Prediction of infective complications after retrograde intra renal surgery using Machine learning.

BACKGROUND: To compare the models obtained with classical statistical methods and machine learning (ML) algorithms to predict postoperative infective complications (PICs) after retrograde intrarenal surgery (RIRS). MATERIAL AND METHODS: Patients who underwent RIRS between January 2014 and December 2020 were retrospectively screened. Patients who did not develop PICs were classified as Group 1 and patients who developed as Group 2. RESULTS: Three-hundred and twenty-two patients were included in the study; 279 patients (86.6%) who did not develop PICs were classified as Group 1, and 43 patients (13.3%) who developed PICs were classified as Group 2. In multivariate analysis, the presence of diabetes mellitus, preoperative nephrostomy, and stone density were determined to be factors that significantly predicted the development of PICs. The area under the curve (AUC) of the model obtained by classical Cox regression analysis was 0.785, and the sensitivity and specificity were 74% and 67%, respectively. With the Random Forest, K- Nearest Neighbour, and Logistic Regression methods, the AUC was calculated as 0.956, 0.903, and 0.849, respectively. RF's sensitivity and specificity were calculated as 87% and 92%, respectively. CONCLUSION: With ML, more reliable and predictive models can be created than with classical statistical methods.

Testicular salvage: using machine learning algorithm to develop a predictive model in testicular torsion.

PURPOSE: To compare the models developed with a classical statistics method and a machine learning model to predict the possibility of orchiectomy using preoperative parameters in patients who were admitted with testicular torsion. MATERIALS AND METHODS: Patients who underwent scrotal exploration due to testicular torsion between the years 2000 and 2020 were retrospectively reviewed. Demographic data, features of admission time, and other preoperative clinical findings were recorded. Cox Regression Analysis as a classical statistics method and Random Forest as a Machine Learning algorithm was used to create a prediction model. RESULTS: Among patients, 215 (71.6%) were performed orchidopexy and 85 (28.3%) were performed orchiectomy. The multivariate analysis revealed that monocyte count, symptom duration, and the number of previous Doppler ultrasonography were predictive of orchiectomy. Classical Cox regression analysis had an area under the curve (AUC) 0.937 with a sensitivity and specificity of 88 and 87%. The AUC for the Random Forest model was 0.95 with a sensitivity and specificity of 92 and 89%. CONCLUSION: The ML model outperformed the conventional statistical regression model in the prediction of orchiectomy. The ML methods are cheap, and their powers increase with increasing data input; we believe that their clinical use will increase over time.

External validation of the T.O.HO. score and derivation of the modified T.O.HO. score for predicting stone-free status after flexible ureteroscopy in ureteral and renal stones.

OBJECTIVE: The T.O.HO. scoring system was developed to predict stone-free status after flexible ureterenoscopy (fURS) lithotripsy applied for ureter and renal stones. This study aimed to perform the external validation of the T.O.HO. score in the Turkish population and propose a modification for this system. MATERIAL METHODS: Patients who underwent fURS for kidney and ureteral stones between January 2017 and January 2020 were retrospectively analysed. The patient and stone characteristics and perioperative findings were noted. The T.O.HO. score was externally validated and compared with the STONE score. Stone-free parameters were evaluated with the multivariate analysis. Based on the results of this analysis, the T.O.HO. score was modified and internally validated. RESULTS: A total of 621 patients were included in the study. The stone-free rate was determined as 79.8% (496/621) after fURS. The regression analysis showed that stone area had better predictive power than stone diameter (P = .025). Lower pole (reference), middle pole [odds ratio (OR) = 0.492 P = .016] and middle ureteral (OR = 0.227, P = .024) localisations, stone density (OR = 1.001, P < .001), and stone volume (OR = 1.008, P < .001) were determined as independent predictive markers for stone-free status. Based on the effect size of the stone surface area in the nomogram, stone volume was divided into five categories, at 1-point intervals. The AUC values of the T.O.HO., STONE, and modified T.O.HO. score in predicting stone-free status were calculated as 0.758, 0.634, and 0.821, respectively. The modified T.O.HO. created by adding stone volume was statistically significantly superior to the original version (ROC curve comparison, P < .001). CONCLUSION: The T.O.HO. score effectively predicted stone-free status after fURS. However, modified T.O.HO. SS showed the best predictive performance compared with original T.O.HO. SS.

A comparative analysis of the efficacy and safety of mini-percutaneous nephrolithotomy performed in the supine and prone positions for the treatment of pediatric kidney stones: a single-center experience.

Mini-percutaneous nephrolithotomy (MPCNL), which has a smaller tract size (14-20 Fr) than conventional percutaneous nephrolithotomy, has been shown to be safe and effective in pediatric patients with large and complex upper urinary tract stones. This study aimed to compare the efficacy and safety of MPCNL between the supine and prone positions in a pediatric population. The data of pediatric patients who underwent MPCNL at our center between January 2010 and March 2023 were retrospectively analyzed. According to the surgical position, the patients were divided into the prone (Group P) and supine (Group S) groups. In both groups, dilatation was performed using 14-18 Fr metallic dilators. The two groups were compared in terms of perioperative data, postoperative stone-free rates (SFRs), and complications. There were 36 (59%) patients in Group P and 25 (41%) patients in Group S. Stones were mostly located in the pelvis (49.2%) and second most frequently in the lower pole (27.9%). Fluoroscopy time was shorter in Group S but did not statistically significantly differ compared to Group P (p = 0.181). However, operation time was statistically significantly shorter in Group S (73.8 ± 35 vs. 99.8 ± 37.4 min, p = 0.008). Although there was no significant difference, relatively higher SFR were detected in Group S (88% vs. 83%, p = 0.725). Endoscopic combined intrarenal surgery (ECIRS) was performed on six (24%) patients in Group S, and the SFR was 100% among these patients. There was no significant difference between the two groups in terms of the presence of complications (16.7% vs. 16%, p = 0.945). Both supine and prone MPCNL appear to be safe and effective in the pediatric age group, with similar stone-free and complication rates. In the supine procedure, the operation time is shortened compared to the prone. In addition, simultaneous retrograde access has the potential to increase the overall success rate of surgery.