequate calibration. The retrospective fashion of the study and the lack of generalizability of the tool towards populations from Asia, Africa or Oceania represent limitations of the current analysis.

CONCLUSIONS

According to the current findings, Micali's nomogram can be used for treatment prediction after SWL, RIRS and PNL; however, a lower discrimination performance than the one at internal validation should be acknowledged, reflecting geographical, temporal and domain limitation of external validation studies. Further prospective evaluation is required to refine and improve the nomogram findings and to validate its clinical value.

Develop a radiomics-based machine learning model to predict the stone-free rate post-percutaneous nephrolithotomy

Radiomics and machine learning have been extensively utilized in the realm of urinary stones, particularly in forecasting stone treatment outcomes. The objective of this study was to integrate clinical variables and radiomic features to develop a machine learning model for predicting the stone-free rate (SFR) following percutaneous nephrolithotomy (PCNL). A total of 212 eligible patients who underwent PCNL surgery at the Second Affiliated Hospital of Nanchang University were included in a retrospective analysis. Preoperative clinical variables and non-contrast-enhanced CT images of all patients were collected, and radiomic features were extracted after delineating the stone ROI. Univariate analysis was conducted to identify clinical variables strongly correlated with the stone-free rate after PCNL, and the least absolute shrinkage and selection operator algorithm (lasso regression) was utilized to screen radiomic features. Four supervised machine learning algorithms, including Logistic Regression, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Decision Tree (GBDT), were employed. The clinical variables with strong correlation and screened radiomic features were integrated into the four machine learning algorithms to construct a prediction model, and the receiver operating curve was plotted. The area under the receiver operating curve (AUC), the accuracy rate, the specificity, etc., were used to evaluate the predictive performance of the four models. After analyzing postoperative statistics, the stone-free rate following the procedure was found to be 70.3% (n = 149). Among the various clinical variables examined, factors, such as stone number, stone diameter, stone CT value, stone location, and history of stone surgery, were identified as statistically significant in relation to the stone-free rate after PCNL. A total of 121 radiomic features were extracted, and through lasso regression, 7 features most closely associated with the stone-free rate post-PCNL were identified. The predictive accuracy of different models (Logistic Regression, RF, XGBoost, and GBDT) for determining the stone-free rate after PCNL was evaluated, yielding accuracies of 78.1%, 76.6%, 75.0%, and 73.4%, respectively. The corresponding area under the curve AUC (95%CI) were 0.85 (0.83-0.89), 0.81 (0.76-0.85), 0.82 (0.78-0.85), and 0.77 (0.73-0.81), positioning these models among the top performers in logistic regression prediction. In terms of predictive importance scores, the key factors identified by the logistic regression model were number of stone, zone percentage, stone diameter, and surface area. Similarly, the RF model highlighted number of stone, stone CT value, stone diameter, and surface area as the top predictors. Among the four machine learning models, the logistic regression model demonstrated the highest accuracy and discrimination ability in predicting the stone-free rate following PCNL. In comparison to XGBoost and GBDT, RF also exhibited superior accuracy and a certain level of discrimination ability. However, based on the performance of all four models, logistic regression is more likely to aid in clinical decision-making by assisting clinicians in diagnosing PCNL in patients. This enables us to effectively predict the presence of residual stones post-surgery and ultimately select patients who are suitable candidates for PCNL.

Stone-scoring systems for predicting complications in percutaneous nephrolithotomy: A systematic review of the literature

Objective

Percutaneous nephrolithotomy is a treatment of choice for larger stones of the upper urinary tract. Currently, several nephrolithometric nomograms for prediction of post-operative surgical outcomes have been proposed, although uncertainties still exist regarding their roles in the estimation of complications.

Methods

We conducted a systematic review on PubMed and Web of Sciences databases including English studies with at least 100 cases and published between January 2010 and December 2021. We identified original articles evaluating correlations between the Guy's stone score, the stone size (S), tract length (T), obstruction (O), number of involved calices (N), and essence or stone density (E) (S.T.O.N.E.), Clinical Research Office of the Endourological Society (CROES), and Seoul National University Renal Stone Complexity (S-ReSC) scores and post-operative complications in adult patients. We also included newly designed nomograms for prediction of specific complications.

Results

After an initial search of 549 abstracts, we finally included a total of 18 papers. Of them, 11 investigated traditional nephrolithometric nomograms, while seven newly designed nomograms were used to predict specific complications. Overall, 7316 patients have been involved. In total, 14 out of 18 papers are derived from retrospective single-center studies. Guy's stone score obtained correlation with complications in five, S.T.O.N.E. nephrolithometry score in four, while CROES score and S-ReSC score in three and two, respectively. None of the studies investigated minimally invasive percutaneous nephrolithotomy (PCNL) and all cases have been conducted in prone position. Considering newly designed nomograms, none of them is currently externally validated; five of them predict post-operative infections; the remaining two have been designed for thromboembolic events and urinary leakage.

Conclusion

This review presents all nomograms currently available in the PCNL field and highlights a certain number of concerns. Published data have appeared contradictory; more recent tools for prediction of post-operative complications are frequently based on small retrospective cohorts and lack external validations. Heterogeneity among studies has also been noticed. More rigorous validations are advisable in the future, involving larger prospective patients' series and with the comparison of different tools.

Does nephrolithometry scoring systems predict success and complications in miniPCNL?

OBJECTIVE

Auxiliary nephrolithometric scoring systems (NSSs) have been developed to predict complications and treatment success of conventional percutaneous nephrolithotomy (PCNL). However, to our knowledge, there is no study comparing these NSSs in patients undergoing miniPCNL. This study aimed to compare the NSSs in terms of their ability to predict miniPCNL-related complications and treatment success.

METHODS

The data of patients undergoing PCNL between September 2016 and May 2018 were retrospectively reviewed through the electronic medical record system, and 140 patients were included in our study. Stone-free status was evaluated using non-contrast computed tomography between 1 and 3 months after the procedure. PCNL was considered successful if the patient was completely stone free. The postsurgical complications were classified according to the modified Clavien-Dindo classification system.

RESULTS

The Clinical Research Office of the Endourological Society (CROES) and STONE NSSs significantly predicted miniPCNL treatment success (p = 0.043, p = 0.018). However, the Guy's NSS did not significantly predict the treatment success (p = 0.415). Guy's, CROES and STONE NSSs were not found to significantly predict postsurgical complications (p = 0.584, p = 0.823, p = 0.189).

CONCLUSION

To the best of our knowledge, our study is the first of its kind to investigate the ability of NSSs to predict treatment success and postsurgical complications in patients undergoing miniPCNL. The study found that STONE and CROES NSSs are independent parameters for predicting stone-free status after miniPCNL. In addition, our study found that none of the NSSs were useful in predicting postsurgical complications in patients undergoing miniPCNL.

[Do the nephrolithometry scoring systems predict the success of percutaneous nephrolithotomy. Comparison of 4 scores: The Guy's stone score, STONE Score, CROES nomogram and S-ReSC score]

INTRODUCTION

The aim of the study is to investigate the factors predictive of surgical outcomes of PCNL and to compare the predictability and accuracy of the Guy's stone score, STONE nephrolithometry, CROES nomogram and S-ReSC score.

PATIENTS AND METHODS

We reviewed retrospectively the surgical outcomes recorded consecutively and imaging data of preoperative computed tomography scans of patients who underwent PCNL from 2013 to 2016. Patients with asymptomatic residual fragments<4mm were considered stone-free. Preoperative abdominopelvic computerized tomography images of the patients were reviewed and scored according The Guy's stone score, STONE nephrolithometry, CROES nomogram, S-ReSC score by one urologist.

RESULTS

A total of 157 PCNLs were reviewed. The overall stone-free rate was 59% (92/157) with a complication rate of 22% (35/157). Stone Burden<542mm³ is significantly associated with stone-free rate (SFR) (P=0.001). On univariate analysis, all the scoring systems were identified as significant factors in terms of SFR. The Guy's Stone Score, the CROES score and the S-ReSC score were associated with complications (P<0.02). The multivariate logistic regression analysis showed that the CROES score was identified as a significant factor in terms of SFR and complications (P<0.01). The area under the receiver operating characteristic (ROC) curves for stone burden, the Guy's, STONE score, CROES core and S-ReSC scores showed good results (0.737/0.674/0.762/0.746/0.710) respectively.

CONCLUSION

Although the four scoring systems were significantly associated with SFR, the STONE score was a significant predictive factor for SFR and complications after PCNL.

LEVEL OF EVIDENCE

3.