A New Scoring System to Predict Febrile Urinary Tract Infection After Retrograde Intrarenal Surgery

A New Scoring System to Predict Febrile Urinary Tract Infection After Retrograde Intrarenal Surgery | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A New Scoring System to Predict Febrile Urinary Tract Infection After Retrograde Intrarenal Surgery Cagdas Senel, Anil Erkan, Tanju Keten, İbrahim Can Aykanat, Ali Yasin Ozercan, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5349729/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Dec, 2024 Read the published version in Urolithiasis → Version 1 posted 4 You are reading this latest preprint version Abstract Purpose: To determine the risk factors and define a new scoring system for predicting febrile urinary tract infection (F-UTI) following retrograde intrarenal surgery (RIRS) by using machine learning methods. Methods: We retrospectively analyzed the medical records of patients who underwent RIRS and 511 patients were included in the study. The patients were divided into two groups: Group 1 consisted of 34 patients who developed postoperative F-UTI, and Group 2 consisted of 477 patients who did not. We applied feature selection to determine the relevant variables. Consistency subset evaluator and greedy stepwise techniques were used for attribute selection. Logistic regression analysis was conducted on the variables obtained through feature selection to develop our scoring system. The accuracy of discrimination was assessed using the receiver operating characteristic curve. Results: Five of the 19 variables, namely diabetes mellitus, hydronephrosis, administration type, a history of post-ureterorenoscopy (URS) UTI, and urine leukocyte count, were identified through feature selection. Binary logistic regression analysis showed that hydronephrosis, a history of post-URS UTI, and urine leukocyte count were significant independent predictors of F-UTI following RIRS. These three factors demonstrated good discrimination ability, with an area under curve value of 0.837. In the presence of at least one of these factors, 32 of 34 patients who developed postoperative F-UTI were successfully predicted. Conclusion: This new scoring system developed based on hydronephrosis, a history of post-URS UTI, and urine leukocyte count can successfully discriminate patients at risk of F-UTI development after RIRS. Figures Figure 1 INTRODUCTION In recent years, advancements in endoscopic devices and laser technology have made retrograde intrarenal surgery (RIRS) a popular minimally invasive procedure in the treatment of upper urinary tract stone disease [ 1 , 2 ]. Although RIRS achieves high stone-free rates and is associated with low morbidity, its overall complication rate varies between 5 and 25%, with infections accounting for the majority of these complications [ 3 , 4 ]. Recent systematic reviews have shown that the rates of fever, urosepsis, and septic shock following RIRS range from 2.8–17.5%, 0.5–11.1%, and 0.3–4.6%, respectively [ 5 , 6 ]. The pathogenesis of infection after RIRS is not fully understood; however, increased intrarenal pressure and the presence of bacteria in the urinary tract are considered the most likely causes [ 5 , 7 ]. To prevent the infectious complications and reduce the risk, it is important to identify risk factors. Although several published studies in the international literature have attempted to determine the risk factors for infectious complications after RIRS, these risk factors have not yet been clearly established [ 8 – 12 ]. In the current retrospective study, we aimed to identify risk factors and develop a new scoring system for predicting F-UTI following RIRS using machine learning methods. PATIENTS AND METHODS The study was conducted in accordance with the principles of the Declaration of Helsinki and approved by the local ethics committee (ruling number: 2024-TBEK 2024/08 − 02). Written informed consent was obtained from all patients. We retrospectively analyzed the medical records of 604 patients who underwent RIRS due to renal or proximal ureteral stones at two different tertiary centers from January 2021 to January 2023. We excluded patients who underwent bilateral RIRS (n = 9), those with autoimmune diseases (n = 1), those with a urosepsis history in the last six months (n = 1), and those with incomplete data (n = 82). Finally, a total of 511 patients were included in the sample, and the perioperative data of these patients were recorded. All patients were evaluated by anamnesis, medical history, physical examination, microscopic urinalysis, urine culture, and routine preoperative examination. In addition, all patients underwent a preoperative computed tomography (CT) to evaluate the urinary tract and the position and size of the stone. Patients with positive urine cultures were treated preoperatively with appropriate antibiotics until a negative urine culture was obtained. All patients received preoperative intravenous third-generation cephalosporin antibiotic prophylaxis. All operations were performed as previously described [ 13 ]. On the first postoperative day, KUB radiography was performed to check for residual stones and/or assess the location of the double-J stent. The double-J stent was inserted based on the surgeon’s decision and removed approximately 14–28 days postoperatively. Stone-free status was evaluated by low-dose, non-contrast abdominal CT 30–45 days after double-J stent removal and was defined as a completely stone-free status or the presence of residual stones of ≤ 3 mm on imaging. A postoperative F-UTI was defined as at least one episode of body temperature > 38°C with pyuria (> 10 white blood cells/high power field) or urine culture growth within ≤ 7 days after surgery [ 14 ]. The patients were divided into two groups: Group 1 consisted of 34 patients who developed postoperative F-UTI, and Group 2 consisted of 477 patients who did not. Statistical analysis Descriptive statistics were obtained, and statistical analyses for the related data set were performed using SPSS and WEKA software. Frequencies, percentages, and mean ± standard deviations of each variable were given as descriptive statistics. Then, the Kolmogorov-Smirnov test was applied to determine whether the related data set followed a normal distribution. To compare the differences between groups, the independent-samples t-test was used for continuous variables, and the chi-square test was used for categorical variables. A p-value of < 0.05 was considered statistically significant for all statistical analyses. In this study, among various machine learning techniques, consistency subset evaluator (CSE) and greedy stepwise (GS) techniques were used for attribute selection to reduce the number of variables through feature selection. The CSE technique assesses the value of a subset of attributes based on how consistently class values are maintained when the training data is projected onto that subset. Notably, the consistency of any subset is always at least as high as that of the full set of attributes. Therefore, CSE is typically used in combination with either random or exhaustive search methods to identify the smallest subset that maintains the same level of consistency as the full attribute set. In contrast, the GS method conducts a greedy search either forward or backward through the attribute subset space. It can begin with no attributes, all attributes, or any arbitrary starting point, and it terminates when adding or removing attributes no longer improves the evaluation. Additionally, GS can generate a ranked list of attributes by traversing the attribute space and recording the order in which attributes are added or removed [ 15 , 16 ]. After determining the relevant variables using CSE and GS techniques for feature selection, logistic regression analysis was performed with the selected variables to develop our scoring system. The regression coefficients (β) were multiplied by 10 and rounded to facilitate the calculation of the score. The accuracy of total score’s discrimination was assessed using the receiver operating characteristic (ROC) curve. RESULTS A total of 511 patients who met the inclusion criteria were included in the study. The mean age of the patients was 50.3 ± 14.4 years. During the follow-up period, F-UTI developed in 6.7% (n = 34) of the patients. Four of the 34 patients developed urosepsis, which was successfully treated without any morbidity or mortality. In the F-UTI group, the microorganisms grown in urine culture were Escherichia coli (n = 19), Klebsiella pneumoniae (n = 5), Pseudomonas aeruginosa (n = 4), Enterococcus faecalis (n = 3), and others (n = 3). Table 1 presents the demographics and perioperative data of the patients. Table 1 Demographic data and perioperative outcomes of the patients. Variables All patients n = 511 Group 1 (n = 34) Group 2 (n = 477) p value Age, years 50.3 ± 14.4 (18–86) 59.5 ± 10.3 (35–74) 49.7 ± 14.4 (18–86) < 0.001 Gender, n (%) Male Female 333 (65.2%) 178 (34.8%) 26 (76.5%) 8 (23.5%) 307 (64.4%) 170 (35.6%) 0.193 Diabetes mellitus, n (%) 87 (17%) 11 (32.4%) 76 (15.9%) 0.03 Modified CCI score, points 2 ± 1.8 (0–9) 3.3 ± 1.7 (0–7) 2 ± 1.7 (0–9) < 0.001 Preoperative nephrostomy, n (%) 11 (2.2%) 1 (2.9%) 10 (2.1%) 0.535 Preoperative double-J stent, n (%) 116 (22.7%) 12 (35.3%) 104 (21.8%) 0.08 Preoperative SWL, n (%) 52 (10.2%) 2 (5.9%) 50 (10.5%) 0.561 Hydronephrosis, n (%) < 20 mm ≥ 20 mm 420 (82.2%) 91 (17.8%) 20 (58.8%) 14 (41.2%) 400 (83.9%) 77 (16.1%) 0.001 Urine culture, n (%) Negative Positive 477 (93.3%) 34 (6.7%) 29 (85.3%) 5 (14.7%) 448 (93.9%) 29 (6.1%) 0.06 Urine leukocyte count, n (%) ≤ 10/hpf > 10/hpf 275 (53.8%) 236 (46.2%) 4 (11.8) 30 (88.2%) 271 (56.8%) 206 (43.2%) < 0.001 Stone location, n (%) Ureter Renal pelvis Lower calyx Middle calyx Upper calyx Multiple 41 (8%) 249 (48.7%) 73 (14.3%) 54 (10.6%) 12 (2.3%) 79 (15.5%) 3 (8.8%) 18 (52.9%) 3 (8.8%) 5 (14.7%) 1 (2.9%) 1 (2.9%) 38 (8%) 231 (48.4%) 70 (14.7%) 49 (10.3%) 11 (2.3%) 78 (16.4%) 0.747 0.723 0.453 0.388 0.566 0.045 Urinary anomaly, n (%) 48 (9.4%) – 48 (10.1%) 0.062 Surgery time, min 62.3 ± 21.2 (15–140) 56 ± 12.3 (40–85) 62.8 ± 21.6 (15–140) 0.006 History of post-URS UTI, n (%) 16 (3.1%) 9 (26.5%) 7 (1.5%) < 0.001 NLR 2.6 ± 1.4 (0.6–12.4) 2.2 ± 1 (1.3–5.3) 2.6 ± 1.4 (0.6–12.4) 0.138 PLR 138.2 ± 55.9 (33.4–390) 111.5 ± 53.7 (47.1–362.4) 140.1 ± 55.6 (33.4–390) 0.004 Stone-free status, n (%) 383 (75%) 23 (67.6%) 360 (75.5%) 0.310 Stone size, mm 15 ± 5.3 (4–40) 12.4 ± 4.6 (7–30) 15.2 ± 5.3 (4–40) 0.003 Administration type, n (%) Elective Emergency 472 (92.4%) 39 (7.6%) 29 (85.3%) 5 (14.7%) 443 (92.9%) 34 (7.1%) 0.168 CCI: Charlson comorbidity index, SWL: shock wave lithotripsy, URS: ureterorenoscopy, NLR: neutrophil-to-lymphocyte ratio, PLR: platelet-to-lymphocyte ratio. Bold values indicate statistically significant differences. Among the 19 potential risk factors for infectious complications, five variables, namely diabetes mellitus, hydronephrosis, administration type, a history of post-ureterorenoscopy (URS) UTI, and urine leukocyte count, were identified through feature selection. Binary logistic regression analysis revealed that among these variables, hydronephrosis (p = 0.011), a history of post-URS UTI (p = 0.007), and urine leukocyte count (p = 0.001) were significant independent predictors of F-UTI following RIRS. The regression coefficients (β) were multiplied by 10 to obtain the score points for the risk factors (Table 2 ). The ROC curve showed that our model had good discrimination ability, with an area under the curve (AUC) value of 0.837 (95% confidence interval: 0.765–0.910) (Fig. 1 ). Table 2 Binary logistic regression analysis of the variables identified through feature selection. Variables HR (95% CI) p value ß Score points Diabetes mellitus 1.326 (0.370–4.745) 0.665 - - Hydronephrosis 0.360 (0.163–0.791) 0.011 1.023 10 Administration type 1.176 (0.243–5.691) 0.841 - - History of post-URS UTI 0.163 (0.043–0.613) 0.007 1.814 18 Urine leukocyte count 0.157 (0.053–0.470) 0.001 1.849 18 Bold values indicate statistically significant differences. The regression coefficients (β) were multiplied by 10 and rounded to facilitate the calculation of the score. According to our scoring system, nearly half of the F-UTI (-) patients had 0 points, while 94.1% of the patients in the F-UTI (+) group had ≥ 10 points (Table 3 ). Table 3 Distribution of the patients in the groups according to the total score. Total score Group 1 (n = 34) Group 2 (n = 477) 0 points (n = 235) 2 (5.9%) 233 (48.8%) 10 points (n = 38) 2 (5.9%) 36 (7.5%) 18 points (n = 172) 9 (26.5%) 163 (34.2%) 28 points (n = 52) 12 (35.3%) 40 (8.4%) 36 points (n = 13) 9 (26.5%) 4 (0.8%) 46 points (n = 1) 0 1 (0.2%) DISCUSSION In the current study, data from two different tertiary centers was collected to develop a scoring system using machine learning algorithms to predict F-UTI in patients undergoing RIRS for upper urinary tract stone disease. Our scoring system is easy to apply for all patients undergoing RIRS because all the parameters included in this study were part of the routine evaluation for patients undergoing stone surgery. Due to variations in the definition and standardization of infectious complications of RIRS, the incidence of postoperative infectious complications varies in a wide range [ 3 ]. Previous reports indicate that the incidence of postoperative fever after RIRS can reach 17.5% [ 9 ]. Dybowski et al. [ 5 ] found that the mean postoperative fever incidence across 14 studies was 7.1%, which is similar to our rate of 6.6%. Preoperatively determining the risk factors for infection and identifying patients with a high risk of postoperative F-UTI may influence antibiotic prophylaxis strategies and patient management. In recent years, several studies have aimed to determine the risk factors for infectious complications following RIRS. The most commonly reported risk factors include stone size, operative time, a history of UTI, urinary leukocyte esterase/nitrite, and comorbidities, mainly diabetes mellitus [ 9 – 12 , 17 – 19 ]. In contrast, in a multicenter study, Berardinelli et al. [ 8 ] found that none of the factors could identify a high-risk patient group for infection. The authors noted that the low complication rate might have limited the results and concluded that, due to this limitation, the risk factors remained unclear. A systematic review of 17 studies reported that long operative time, a history of UTI, urinary pyuria/nitrites, the use of a small-caliber ureteral access sheath, the presence of struvite stones, high irrigation rates, and comorbidities were independent risk factors for infectious complications after RIRS [ 5 ]. Another systematic review by Corrales et al. [ 6 ] identified mostly different risk factors for sepsis in RIRS, namely stone size, high irrigation pressure, prolonged stent dwelling time (> 30 d), sepsis as an indication for stent insertion, female gender, positive intraoperative bladder urine culture, longer surgical time, and diabetes mellitus. The low complication rate and/or a lack of standardization of infectious complications challenge the identification of definitive risk factors. Thus, it remains unclear which factors reliably predict post-URS infection. In the current study, we found that hydronephrosis, a history of post-URS UTI, and urine leukocyte count were significant risk factors for F-UTI. In contrast to our results, several studies [ 5 , 6 , 9 – 11 ] reported that hydronephrosis was not a risk factor for infection after RIRS. Zhao et al. [ 20 ] determined that a hydronephrosis level of ≤ 20 mm was a preoperative risk factor. The authors speculated that in patients with hydronephrosis, an increased intrarenal reflux threshold might reduce the risk of bacterial contamination of the bloodstream. However, studies by Matsumoto et al. [ 21 ] and Sohn et al. [ 22 ] found that a higher degree of hydronephrosis was a risk factor for infectious complications following upper urinary tract procedures, which is consistent with our results. We believe that obstruction of urine flow creates a conducive environment for bacterial growth, and a higher degree of hydronephrosis may be a significant risk factor for infection after RIRS. Although pyuria was identified as another risk factor for F-UTI in our study, there is some debate on this matter in the international literature. Dybowski et al. [ 5 ] found pyuria as one of seven risk factors for infectious complications after RIRS. However, studies by Hao et al. [ 11 ] and Qi et al. [ 12 ] indicated that urinary leukocyte count was not a risk factor for sepsis and fever, respectively. Our results suggest that although it can be difficult to determine whether all cases of pyuria are due to an infection, pyuria is an important marker of infection and a risk factor for F-UTI. Several studies have found that a history of UTI is a risk factor for postoperative infection following RIRS [ 17 , 19 , 23 ]. In contrast, Li et al. [ 9 ] reported that a history of UTI was not a risk factor for postoperative fever or systemic inflammatory response syndrome. We believe that the lack of urine culture results can make it difficult to accurately document a history of UTI. In addition, based on our clinical observations, we hypothesized that a history of post-URS UTI might be associated with recurrent post-URS F-UTI. Therefore, we included this parameter in our analysis. The results obtained from the machine learning method supported our clinical observations, indicating that a history of post-URS UTI was an independent risk factor for F-UTI in patients who underwent RIRS. To the best of our knowledge, only one study in the international literature has assessed the history of post-URS infection and found a weak relationship [ 24 ]. Machine learning methods, a subfield of artificial intelligence in healthcare, allow for more accurate predictions by revealing complex relationships in large databases compared to classical statistical methods [ 25 ]. In recent years, these applications have been expanding in urological practice and are expected to become more common in decision-making processes [ 25 , 26 ]. Studies on machine learning methods in urology have shown promising results [ 27 – 29 ]. Feature selection, a fundamental topic of machine learning, is used extensively in predictive applications. Therefore, we used a feature selection method to identify the relevant predictive factors of post-RIRS F-UTI, rather than relying on classical models. A retrospective multicenter study by Pietropaolo [ 24 ] determined the predictors of post-URS urosepsis using a machine learning model. The authors found that proximal stone location, large stone size, prolonged stent duration, and extended operative time were the parameters with the highest predictive value. In addition, their machine learning model achieved an AUC value of 0.89. In a recent study comparing models generated by classical statistical methods and machine learning algorithms to predict postoperative infection after RIRS, it was found that machine learning models had a higher AUC compared to classical statistical models (0.956 vs. 0.785) [ 30 ]. The authors concluded that machine learning models were more reliable and predictive compared to traditional models. In the current study, we used machine learning to select the relevant predictive features. Following feature selection, we performed logistic regression analysis to determine significant predictors and create the model. Our model demonstrated a high AUC value (0.837), comparable to previous machine learning models. However, we identified different risk factors, which we believe may be due to our use of feature selection to reduce the number of variables, a method that differed from previous studies. A few limitations of this study must be noted. The main limitation of our study is its retrospective nature. In addition, some parameters, including stone density and serum C-reactive protein level, were excluded from feature selection due to missing data. We consider that the external validation of our model is necessary to confirm its reliability and power. CONCLUSION The results of our study demonstrated that hydronephrosis, a history of post-URS UTI, and urine leukocyte count were significant predictive parameters of F-UTI following RIRS. We believe that patients with these risk factors should be closely monitored for postoperative infection to reduce morbidity and mortality. Our results need to be confirmed with further studies. Declarations The authors have no relevant financial or non-financial interests to disclose. Author Contribution CS: Project development, Manuscript writing, Data collection. AE: Data collection. TK: Data management. ICA: Manuscript writing. AYO: Data management. KT: Data management. SB: Data management. SS: Data analysis. OG: Project development, Manuscript writing. AT: Project development, Manuscript editing. References Raheem OA, Khandwala YS, Sur RL, Ghani KR, Denstedt JD (2017) Burden of Urolithiasis: Trends in Prevalence, Treatments, and Costs. Eur Urol Focus 3:18–26. https://doi.org/10.1016/j.euf.2017.04.001 Pietropaolo A, Proietti S, Geraghty R, Skolarikos A, Papatsoris A, Liatsikos E, Somani BK (2017) Trends of 'urolithiasis: interventions, simulation, and laser technology' over the last 16 years (2000–2015) as published in the literature (PubMed): a systematic review from European section of Uro-technology (ESUT). World J Urol 35:1651–1658. https://doi.org/10.1007/s00345-017-2055-z Grosso AA, Sessa F, Campi R et al (2021) Intraoperative and postoperative surgical complications after ureteroscopy, retrograde intrarenal surgery, and percutaneous nephrolithotomy: a systematic review. Minerva Urol Nephrol 73:309–332. https://doi.org/10.23736/S2724-6051.21.04294-4 Baş O, Tuygun C, Dede O, Sarı S, Çakıcı M, Öztürk U, Göktuğ G, İmamoğlu A (2017) Factors affecting complication rates of retrograde flexible ureterorenoscopy: analysis of 1571 procedures-a single-center experience. World J Urol 35:819–826. https://doi.org/10.1007/s00345-016-1930-3 Dybowski B, Bres-Niewada E, Rzeszutko M, Tkaczyk A, Woźniak B, Wójcik M, Znajdek Z (2021) Risk factors for infectious complications after retrograde intrarenal surgery - a systematic review and narrative synthesis. Cent Eur J Urol 74:437–445. https://doi.org/10.5173/ceju.2021.250 Corrales M, Sierra A, Doizi S, Traxer O (2022) Risk of Sepsis in Retrograde Intrarenal Surgery: A Systematic Review of the Literature. Eur Urol Open Sci 44:84–91. https://doi.org/10.1016/j.euros.2022.08.008 Parkhomenko E, De Fazio A, Tran T, Thai J, Blum K, Gupta M (2017) A Multi-Institutional Study of Struvite Stones: Patterns of Infection and Colonization. J Endourol 31:533–537. https://doi.org/10.1089/end.2016.0885 Berardinelli F, De Francesco P, Marchioni M et al (2016) Infective complications after retrograde intrarenal surgery: a new standardized classification system. Int Urol Nephrol 48:1757–1762. https://doi.org/10.1007/s11255-016-1373-1 Li T, Sun XZ, Lai DH, Li X, He YZ (2018) Fever and systemic inflammatory response syndrome after retrograde intrarenal surgery: Risk factors and predictive model. Kaohsiung J Med Sci 34:400–408. https://doi.org/10.1016/j.kjms.2018.01.002 Xuan Z, Yu Z, Tan G, Ding N, He H, Yu S, Liu G, Zhu X, Zhu B, Liu Z (2022) Development and validation of a novel nomogram for predicting systemic inflammatory response syndrome's occurrence in patients undertaking flexible ureteroscopy. Transl Androl Urol 11:228–237. https://doi.org/10.21037/tau-22-34 Hao X, Wang X, Ding H, Zheng S, Li Z, Yin H, Wang L, Luo J, Wei H (2022) A model for sepsis prediction after retrograde intrarenal surgery and the use of the preoperative/postoperative white blood cell ratio to predict progression from sepsis to septic shock. World J Urol 40:2979–2990. https://doi.org/10.1007/s00345-022-04182-1 Qi Q, Hu Y, Chen Y, Yan Q, Xu Y, Liang H, Liang C, Hao Z (2023) Nomogram for predicting risk factors of fever in patients with negative preoperative urine culture after retrograde intrarenal surgery. World J Urol 41:783–789. https://doi.org/10.1007/s00345-023-04302-5 Senel C, Tuncel A, Balci M, Asfuroglu A, Aykanat C, Guzel O, Aslan Y (2018) Safety and reliability of fluoroscopy-free technique in retrograde intrarenal surgery. Minerva Urol Nefrol 70:606–611. https://doi.org/10.23736/S0393-2249.18.03228-9 Deng T, Liu B, Duan X, Cai C, Zhao Z, Zhu W, Fan J, Wu W, Zeng G (2018) Antibiotic prophylaxis in ureteroscopic lithotripsy: a systematic review and meta-analysis of comparative studies. BJU Int 122:29–39. https://doi.org/10.1111/bju.14101 Devi MI, Rajaram R, Selvakuberan K (2008) Generating best features for web page classification. Webology 5:52 Ali A, Jillani F, Zaheer R, Karim A, Alharbi YO, Alsaffar M, Alhamazani K (2022) Practically implementation of information loss: sensitivity, risk by different feature selection techniques. IEEE Access 10:27643–27654 Baboudjian M, Gondran-Tellier B, Abdallah R, Sichez PC, Akiki A, Gaillet S, Delaporte V, Karsenty G, Lechevallier E, Boissier R (2020) Predictive risk factors of urinary tract infection following flexible ureteroscopy despite preoperative precautions to avoid infectious complications. World J Urol 38:1253–1259. https://doi.org/10.1007/s00345-019-02891-8 Zhang H, Jiang T, Gao R, Chen Q, Chen W, Liu C, Mao H (2020) Risk factors of infectious complications after retrograde intrarenal surgery: a retrospective clinical analysis. J Int Med Res 48:300060520956833. https://doi.org/10.1177/0300060520956833 Yang M, Li Y, Huang F (2023) A nomogram for predicting postoperative urosepsis following retrograde intrarenal surgery in upper urinary calculi patients with negative preoperative urine culture. Sci Rep 13:2123. https://doi.org/10.1038/s41598-023-29352-y Zhao Z, Sun H, Zhu W, Liu Y, Zhong W, Liu Y, Zeng G (2023) A new model to assist decision-making of optimal antibiotics duration for treating asymptomatic bacteriuria or pyuria prior to retrograde intrarenal surgery. Minerva Urol Nephrol 75:486–492. https://doi.org/10.23736/S2724-6051.21.04454-2 Matsumoto M, Shigemura K, Yamamichi F, Tanaka K, Nakano Y, Arakawa S, Fujisawa M (2012) Prevention of infectious complication and its risk factors after urological procedures of the upper urinary tract. Urol Int 88:43–47. https://doi.org/10.1159/000332224 Sohn DW, Kim SW, Hong CG, Yoon BI, Ha US, Cho YH (2013) Risk factors of infectious complication after ureteroscopic procedures of the upper urinary tract. J Infect Chemother 19:1102–1108. https://doi.org/10.1007/s10156-013-0632-7 Baseskioglu B (2019) The Prevalence of Urinary Tract Infection Following Flexible Ureterenoscopy and the Associated Risk Factors. Urol J 16:439–442. https://doi.org/10.22037/uj.v0i0.4340 Pietropaolo A, Geraghty RM, Veeratterapillay R et al (2021) A Machine Learning Predictive Model for Post-Ureteroscopy Urosepsis Needing Intensive Care Unit Admission: A Case-Control YAU Endourology Study from Nine European Centres. J Clin Med 10:3888. https://doi.org/10.3390/jcm10173888 Checcucci E, Autorino R, Cacciamani GE et al (2020) Artificial intelligence and neural networks in urology: current clinical applications. Minerva Urol Nefrol 72:49–57. https://doi.org/10.23736/S0393-2249.19.03613-0 Shah M, Naik N, Somani BK, Hameed BMZ (2020) Artificial intelligence (AI) in urology-Current use and future directions: An iTRUE study. Turk J Urol 46(1):S27–S39. https://doi.org/10.5152/tud.2020.20117 Blum ES, Porras AR, Biggs E, Tabrizi PR, Sussman RD, Sprague BM, Shalaby-Rana E, Majd M, Pohl HG, Linguraru MG (2018) Early Detection of Ureteropelvic Junction Obstruction Using Signal Analysis and Machine Learning: A Dynamic Solution to a Dynamic Problem. J Urol 199:847–852. https://doi.org/10.1016/j.juro.2017.09.147 Aminsharifi A, Irani D, Tayebi S, Jafari Kafash T, Shabanian T, Parsaei H (2020) Predicting the Postoperative Outcome of Percutaneous Nephrolithotomy with Machine Learning System: Software Validation and Comparative Analysis with Guy's Stone Score and the CROES Nomogram. J Endourol 34:692–699. https://doi.org/10.1089/end.2019.0475 Altıntaş E, Şahin A, Babayev H, Gül M, Batur AF, Kaynar M, Kılıç Ö, Göktaş S (2024) Machine learning algorithm predicts urethral stricture following transurethral prostate resection. World J Urol 42:324. https://doi.org/10.1007/s00345-024-05017-x Ekşi M, Fakir AE, Evren İ, Şam E, Arıkan Y, Kargı T, Hacıislamoğlu A, Yavuzsan AH, Şahin S, Taşçı A (2023) Prediction of infective complications after retrograde intra renal surgery using Machine learning. Minim Invasive Ther Allied Technol 32:73–80. https://doi.org/10.1080/13645706.2023.2186181 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 24 Dec, 2024 Read the published version in Urolithiasis → Version 1 posted Editorial decision: Revision requested 30 Oct, 2024 Editor assigned by journal 29 Oct, 2024 Submission checks completed at journal 29 Oct, 2024 First submitted to journal 28 Oct, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5349729","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":372286653,"identity":"9ea57aae-4a04-4fb6-b53a-297d1dfa38ab","order_by":0,"name":"Cagdas Senel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYJACCSjNeOBjA5huPECsFoaDMxtAHMYG4rUc5m2AcPBq4W8/fvHGjz8M9vzSzQcO2+6wqdNtPwy0pcYmGqcNZ3KKLXvbGBJnzjmWcDj3TJqE2ZlEoJZjabkNOLQYMOSkSQDdk2BwI8fgcG7bYQmzA0AtjA2HcWvhf5Mm+QfoMPsb+R8OW4K0nH9IQItE+jFpHjYGxg0SOQyHGUFabhCwReLGG2ZrWaBfZtxIMzjY25Ymue0G0JYEPH7h709/ePMNKMRmJD988LPNht/sfPrDBx9qbHBqYWDgMQAS/9EEE3AqBwH2B3ilR8EoGAWjYBQwAADdJ2VEcZ+ISAAAAABJRU5ErkJggg==","orcid":"","institution":"Balıkesir University","correspondingAuthor":true,"prefix":"","firstName":"Cagdas","middleName":"","lastName":"Senel","suffix":""},{"id":372286654,"identity":"cefb6b13-239d-49f3-a1c4-f0825fd64eb9","order_by":1,"name":"Anil Erkan","email":"","orcid":"","institution":"Bursa Yuksek Ihtisas Egitim Ve Arastirma Hastanesi","correspondingAuthor":false,"prefix":"","firstName":"Anil","middleName":"","lastName":"Erkan","suffix":""},{"id":372286655,"identity":"3b8668de-a508-46b6-ad69-7d0b655f55ce","order_by":2,"name":"Tanju Keten","email":"","orcid":"","institution":"university of health sciences school of medicine, Ankara State Hospital","correspondingAuthor":false,"prefix":"","firstName":"Tanju","middleName":"","lastName":"Keten","suffix":""},{"id":372286656,"identity":"5e342394-d9b0-4d45-ae04-15fd0a7bb094","order_by":3,"name":"İbrahim Can Aykanat","email":"","orcid":"","institution":"Koç University","correspondingAuthor":false,"prefix":"","firstName":"İbrahim","middleName":"Can","lastName":"Aykanat","suffix":""},{"id":372286657,"identity":"1345fef0-e4fb-4482-8d19-23a1629ea5ed","order_by":4,"name":"Ali Yasin Ozercan","email":"","orcid":"","institution":"Ministry of Health, Sirnak State Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ali","middleName":"Yasin","lastName":"Ozercan","suffix":""},{"id":372286658,"identity":"8eae754c-a44e-4343-9af0-cfe0cc4d998e","order_by":5,"name":"Koray Tatlici","email":"","orcid":"","institution":"university of health sciences school of medicine, Ankara State Hospital","correspondingAuthor":false,"prefix":"","firstName":"Koray","middleName":"","lastName":"Tatlici","suffix":""},{"id":372286659,"identity":"c0a9cb5f-052f-40b5-8182-30c470a0ea78","order_by":6,"name":"Serdar Basboga","email":"","orcid":"","institution":"university of health sciences school of medicine, Ankara State Hospital","correspondingAuthor":false,"prefix":"","firstName":"Serdar","middleName":"","lastName":"Basboga","suffix":""},{"id":372286660,"identity":"0c755965-14eb-4011-a7d1-f828bffda4fc","order_by":7,"name":"Sinan Saracli","email":"","orcid":"","institution":"Balıkesir University","correspondingAuthor":false,"prefix":"","firstName":"Sinan","middleName":"","lastName":"Saracli","suffix":""},{"id":372286661,"identity":"b3d62452-6c92-406b-a7ef-a3a5d762cf62","order_by":8,"name":"Ozer Guzel","email":"","orcid":"","institution":"university of health sciences school of medicine, Ankara State Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ozer","middleName":"","lastName":"Guzel","suffix":""},{"id":372286662,"identity":"4e97791f-aa32-48e9-b9be-0a373e9f1c18","order_by":9,"name":"Altug Tuncel","email":"","orcid":"","institution":"university of health sciences school of medicine, Ankara State Hospital","correspondingAuthor":false,"prefix":"","firstName":"Altug","middleName":"","lastName":"Tuncel","suffix":""}],"badges":[],"createdAt":"2024-10-28 21:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5349729/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5349729/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00240-024-01685-x","type":"published","date":"2024-12-24T15:56:56+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":69437909,"identity":"80edc19d-cbbc-4492-9dfa-11efae22762b","added_by":"auto","created_at":"2024-11-20 10:52:36","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":104661,"visible":true,"origin":"","legend":"\u003cp\u003eThe receiver operating characteristic curve of our scoring system.\u003c/p\u003e","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5349729/v1/01ca6e73ff06512f63ddfb7a.jpeg"},{"id":72640363,"identity":"7ad1290e-7339-4e5b-b47b-d0f2e06e4f33","added_by":"auto","created_at":"2024-12-30 16:04:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":571038,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5349729/v1/299ab625-064e-4c6e-a08f-fa7bbe556fd0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A New Scoring System to Predict Febrile Urinary Tract Infection After Retrograde Intrarenal Surgery","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003eIn recent years, advancements in endoscopic devices and laser technology have made retrograde intrarenal surgery (RIRS) a popular minimally invasive procedure in the treatment of upper urinary tract stone disease [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Although RIRS achieves high stone-free rates and is associated with low morbidity, its overall complication rate varies between 5 and 25%, with infections accounting for the majority of these complications [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Recent systematic reviews have shown that the rates of fever, urosepsis, and septic shock following RIRS range from 2.8\u0026ndash;17.5%, 0.5\u0026ndash;11.1%, and 0.3\u0026ndash;4.6%, respectively [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe pathogenesis of infection after RIRS is not fully understood; however, increased intrarenal pressure and the presence of bacteria in the urinary tract are considered the most likely causes [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. To prevent the infectious complications and reduce the risk, it is important to identify risk factors. Although several published studies in the international literature have attempted to determine the risk factors for infectious complications after RIRS, these risk factors have not yet been clearly established [\u003cspan additionalcitationids=\"CR9 CR10 CR11\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn the current retrospective study, we aimed to identify risk factors and develop a new scoring system for predicting F-UTI following RIRS using machine learning methods.\u003c/p\u003e"},{"header":"PATIENTS AND METHODS","content":"\u003cp\u003e The study was conducted in accordance with the principles of the Declaration of Helsinki and approved by the local ethics committee (ruling number: 2024-TBEK 2024/08\u0026thinsp;\u0026minus;\u0026thinsp;02). Written informed consent was obtained from all patients. We retrospectively analyzed the medical records of 604 patients who underwent RIRS due to renal or proximal ureteral stones at two different tertiary centers from January 2021 to January 2023. We excluded patients who underwent bilateral RIRS (n\u0026thinsp;=\u0026thinsp;9), those with autoimmune diseases (n\u0026thinsp;=\u0026thinsp;1), those with a urosepsis history in the last six months (n\u0026thinsp;=\u0026thinsp;1), and those with incomplete data (n\u0026thinsp;=\u0026thinsp;82). Finally, a total of 511 patients were included in the sample, and the perioperative data of these patients were recorded.\u003c/p\u003e \u003cp\u003eAll patients were evaluated by anamnesis, medical history, physical examination, microscopic urinalysis, urine culture, and routine preoperative examination. In addition, all patients underwent a preoperative computed tomography (CT) to evaluate the urinary tract and the position and size of the stone. Patients with positive urine cultures were treated preoperatively with appropriate antibiotics until a negative urine culture was obtained. All patients received preoperative intravenous third-generation cephalosporin antibiotic prophylaxis.\u003c/p\u003e \u003cp\u003eAll operations were performed as previously described [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. On the first postoperative day, KUB radiography was performed to check for residual stones and/or assess the location of the double-J stent. The double-J stent was inserted based on the surgeon\u0026rsquo;s decision and removed approximately 14\u0026ndash;28 days postoperatively. Stone-free status was evaluated by low-dose, non-contrast abdominal CT 30\u0026ndash;45 days after double-J stent removal and was defined as a completely stone-free status or the presence of residual stones of \u0026le;\u0026thinsp;3 mm on imaging.\u003c/p\u003e \u003cp\u003eA postoperative F-UTI was defined as at least one episode of body temperature\u0026thinsp;\u0026gt;\u0026thinsp;38\u0026deg;C with pyuria (\u0026gt;\u0026thinsp;10 white blood cells/high power field) or urine culture growth within \u0026le;\u0026thinsp;7 days after surgery [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. The patients were divided into two groups: Group 1 consisted of 34 patients who developed postoperative F-UTI, and Group 2 consisted of 477 patients who did not.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eDescriptive statistics were obtained, and statistical analyses for the related data set were performed using SPSS and WEKA software. Frequencies, percentages, and mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviations of each variable were given as descriptive statistics. Then, the Kolmogorov-Smirnov test was applied to determine whether the related data set followed a normal distribution. To compare the differences between groups, the independent-samples t-test was used for continuous variables, and the chi-square test was used for categorical variables. A p-value of \u0026lt;\u0026thinsp;0.05 was considered statistically significant for all statistical analyses.\u003c/p\u003e \u003cp\u003eIn this study, among various machine learning techniques, consistency subset evaluator (CSE) and greedy stepwise (GS) techniques were used for attribute selection to reduce the number of variables through feature selection. The CSE technique assesses the value of a subset of attributes based on how consistently class values are maintained when the training data is projected onto that subset. Notably, the consistency of any subset is always at least as high as that of the full set of attributes. Therefore, CSE is typically used in combination with either random or exhaustive search methods to identify the smallest subset that maintains the same level of consistency as the full attribute set. In contrast, the GS method conducts a greedy search either forward or backward through the attribute subset space. It can begin with no attributes, all attributes, or any arbitrary starting point, and it terminates when adding or removing attributes no longer improves the evaluation. Additionally, GS can generate a ranked list of attributes by traversing the attribute space and recording the order in which attributes are added or removed [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAfter determining the relevant variables using CSE and GS techniques for feature selection, logistic regression analysis was performed with the selected variables to develop our scoring system. The regression coefficients (β) were multiplied by 10 and rounded to facilitate the calculation of the score. The accuracy of total score\u0026rsquo;s discrimination was assessed using the receiver operating characteristic (ROC) curve.\u003c/p\u003e \u003c/div\u003e"},{"header":"RESULTS","content":"\u003cp\u003eA total of 511 patients who met the inclusion criteria were included in the study. The mean age of the patients was 50.3\u0026thinsp;\u0026plusmn;\u0026thinsp;14.4 years. During the follow-up period, F-UTI developed in 6.7% (n\u0026thinsp;=\u0026thinsp;34) of the patients. Four of the 34 patients developed urosepsis, which was successfully treated without any morbidity or mortality. In the F-UTI group, the microorganisms grown in urine culture were \u003cem\u003eEscherichia coli\u003c/em\u003e (n\u0026thinsp;=\u0026thinsp;19), \u003cem\u003eKlebsiella pneumoniae\u003c/em\u003e (n\u0026thinsp;=\u0026thinsp;5), \u003cem\u003ePseudomonas aeruginosa\u003c/em\u003e (n\u0026thinsp;=\u0026thinsp;4), \u003cem\u003eEnterococcus faecalis\u003c/em\u003e (n\u0026thinsp;=\u0026thinsp;3), and others (n\u0026thinsp;=\u0026thinsp;3). Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e presents the demographics and perioperative data of the patients.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographic data and perioperative outcomes of the patients.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAll patients\u003c/p\u003e \u003cp\u003en\u0026thinsp;=\u0026thinsp;511\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGroup 1\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;34)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eGroup 2\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;477)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ep value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, years\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e50.3\u0026thinsp;\u0026plusmn;\u0026thinsp;14.4 (18\u0026ndash;86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e59.5\u0026thinsp;\u0026plusmn;\u0026thinsp;10.3 (35\u0026ndash;74)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e49.7\u0026thinsp;\u0026plusmn;\u0026thinsp;14.4 (18\u0026ndash;86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGender, n (%)\u003c/p\u003e \u003cp\u003e\u003cem\u003eMale\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eFemale\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e333 (65.2%)\u003c/p\u003e \u003cp\u003e178 (34.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26 (76.5%)\u003c/p\u003e \u003cp\u003e8 (23.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e307 (64.4%)\u003c/p\u003e \u003cp\u003e170 (35.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.193\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes mellitus, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e87 (17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (32.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e76 (15.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e0.03\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModified CCI score, points\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.8 (0\u0026ndash;9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7 (0\u0026ndash;7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7 (0\u0026ndash;9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePreoperative nephrostomy, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (2.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (2.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10 (2.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.535\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePreoperative double-J stent, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e116 (22.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12 (35.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e104 (21.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePreoperative SWL, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e52 (10.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (5.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e50 (10.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.561\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHydronephrosis, n (%)\u003c/p\u003e \u003cp\u003e\u003cem\u003e\u0026lt;\u0026thinsp;20 mm\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003e\u0026ge;\u0026thinsp;20 mm\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e420 (82.2%)\u003c/p\u003e \u003cp\u003e91 (17.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e20 (58.8%)\u003c/p\u003e \u003cp\u003e14 (41.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e400 (83.9%)\u003c/p\u003e \u003cp\u003e77 (16.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrine culture, n (%)\u003c/p\u003e \u003cp\u003e\u003cem\u003eNegative\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003ePositive\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e477 (93.3%)\u003c/p\u003e \u003cp\u003e34 (6.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e29 (85.3%)\u003c/p\u003e \u003cp\u003e5 (14.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e448 (93.9%)\u003c/p\u003e \u003cp\u003e29 (6.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrine leukocyte count, n (%)\u003c/p\u003e \u003cp\u003e\u003cem\u003e\u0026le;\u0026thinsp;10/hpf\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003e\u0026gt;\u0026thinsp;10/hpf\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e275 (53.8%)\u003c/p\u003e \u003cp\u003e236 (46.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (11.8)\u003c/p\u003e \u003cp\u003e30 (88.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e271 (56.8%)\u003c/p\u003e \u003cp\u003e206 (43.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStone location, n (%)\u003c/p\u003e \u003cp\u003e\u003cem\u003eUreter\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eRenal pelvis\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eLower calyx\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eMiddle calyx\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eUpper calyx\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eMultiple\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e41 (8%)\u003c/p\u003e \u003cp\u003e249 (48.7%)\u003c/p\u003e \u003cp\u003e73 (14.3%)\u003c/p\u003e \u003cp\u003e54 (10.6%)\u003c/p\u003e \u003cp\u003e12 (2.3%)\u003c/p\u003e \u003cp\u003e79 (15.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (8.8%)\u003c/p\u003e \u003cp\u003e18 (52.9%)\u003c/p\u003e \u003cp\u003e3 (8.8%)\u003c/p\u003e \u003cp\u003e5 (14.7%)\u003c/p\u003e \u003cp\u003e1 (2.9%)\u003c/p\u003e \u003cp\u003e1 (2.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e38 (8%)\u003c/p\u003e \u003cp\u003e231 (48.4%)\u003c/p\u003e \u003cp\u003e70 (14.7%)\u003c/p\u003e \u003cp\u003e49 (10.3%)\u003c/p\u003e \u003cp\u003e11 (2.3%)\u003c/p\u003e \u003cp\u003e78 (16.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.747\u003c/p\u003e \u003cp\u003e0.723\u003c/p\u003e \u003cp\u003e0.453\u003c/p\u003e \u003cp\u003e0.388\u003c/p\u003e \u003cp\u003e0.566\u003c/p\u003e \u003cp\u003e\u003cb\u003e0.045\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrinary anomaly, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e48 (9.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026ndash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e48 (10.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.062\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSurgery time, min\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e62.3\u0026thinsp;\u0026plusmn;\u0026thinsp;21.2 (15\u0026ndash;140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56\u0026thinsp;\u0026plusmn;\u0026thinsp;12.3 (40\u0026ndash;85)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e62.8\u0026thinsp;\u0026plusmn;\u0026thinsp;21.6 (15\u0026ndash;140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e0.006\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHistory of post-URS UTI, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (3.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (26.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7 (1.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNLR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4 (0.6\u0026ndash;12.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1 (1.3\u0026ndash;5.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4 (0.6\u0026ndash;12.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.138\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePLR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e138.2\u0026thinsp;\u0026plusmn;\u0026thinsp;55.9 (33.4\u0026ndash;390)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e111.5\u0026thinsp;\u0026plusmn;\u0026thinsp;53.7 (47.1\u0026ndash;362.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e140.1\u0026thinsp;\u0026plusmn;\u0026thinsp;55.6 (33.4\u0026ndash;390)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e0.004\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c6\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStone-free status, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e383 (75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e23 (67.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e360 (75.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e0.310\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStone size, mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e15\u0026thinsp;\u0026plusmn;\u0026thinsp;5.3 (4\u0026ndash;40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.4\u0026thinsp;\u0026plusmn;\u0026thinsp;4.6 (7\u0026ndash;30)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e15.2\u0026thinsp;\u0026plusmn;\u0026thinsp;5.3 (4\u0026ndash;40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e\u003cb\u003e0.003\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdministration type, n (%)\u003c/p\u003e \u003cp\u003e\u003cem\u003eElective\u003c/em\u003e\u003c/p\u003e \u003cp\u003e\u003cem\u003eEmergency\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e472 (92.4%)\u003c/p\u003e \u003cp\u003e39 (7.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e29 (85.3%)\u003c/p\u003e \u003cp\u003e5 (14.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e443 (92.9%)\u003c/p\u003e \u003cp\u003e34 (7.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e0.168\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"6\"\u003eCCI: Charlson comorbidity index, SWL: shock wave lithotripsy, URS: ureterorenoscopy, NLR: neutrophil-to-lymphocyte ratio, PLR: platelet-to-lymphocyte ratio.\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"6\"\u003eBold values indicate statistically significant differences.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eAmong the 19 potential risk factors for infectious complications, five variables, namely diabetes mellitus, hydronephrosis, administration type, a history of post-ureterorenoscopy (URS) UTI, and urine leukocyte count, were identified through feature selection. Binary logistic regression analysis revealed that among these variables, hydronephrosis (p\u0026thinsp;=\u0026thinsp;0.011), a history of post-URS UTI (p\u0026thinsp;=\u0026thinsp;0.007), and urine leukocyte count (p\u0026thinsp;=\u0026thinsp;0.001) were significant independent predictors of F-UTI following RIRS. The regression coefficients (β) were multiplied by 10 to obtain the score points for the risk factors (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). The ROC curve showed that our model had good discrimination ability, with an area under the curve (AUC) value of 0.837 (95% confidence interval: 0.765\u0026ndash;0.910) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eBinary logistic regression analysis of the variables identified through feature selection.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHR (95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ep value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026szlig;\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eScore points\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes mellitus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.326 (0.370\u0026ndash;4.745)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.665\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHydronephrosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.360 (0.163\u0026ndash;0.791)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e0.011\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdministration type\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.176 (0.243\u0026ndash;5.691)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.841\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHistory of post-URS UTI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.163 (0.043\u0026ndash;0.613)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e0.007\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.814\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrine leukocyte count\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.157 (0.053\u0026ndash;0.470)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.849\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003eBold values indicate statistically significant differences.\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003eThe regression coefficients (β) were multiplied by 10 and rounded to facilitate the calculation of the score.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eAccording to our scoring system, nearly half of the F-UTI (-) patients had 0 points, while 94.1% of the patients in the F-UTI (+) group had\u0026thinsp;\u0026ge;\u0026thinsp;10 points (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDistribution of the patients in the groups according to the total score.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGroup 1\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;34)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGroup 2\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;477)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e0 points (n\u0026thinsp;=\u0026thinsp;235)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (5.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e233 (48.8%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10 points (n\u0026thinsp;=\u0026thinsp;38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (5.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36 (7.5%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18 points (n\u0026thinsp;=\u0026thinsp;172)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (26.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e163 (34.2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e28 points (n\u0026thinsp;=\u0026thinsp;52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (35.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e40 (8.4%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e36 points (n\u0026thinsp;=\u0026thinsp;13)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (26.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (0.8%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e46 points (n\u0026thinsp;=\u0026thinsp;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"DISCUSSION","content":"\u003cp\u003eIn the current study, data from two different tertiary centers was collected to develop a scoring system using machine learning algorithms to predict F-UTI in patients undergoing RIRS for upper urinary tract stone disease. Our scoring system is easy to apply for all patients undergoing RIRS because all the parameters included in this study were part of the routine evaluation for patients undergoing stone surgery.\u003c/p\u003e \u003cp\u003eDue to variations in the definition and standardization of infectious complications of RIRS, the incidence of postoperative infectious complications varies in a wide range [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Previous reports indicate that the incidence of postoperative fever after RIRS can reach 17.5% [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Dybowski et al. [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e] found that the mean postoperative fever incidence across 14 studies was 7.1%, which is similar to our rate of 6.6%.\u003c/p\u003e \u003cp\u003ePreoperatively determining the risk factors for infection and identifying patients with a high risk of postoperative F-UTI may influence antibiotic prophylaxis strategies and patient management. In recent years, several studies have aimed to determine the risk factors for infectious complications following RIRS. The most commonly reported risk factors include stone size, operative time, a history of UTI, urinary leukocyte esterase/nitrite, and comorbidities, mainly diabetes mellitus [\u003cspan additionalcitationids=\"CR10 CR11\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan additionalcitationids=\"CR18\" citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. In contrast, in a multicenter study, Berardinelli et al. [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e] found that none of the factors could identify a high-risk patient group for infection. The authors noted that the low complication rate might have limited the results and concluded that, due to this limitation, the risk factors remained unclear. A systematic review of 17 studies reported that long operative time, a history of UTI, urinary pyuria/nitrites, the use of a small-caliber ureteral access sheath, the presence of struvite stones, high irrigation rates, and comorbidities were independent risk factors for infectious complications after RIRS [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Another systematic review by Corrales et al. [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] identified mostly different risk factors for sepsis in RIRS, namely stone size, high irrigation pressure, prolonged stent dwelling time (\u0026gt;\u0026thinsp;30 d), sepsis as an indication for stent insertion, female gender, positive intraoperative bladder urine culture, longer surgical time, and diabetes mellitus. The low complication rate and/or a lack of standardization of infectious complications challenge the identification of definitive risk factors. Thus, it remains unclear which factors reliably predict post-URS infection.\u003c/p\u003e \u003cp\u003eIn the current study, we found that hydronephrosis, a history of post-URS UTI, and urine leukocyte count were significant risk factors for F-UTI. In contrast to our results, several studies [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan additionalcitationids=\"CR10\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] reported that hydronephrosis was not a risk factor for infection after RIRS. Zhao et al. [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] determined that a hydronephrosis level of \u0026le;\u0026thinsp;20 mm was a preoperative risk factor. The authors speculated that in patients with hydronephrosis, an increased intrarenal reflux threshold might reduce the risk of bacterial contamination of the bloodstream. However, studies by Matsumoto et al. [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e] and Sohn et al. [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e] found that a higher degree of hydronephrosis was a risk factor for infectious complications following upper urinary tract procedures, which is consistent with our results. We believe that obstruction of urine flow creates a conducive environment for bacterial growth, and a higher degree of hydronephrosis may be a significant risk factor for infection after RIRS.\u003c/p\u003e \u003cp\u003eAlthough pyuria was identified as another risk factor for F-UTI in our study, there is some debate on this matter in the international literature. Dybowski et al. [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e] found pyuria as one of seven risk factors for infectious complications after RIRS. However, studies by Hao et al. [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] and Qi et al. [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] indicated that urinary leukocyte count was not a risk factor for sepsis and fever, respectively. Our results suggest that although it can be difficult to determine whether all cases of pyuria are due to an infection, pyuria is an important marker of infection and a risk factor for F-UTI.\u003c/p\u003e \u003cp\u003eSeveral studies have found that a history of UTI is a risk factor for postoperative infection following RIRS [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. In contrast, Li et al. [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] reported that a history of UTI was not a risk factor for postoperative fever or systemic inflammatory response syndrome. We believe that the lack of urine culture results can make it difficult to accurately document a history of UTI. In addition, based on our clinical observations, we hypothesized that a history of post-URS UTI might be associated with recurrent post-URS F-UTI. Therefore, we included this parameter in our analysis. The results obtained from the machine learning method supported our clinical observations, indicating that a history of post-URS UTI was an independent risk factor for F-UTI in patients who underwent RIRS. To the best of our knowledge, only one study in the international literature has assessed the history of post-URS infection and found a weak relationship [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eMachine learning methods, a subfield of artificial intelligence in healthcare, allow for more accurate predictions by revealing complex relationships in large databases compared to classical statistical methods [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. In recent years, these applications have been expanding in urological practice and are expected to become more common in decision-making processes [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Studies on machine learning methods in urology have shown promising results [\u003cspan additionalcitationids=\"CR28\" citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Feature selection, a fundamental topic of machine learning, is used extensively in predictive applications. Therefore, we used a feature selection method to identify the relevant predictive factors of post-RIRS F-UTI, rather than relying on classical models.\u003c/p\u003e \u003cp\u003eA retrospective multicenter study by Pietropaolo [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] determined the predictors of post-URS urosepsis using a machine learning model. The authors found that proximal stone location, large stone size, prolonged stent duration, and extended operative time were the parameters with the highest predictive value. In addition, their machine learning model achieved an AUC value of 0.89. In a recent study comparing models generated by classical statistical methods and machine learning algorithms to predict postoperative infection after RIRS, it was found that machine learning models had a higher AUC compared to classical statistical models (0.956 vs. 0.785) [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. The authors concluded that machine learning models were more reliable and predictive compared to traditional models. In the current study, we used machine learning to select the relevant predictive features. Following feature selection, we performed logistic regression analysis to determine significant predictors and create the model. Our model demonstrated a high AUC value (0.837), comparable to previous machine learning models. However, we identified different risk factors, which we believe may be due to our use of feature selection to reduce the number of variables, a method that differed from previous studies.\u003c/p\u003e \u003cp\u003eA few limitations of this study must be noted. The main limitation of our study is its retrospective nature. In addition, some parameters, including stone density and serum C-reactive protein level, were excluded from feature selection due to missing data. We consider that the external validation of our model is necessary to confirm its reliability and power.\u003c/p\u003e"},{"header":"CONCLUSION","content":"\u003cp\u003eThe results of our study demonstrated that hydronephrosis, a history of post-URS UTI, and urine leukocyte count were significant predictive parameters of F-UTI following RIRS. We believe that patients with these risk factors should be closely monitored for postoperative infection to reduce morbidity and mortality. Our results need to be confirmed with further studies.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"Declarations","content":" \u003cp\u003eThe authors have no relevant financial or non-financial interests to disclose.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eCS: Project development, Manuscript writing, Data collection. AE: Data collection. TK: Data management. ICA: Manuscript writing. AYO: Data management. KT: Data management. SB: Data management. SS: Data analysis. OG: Project development, Manuscript writing. AT: Project development, Manuscript editing.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eRaheem OA, Khandwala YS, Sur RL, Ghani KR, Denstedt JD (2017) Burden of Urolithiasis: Trends in Prevalence, Treatments, and Costs. Eur Urol Focus 3:18\u0026ndash;26. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.euf.2017.04.001\u003c/span\u003e\u003cspan address=\"10.1016/j.euf.2017.04.001\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePietropaolo A, Proietti S, Geraghty R, Skolarikos A, Papatsoris A, Liatsikos E, Somani BK (2017) Trends of 'urolithiasis: interventions, simulation, and laser technology' over the last 16 years (2000\u0026ndash;2015) as published in the literature (PubMed): a systematic review from European section of Uro-technology (ESUT). World J Urol 35:1651\u0026ndash;1658. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-017-2055-z\u003c/span\u003e\u003cspan address=\"10.1007/s00345-017-2055-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGrosso AA, Sessa F, Campi R et al (2021) Intraoperative and postoperative surgical complications after ureteroscopy, retrograde intrarenal surgery, and percutaneous nephrolithotomy: a systematic review. Minerva Urol Nephrol 73:309\u0026ndash;332. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.23736/S2724-6051.21.04294-4\u003c/span\u003e\u003cspan address=\"10.23736/S2724-6051.21.04294-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaş O, Tuygun C, Dede O, Sarı S, \u0026Ccedil;akıcı M, \u0026Ouml;zt\u0026uuml;rk U, G\u0026ouml;ktuğ G, İmamoğlu A (2017) Factors affecting complication rates of retrograde flexible ureterorenoscopy: analysis of 1571 procedures-a single-center experience. World J Urol 35:819\u0026ndash;826. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-016-1930-3\u003c/span\u003e\u003cspan address=\"10.1007/s00345-016-1930-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDybowski B, Bres-Niewada E, Rzeszutko M, Tkaczyk A, Woźniak B, W\u0026oacute;jcik M, Znajdek Z (2021) Risk factors for infectious complications after retrograde intrarenal surgery - a systematic review and narrative synthesis. Cent Eur J Urol 74:437\u0026ndash;445. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5173/ceju.2021.250\u003c/span\u003e\u003cspan address=\"10.5173/ceju.2021.250\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCorrales M, Sierra A, Doizi S, Traxer O (2022) Risk of Sepsis in Retrograde Intrarenal Surgery: A Systematic Review of the Literature. Eur Urol Open Sci 44:84\u0026ndash;91. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.euros.2022.08.008\u003c/span\u003e\u003cspan address=\"10.1016/j.euros.2022.08.008\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eParkhomenko E, De Fazio A, Tran T, Thai J, Blum K, Gupta M (2017) A Multi-Institutional Study of Struvite Stones: Patterns of Infection and Colonization. J Endourol 31:533\u0026ndash;537. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1089/end.2016.0885\u003c/span\u003e\u003cspan address=\"10.1089/end.2016.0885\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBerardinelli F, De Francesco P, Marchioni M et al (2016) Infective complications after retrograde intrarenal surgery: a new standardized classification system. Int Urol Nephrol 48:1757\u0026ndash;1762. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11255-016-1373-1\u003c/span\u003e\u003cspan address=\"10.1007/s11255-016-1373-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi T, Sun XZ, Lai DH, Li X, He YZ (2018) Fever and systemic inflammatory response syndrome after retrograde intrarenal surgery: Risk factors and predictive model. Kaohsiung J Med Sci 34:400\u0026ndash;408. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.kjms.2018.01.002\u003c/span\u003e\u003cspan address=\"10.1016/j.kjms.2018.01.002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXuan Z, Yu Z, Tan G, Ding N, He H, Yu S, Liu G, Zhu X, Zhu B, Liu Z (2022) Development and validation of a novel nomogram for predicting systemic inflammatory response syndrome's occurrence in patients undertaking flexible ureteroscopy. Transl Androl Urol 11:228\u0026ndash;237. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21037/tau-22-34\u003c/span\u003e\u003cspan address=\"10.21037/tau-22-34\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHao X, Wang X, Ding H, Zheng S, Li Z, Yin H, Wang L, Luo J, Wei H (2022) A model for sepsis prediction after retrograde intrarenal surgery and the use of the preoperative/postoperative white blood cell ratio to predict progression from sepsis to septic shock. World J Urol 40:2979\u0026ndash;2990. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-022-04182-1\u003c/span\u003e\u003cspan address=\"10.1007/s00345-022-04182-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQi Q, Hu Y, Chen Y, Yan Q, Xu Y, Liang H, Liang C, Hao Z (2023) Nomogram for predicting risk factors of fever in patients with negative preoperative urine culture after retrograde intrarenal surgery. World J Urol 41:783\u0026ndash;789. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-023-04302-5\u003c/span\u003e\u003cspan address=\"10.1007/s00345-023-04302-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSenel C, Tuncel A, Balci M, Asfuroglu A, Aykanat C, Guzel O, Aslan Y (2018) Safety and reliability of fluoroscopy-free technique in retrograde intrarenal surgery. Minerva Urol Nefrol 70:606\u0026ndash;611. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.23736/S0393-2249.18.03228-9\u003c/span\u003e\u003cspan address=\"10.23736/S0393-2249.18.03228-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDeng T, Liu B, Duan X, Cai C, Zhao Z, Zhu W, Fan J, Wu W, Zeng G (2018) Antibiotic prophylaxis in ureteroscopic lithotripsy: a systematic review and meta-analysis of comparative studies. BJU Int 122:29\u0026ndash;39. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/bju.14101\u003c/span\u003e\u003cspan address=\"10.1111/bju.14101\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDevi MI, Rajaram R, Selvakuberan K (2008) Generating best features for web page classification. Webology 5:52\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAli A, Jillani F, Zaheer R, Karim A, Alharbi YO, Alsaffar M, Alhamazani K (2022) Practically implementation of information loss: sensitivity, risk by different feature selection techniques. IEEE Access 10:27643\u0026ndash;27654\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaboudjian M, Gondran-Tellier B, Abdallah R, Sichez PC, Akiki A, Gaillet S, Delaporte V, Karsenty G, Lechevallier E, Boissier R (2020) Predictive risk factors of urinary tract infection following flexible ureteroscopy despite preoperative precautions to avoid infectious complications. World J Urol 38:1253\u0026ndash;1259. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-019-02891-8\u003c/span\u003e\u003cspan address=\"10.1007/s00345-019-02891-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang H, Jiang T, Gao R, Chen Q, Chen W, Liu C, Mao H (2020) Risk factors of infectious complications after retrograde intrarenal surgery: a retrospective clinical analysis. J Int Med Res 48:300060520956833. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/0300060520956833\u003c/span\u003e\u003cspan address=\"10.1177/0300060520956833\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang M, Li Y, Huang F (2023) A nomogram for predicting postoperative urosepsis following retrograde intrarenal surgery in upper urinary calculi patients with negative preoperative urine culture. Sci Rep 13:2123. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41598-023-29352-y\u003c/span\u003e\u003cspan address=\"10.1038/s41598-023-29352-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao Z, Sun H, Zhu W, Liu Y, Zhong W, Liu Y, Zeng G (2023) A new model to assist decision-making of optimal antibiotics duration for treating asymptomatic bacteriuria or pyuria prior to retrograde intrarenal surgery. Minerva Urol Nephrol 75:486\u0026ndash;492. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.23736/S2724-6051.21.04454-2\u003c/span\u003e\u003cspan address=\"10.23736/S2724-6051.21.04454-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMatsumoto M, Shigemura K, Yamamichi F, Tanaka K, Nakano Y, Arakawa S, Fujisawa M (2012) Prevention of infectious complication and its risk factors after urological procedures of the upper urinary tract. Urol Int 88:43\u0026ndash;47. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1159/000332224\u003c/span\u003e\u003cspan address=\"10.1159/000332224\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSohn DW, Kim SW, Hong CG, Yoon BI, Ha US, Cho YH (2013) Risk factors of infectious complication after ureteroscopic procedures of the upper urinary tract. J Infect Chemother 19:1102\u0026ndash;1108. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10156-013-0632-7\u003c/span\u003e\u003cspan address=\"10.1007/s10156-013-0632-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaseskioglu B (2019) The Prevalence of Urinary Tract Infection Following Flexible Ureterenoscopy and the Associated Risk Factors. Urol J 16:439\u0026ndash;442. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.22037/uj.v0i0.4340\u003c/span\u003e\u003cspan address=\"10.22037/uj.v0i0.4340\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePietropaolo A, Geraghty RM, Veeratterapillay R et al (2021) A Machine Learning Predictive Model for Post-Ureteroscopy Urosepsis Needing Intensive Care Unit Admission: A Case-Control YAU Endourology Study from Nine European Centres. J Clin Med 10:3888. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/jcm10173888\u003c/span\u003e\u003cspan address=\"10.3390/jcm10173888\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCheccucci E, Autorino R, Cacciamani GE et al (2020) Artificial intelligence and neural networks in urology: current clinical applications. Minerva Urol Nefrol 72:49\u0026ndash;57. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.23736/S0393-2249.19.03613-0\u003c/span\u003e\u003cspan address=\"10.23736/S0393-2249.19.03613-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShah M, Naik N, Somani BK, Hameed BMZ (2020) Artificial intelligence (AI) in urology-Current use and future directions: An iTRUE study. Turk J Urol 46(1):S27\u0026ndash;S39. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5152/tud.2020.20117\u003c/span\u003e\u003cspan address=\"10.5152/tud.2020.20117\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBlum ES, Porras AR, Biggs E, Tabrizi PR, Sussman RD, Sprague BM, Shalaby-Rana E, Majd M, Pohl HG, Linguraru MG (2018) Early Detection of Ureteropelvic Junction Obstruction Using Signal Analysis and Machine Learning: A Dynamic Solution to a Dynamic Problem. J Urol 199:847\u0026ndash;852. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.juro.2017.09.147\u003c/span\u003e\u003cspan address=\"10.1016/j.juro.2017.09.147\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAminsharifi A, Irani D, Tayebi S, Jafari Kafash T, Shabanian T, Parsaei H (2020) Predicting the Postoperative Outcome of Percutaneous Nephrolithotomy with Machine Learning System: Software Validation and Comparative Analysis with Guy's Stone Score and the CROES Nomogram. J Endourol 34:692\u0026ndash;699. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1089/end.2019.0475\u003c/span\u003e\u003cspan address=\"10.1089/end.2019.0475\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAltıntaş E, Şahin A, Babayev H, G\u0026uuml;l M, Batur AF, Kaynar M, Kılı\u0026ccedil; \u0026Ouml;, G\u0026ouml;ktaş S (2024) Machine learning algorithm predicts urethral stricture following transurethral prostate resection. World J Urol 42:324. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-024-05017-x\u003c/span\u003e\u003cspan address=\"10.1007/s00345-024-05017-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEkşi M, Fakir AE, Evren İ, Şam E, Arıkan Y, Kargı T, Hacıislamoğlu A, Yavuzsan AH, Şahin S, Taş\u0026ccedil;ı A (2023) Prediction of infective complications after retrograde intra renal surgery using Machine learning. Minim Invasive Ther Allied Technol 32:73\u0026ndash;80. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/13645706.2023.2186181\u003c/span\u003e\u003cspan address=\"10.1080/13645706.2023.2186181\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"urolithiasis","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ures","sideBox":"Learn more about [Urolithiasis](http://link.springer.com/journal/240)","snPcode":"240","submissionUrl":"https://submission.nature.com/new-submission/240/3","title":"Urolithiasis","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5349729/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5349729/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Purpose: To determine the risk factors and define a new scoring system for predicting febrile urinary tract infection (F-UTI) following retrograde intrarenal surgery (RIRS) by using machine learning methods.\nMethods: We retrospectively analyzed the medical records of patients who underwent RIRS and 511 patients were included in the study. The patients were divided into two groups: Group 1 consisted of 34 patients who developed postoperative F-UTI, and Group 2 consisted of 477 patients who did not. We applied feature selection to determine the relevant variables. Consistency subset evaluator and greedy stepwise techniques were used for attribute selection. Logistic regression analysis was conducted on the variables obtained through feature selection to develop our scoring system. The accuracy of discrimination was assessed using the receiver operating characteristic curve.\nResults: Five of the 19 variables, namely diabetes mellitus, hydronephrosis, administration type, a history of post-ureterorenoscopy (URS) UTI, and urine leukocyte count, were identified through feature selection. Binary logistic regression analysis showed that hydronephrosis, a history of post-URS UTI, and urine leukocyte count were significant independent predictors of F-UTI following RIRS. These three factors demonstrated good discrimination ability, with an area under curve value of 0.837. In the presence of at least one of these factors, 32 of 34 patients who developed postoperative F-UTI were successfully predicted. \n \nConclusion: This new scoring system developed based on hydronephrosis, a history of post-URS UTI, and urine leukocyte count can successfully discriminate patients at risk of F-UTI development after RIRS.\n ","manuscriptTitle":"A New Scoring System to Predict Febrile Urinary Tract Infection After Retrograde Intrarenal Surgery","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-20 10:52:31","doi":"10.21203/rs.3.rs-5349729/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-30T14:53:42+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-10-29T17:47:10+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-10-29T17:45:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Urolithiasis","date":"2024-10-28T21:10:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"urolithiasis","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ures","sideBox":"Learn more about [Urolithiasis](http://link.springer.com/journal/240)","snPcode":"240","submissionUrl":"https://submission.nature.com/new-submission/240/3","title":"Urolithiasis","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"429a932b-6f8b-4f92-8b48-4ff149bc0d43","owner":[],"postedDate":"November 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-30T15:58:32+00:00","versionOfRecord":{"articleIdentity":"rs-5349729","link":"https://doi.org/10.1007/s00240-024-01685-x","journal":{"identity":"urolithiasis","isVorOnly":false,"title":"Urolithiasis"},"publishedOn":"2024-12-24 15:56:56","publishedOnDateReadable":"December 24th, 2024"},"versionCreatedAt":"2024-11-20 10:52:31","video":"","vorDoi":"10.1007/s00240-024-01685-x","vorDoiUrl":"https://doi.org/10.1007/s00240-024-01685-x","workflowStages":[]},"version":"v1","identity":"rs-5349729","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5349729","identity":"rs-5349729","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}