A Machine Learning Predictive Model for Post-Ureteroscopy Urosepsis Needing Intensive Care Unit Admission: A Case-Control YAU Endourology Study from Nine European Centres

A new scoring system to predict febrile urinary tract infection after retrograde intrarenal surgery

The current study aimed 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. 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. 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 (94.1%) who developed postoperative F-UTI were successfully predicted. 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.

High-power versus low-power laser settings during endoscopic stone disease management: a systematic review from the EAU endourology section

PURPOSE

Optimal laser settings during endoscopic stone disease management still represents a debatable issue. The aim of this systematic review is to summarize all existing evidence regarding the comparison of high-power (HP) versus low-power (LP) laser settings during different endoscopic lithotripsy procedures.

METHODS

PubMed, Scopus and Cochrane databases were systematically screened, based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) Guidelines. All endoscopic laser lithotripsy surgical approaches were included, including ureteroscopy (URS), retrograde intrarenal surgery (RIRS), percutaneous nephrolithotomy (PCNL) and transurethral lithotripsy for bladder stones. Pediatric patients were also included.

RESULTS

In total, 10 studies met the inclusion criteria and were included in final qualitative synthesis. In most studies total operative time (OT) was shorter for the HP group. Mean fragmentation time was homogenously significantly shorter in the HP group. Stone-free rates (SFR) ranged from 59.0% to 100% for the LP group and from 78.9% to 100% for the HP group. Total complication rates were higher for the LP group in six studies, equivalent between the two groups in one study and higher in the HP group in one study.

CONCLUSION

HP laser lithotripsy is a safe and efficient approach for URS, RIRS, PCNL and cystolithotripsy. HP laser settings were associated with significantly shorter total operative time, while some studies reported also better SFR in the HP groups. The implementation of more Randomized Controlled Trials comparing HP and LP laser lithotripsy in different stone settings is of outmost importance, so that better conclusions can be drawn.

Efficacy analysis of tip-flexible suction access sheath during flexible ureteroscopic lithotripsy for unilateral upper urinary tract calculi

PURPOSE

This study aims to evaluate the efficacy of tip-flexible suctioning ureteral access sheath (TFS-UAS) compared to traditional ureteral access sheath (T-UAS) in flexible ureteroscopic lithotripsy (FURL) for unilateral upper urinary tract calculi.

METHODS

The study retrospectively compared outcomes from 103 cases using TFS-UAS and 138 using T-UAS treated with FURL for unilateral upper urinary tract calculi from January to October 2023. Assessed parameters included patient demographics, stone characteristics, preoperative urine cultures, ureteral pre-stenting, comorbidities, procedure time, stone-free rate (SFR), utilization of stone retrieval baskets, and postoperative Systemic Inflammatory Response Syndrome (SIRS) rates. The maximum angle of deflection was also measured when the flexible ureteroscope was located in different parts of the TFS-UAS with different diameters in vitro.

RESULTS

The TFS-UAS group achieved a higher Immediate SFR (76.70% vs. 63.77%, p = 0.031) and final SFR (89.32% vs. 73.91%, p = 0.003) than the T-UAS group, especially in the lower calyx stones (80.00% vs. 41.18%, p = 0.018) and upper urinary tract calculi with a cumulative diameter of 2 cm or larger (68.97% vs. 42.11%, p = 0.029). Notably, TFS-UAS with a 10 French (F) inside diameter size achieved a higher SFR (88.57% vs. 70.59%, p = 0.041) and a greater deflection angle than the 12.5 F inside diameter size. No significant variations were observed in the operative duration, hospitalization duration and the occurrence of SIRS between the compared cohorts.

CONCLUSION

TFS-UAS significantly improves SFR in FURL treatment of unilateral upper urinary tract calculi, particularly for stones located in the lower calyx or with a cumulative diameter of 2 cm or greater, compared to T-UAS.

The infection post flexible UreteroreNoscopy (I-FUN) predictive model based on machine learning: a new clinical tool to assess the risk of sepsis post retrograde intrarenal surgery for kidney stone disease

PURPOSE

To create a machine-learning model for estimating the likelihood of post-retrograde intrarenal surgery (RIRS) sepsis.

METHODS

All consecutive patients with kidney stone(s) only undergoing RIRS in 16 centers were prospectively included (January 2022-August 2023).

INCLUSION CRITERIA

adult, renal stone(s) only, CT scan (within three months), mid-stream urine culture (within 10 days).

EXCLUSION CRITERIA

concomitant ureteral stone, bilateral procedures. In case of symptomatic infection/asymptomatic bacteriuria, patients were given six days of antibiotics according to susceptibility profiles. All patients had antibiotics prophylaxis. Variables selected for the model: age, gender, age-adjusted Charlson Comorbidity Index, stone volume, indwelling preoperative bladder catheter, urine culture, single/multiple stones, indwelling preoperative stent/nephrostomy, ureteric access sheath, surgical time. Analysis was conducted using Python programming language, with Pandas library and machine learning models implemented using the Scikit-learn library. Machine learning algorithms tested: Decision Tree, Random Forest, Gradient Boosting. Overall performance was accurately estimated by K-Fold cross-validation with three folds.

RESULTS

1552 patients were included. There were 20 (1.3%) sepsis cases, 16 (1.0%) septic shock cases, and three more cases (0.2%) of sepsis-related deaths. Random Forest model showed the best performance (precision = 1.00; recall = 0.86; F1 score = 0.92; accuracy = 0.92). A web-based interface of the predictive model was built and is available at https://emabal.pythonanywhere.com/ CONCLUSIONS: Our model can predict post-RIRS sepsis with high accuracy and might facilitate patient selection for day-surgery procedures and identify patients at higher risk of sepsis who deserve extreme attention for prompt identification and treatment.

Clinical significance of stone culture during endourological procedures in predicting post-operative urinary sepsis: should it be a standard of care-evidence from a systematic review and meta-analysis from EAU section of Urolithiasis (EULIS)

PURPOSE

Urinary sepsis is the leading cause of mortality in the setting of endourological procedures for stone treatment such as URS and PCNL; renal stones themselves may be a source of infection. Aim of this study is to determine the diagnostic accuracy of stone cultures (SC) collected during URS and PCNL in predicting post-operative septic complications, compared to preoperative bladder urine culture (BUC).

METHODS

We performed a systematic review (SR) of literature according to the PRISMA guidelines; Literature quality was evaluated according to The Risk Of Bias In Non-randomized Studies-of Interventions (ROBINS-I) assessment tool. A univariate meta-analysis (MA) was used to estimate pooled log odds ratio of BUC and SC, respectively.

RESULTS

Overall, 14 studies including 3646 patients met the inclusion criteria. Eight studies reported data from PCNL only; three from URS only; three from both URS and PCNL. Stone cultures showed a higher sensitivity (0.52 vs 0.32) and higher positive predictive value (0.28 vs 0.21) in predicting post-operative sepsis, compared to bladder urine cultures. The pool-weighted logarithmic odd risk (LOR) for BUC was 2.30 (95% CI 1.51-3.49, p < 0.001); the LOR for stone cultures (SC) in predicting post-operative sepsis was 5.79 (95% CI 3.58-9.38, p < 0.001).

CONCLUSION

The evidence from this SR and MA suggests that intraoperative SC from stone fragments retrieved during endourological procedures are better predictors of the likelihood of occurrence of post-operative sepsis compared to pre-operative BUC. Therefore, SC should be a standard of care in patients undergoing endourological interventions.

A Machine Learning Predictive Model for Ureteroscopy Lasertripsy Outcomes in a Pediatric Population-Results from a Large Endourology Tertiary Center

Introduction: We aimed to develop machine learning (ML) algorithms for the automated prediction of postoperative ureteroscopy outcomes for pediatric kidney stones based on preoperative characteristics. Materials and Methods: Data from pediatric patients who underwent ureteroscopy for stone treatment by a single experienced surgeon, between 2010 and 2023 in Southampton General Hospital, were retrospectively collected. Fifteen ML classification algorithms were used to investigate correlations between preoperative characteristics and postoperative outcomes: primary stone-free status (SFS, defined as stone fragments <2 mm at the end of the procedure confirmed endoscopically and no evidence of stone fragments >2 mm at Xray kidney-ureters-bladder (XR KUB) or ultrasound kidney-ureters-bladder (US KUB) at 3 months follow-up) and complications. For the task of complication and stone status, an ensemble model was made out of Bagging classifier, Extra Trees classifier, and linear discriminant analysis. Also, a multitask neural network was constructed for the simultaneous prediction of all postoperative characteristics. Finally, explainable artificial intelligence techniques were used to explain the prediction made by the best models. Results: The ensemble model produced the highest accuracy (90%) in predicting SFS, finding correlation with overall stone size (-0.205), presence of multiple stones (-0.127), and preoperative stenting (-0.102). Complications were predicted by Synthetic Minority Oversampling Technique (SMOTE) oversampled dataset (93.3% accuracy) with relation to preoperative positive urine culture (-0.060) a1nd SFS (0.003). Training ML for the multitask model, accuracies of 83.3% and 80% were respectively reached. Conclusion: ML has a great potential of assisting health care research, with possibilities to investigate dataset at a higher level. With the aid of this intelligent tool, urologists can implement their practice and develop new strategies for outcome prediction and patient counseling and informed shared decision-making. Our model reached an excellent accuracy in predicting SFS and complications in the pediatric population, leading the way to the validation of patient-specific predictive tools.

Urosepsis after ureterorenoscopy, intraoperative recognition of type-IV stones could change clinical practice

OBJECTIVES

Urosepsis currently accounts for half of all post flexible ureterorenoscopy (F-URS) complications, with an incidence of up to 4.3%. It represents a quarter of all septic episodes in adults and 2% of hospital spendings. The primary objective of this study was to define the predictive clinical parameters that increase the risk of urosepsis after F-URS.

SUBJECTS/PATIENTS (OR MATERIALS) AND METHODS

This prospective multicentric study evaluated patients who underwent F-URS for calculus between June 2016 and June 2018 in eleven French centers. Clinical, bacteriological, morpho-constitutional stone data, intraoperative information and complications were compared. Risk factors for postoperative urosepsis were identified and analyzed.

RESULTS

We included 486 F-URS in 432 patients. The ureter was prepared using a double J stent in 51% of cases, a digital endoscope was used in 56% of patients with a median operative time of 120 min IQR (90-125) and using a sheath in 90% of cases. Postoperative urosepsis was observed in 18 patients (4%) with a median time to onset of 2 days IQR (1-5). The presence of coronary insufficiency: 3 (17%) vs 14 (3%) p = 0.005, a larger stone diameter: 11 cm [9-17] vs 10 cm [8-13] p = 0.02, a positive preoperative urine culture even when treated: 3 (17%) vs 56 (12%) p = 0.04, as well as the final composition of the type IV calculus (carbapatite or struvite) 5 (28%) vs 20 (4%) p < 0.001, were significantly associated with the occurrence of urosepsis. In multivariate analysis, only the presence of a type IV stone (OR = 14.0; p = 0.025) remained significant.

CONCLUSION

Ureteroscopic treatment of a type IV stone (carbapatite or struvite) in a patient should raise concerns about the risk of post-operative urosepsis. When recognized intraoperatively, they should lead to a pyelic urinary sample and prolonged clinical surveillance.

Trends of "Artificial Intelligence, Machine Learning, Virtual Reality, and Radiomics in Urolithiasis" over the Last 30 Years (1994-2023) as Published in the Literature (PubMed): A Comprehensive Review

Purpose: To analyze the bibliometric publication trend on the application of "Artificial Intelligence (AI) and its subsets (Machine Learning-ML, Virtual reality-VR, Radiomics) in Urolithiasis" over 3 decades. We looked at the publication trends associated with AI and stone disease, including both clinical and surgical applications, and training in endourology. Methods: Through a MeshTerms research on PubMed, we performed a comprehensive review from 1994-2023 for all published articles on "AI, ML, VR, and Radiomics." Articles were then divided into three categories as follows: A-Clinical (Nonsurgical), B-Clinical (Surgical), and C-Training articles, and articles were then assigned to following three periods: Period-1 (1994-2003), Period-2 (2004-2013), and Period-3 (2014-2023). Results: A total of 343 articles were noted (Groups A-129, B-163, and C-51), and trends increased from Period-1 to Period-2 at 123% (p = 0.009) and to period-3 at 453% (p = 0.003). This increase from Period-2 to Period-3 for groups A, B, and C was 476% (p = 0.019), 616% (0.001), and 185% (p < 0.001), respectively. Group A articles included rise in articles on "stone characteristics" (+2100%; p = 0.011), "renal function" (p = 0.002), "stone diagnosis" (+192%), "prediction of stone passage" (+400%), and "quality of life" (+1000%). Group B articles included rise in articles on "URS" (+2650%, p = 0.008), "PCNL"(+600%, p = 0.001), and "SWL" (+650%, p = 0.018). Articles on "Targeting" (+453%, p < 0.001), "Outcomes" (+850%, p = 0.013), and "Technological Innovation" (p = 0.0311) had rising trends. Group C articles included rise in articles on "PCNL" (+300%, p = 0.039) and "URS" (+188%, p = 0.003). Conclusion: Publications on AI and its subset areas for urolithiasis have seen an exponential increase over the last decade, with an increase in surgical and nonsurgical clinical areas, as well as in training. Future AI related growth in the field of endourology and urolithiasis is likely to improve training, patient centered decision-making, and clinical outcomes.

Can Machine Learning Correctly Predict Outcomes of Flexible Ureteroscopy with Laser Lithotripsy for Kidney Stone Disease? Results from a Large Endourology University Centre

Background and objective

The integration of machine learning (ML) in health care has garnered significant attention because of its unprecedented opportunities to enhance patient care and outcomes. In this study, we trained ML algorithms for automated prediction of outcomes of ureteroscopic laser lithotripsy (URSL) on the basis of preoperative characteristics.

Methods

Data were retrieved for patients treated with ureteroscopy for urolithiasis by a single experienced surgeon over a 7-yr period. Sixteen ML classification algorithms were trained to investigate correlation between preoperative characteristics and postoperative outcomes. The outcomes assessed were primary stone-free status (SFS, defined as the presence of only stone fragments <2 mm on endoscopic visualisation and at 3-mo imaging) and postoperative complications. An ensemble model was constructed from the best-performing algorithms for prediction of complications and for prediction of SFS. Simultaneous prediction of postoperative characteristics was then investigated using a multitask neural network, and explainable artificial intelligence (AI) was used to demonstrate the predictive power of the best models.

Key findings and limitations

An ensemble ML model achieved accuracy of 93% and precision of 87% for prediction of SFS. Complications were mainly associated with a preoperative positive urine culture (1.44). Logistic regression revealed that SFS was impacted by the total stone burden (0.34), the presence of a preoperative stent (0.106), a positive preoperative urine culture (0.14), and stone location (0.09). Explainable AI results emphasised the key features and their contributions to the output.

Conclusions and clinical implications

Technological advances are helping urologists to overcome the classic limits of ureteroscopy, namely stone size and the risk of complications. ML represents an excellent aid for correct prediction of outcomes after training on pre-existing data sets. Our ML model achieved accuracy of >90% for prediction of SFS and complications, and represents a basis for the development of an accessible predictive model for endourologists and patients in the URSL setting.

Patient summary

We tested the ability of artificial intelligence to predict treatment outcomes for patients with kidney stones. We trained 16 different machine learning tools with data before surgery, such as patient age and the stone characteristics. Our final model was >90% accurate in predicting stone-free status after surgery and the occurrence of complications.

Application of AI in urolithiasis risk of infection: a scoping review

INTRODUCTION

Artificial intelligence and machine learning are the new frontier in urology; they can assist the diagnostic work-up and in prognostication bring superior to the existing nomograms. Infectious events and in particular the septic risk, are one of the most common and in some cases life threatening complication in patients with urolithiasis. We performed a scoping review to provide an overview of the current application of AI in prediction the infectious complications in patients affected by urolithiasis.

EVIDENCE ACQUISITION

A systematic scoping review of the literature was performed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses for Scoping Reviews (PRISMA-ScR) guidelines by screening Medline, PubMed, and Embase to detect pertinent studies.

EVIDENCE SYNTHESIS

A total of 467 articles were found, of which nine met the inclusion criteria and were considered. All studies are retrospective and published between 2021 and 2023. Only two studies performed an external validation of the described models. The main event considered is urosepsis in four articles, urinary tract infection in two articles and diagnosis of infection stones in three articles. Different AI models were trained, each of which exploited several types and numbers of variables. All studies reveal good performance. Random forest and artificial neural networks seem to have higher AUC, specificity and sensibility and perform better than the traditional statistical analysis.

CONCLUSIONS

Further prospective and multi-institutional studies with external validation are needed to better clarify which variables and AI models should be integrated in our clinical practice to predict infectious events.

Diagnostic performance of machine learning in systemic infection following percutaneous nephrolithotomy and identification of associated risk factors

Objective

This study aims to investigate the predictive performance of machine learning in predicting the occurrence of systemic inflammatory response syndrome (SIRS) and urosepsis after percutaneous nephrolithotomy (PCNL).

Methods

A retrospective analysis was conducted on patients who underwent PCNL treatment between January 2016 and July 2022. Machine learning techniques were employed to establish and select the best predictive model for postoperative systemic infection. The feasibility of using relevant risk factors as predictive markers was explored through interpretability with Machine Learning.

Results

A total of 1067 PCNL patients were included in this study, with 111 (10.4 %) patients developing SIRS and 49 (4.5 %) patients developing urosepsis. In the validation set, the risk model based on the GBM protocol demonstrated a predictive power of 0.871 for SIRS and 0.854 for urosepsis. Preoperative and postoperative platelet changes were identified as the most significant predictors. Both thrombocytopenia and thrombocytosis were found to be risk factors for SIRS or urosepsis after PCNL. Furthermore, it was observed that when the change in platelet count before and after PCNL surgery exceeded 30*109/L (whether an increase or decrease), the risk of developing SIRS or urosepsis significantly increased.

Conclusion

Machine learning can be effectively utilized for predicting the occurrence of SIRS or urosepsis after PCNL. The changes in platelet count before and after PCNL surgery serve as important predictors.

A machine learning approach using stone volume to predict stone-free status at ureteroscopy

INTRODUCTION

To develop a predictive model incorporating stone volume along with other clinical and radiological factors to predict stone-free (SF) status at ureteroscopy (URS).

MATERIAL AND METHODS

Retrospective analysis of patients undergoing URS for kidney stone disease at our institution from 2012 to 2021. SF status was defined as stone fragments < 2 mm at the end of the procedure confirmed endoscopically and no evidence of stone fragments > 2 mm at XR KUB or US KUB at 3 months follow up. We specifically included all non-SF patients to optimise our algorithm for identifying instances with residual stone burden. SF patients were also randomly sampled over the same time period to ensure a more balanced dataset for ML prediction. Stone volumes were measured using preprocedural CT and combined with 19 other clinical and radiological factors. A bagged trees machine learning model with cross-validation was used for this analysis.

RESULTS

330 patients were included (SF: n = 276, not SF: n = 54, mean age 59.5 ± 16.1 years). A fivefold cross validated RUSboosted trees model has an accuracy of 74.5% and AUC of 0.82. The model sensitivity and specificity were 75% and 72.2% respectively. Variable importance analysis identified total stone volume (17.7% of total importance), operation time (14.3%), age (12.9%) and stone composition (10.9%) as important factors in predicting non-SF patients. Single and cumulative stone size which are commonly used in current practice to guide management, only represented 9.4% and 4.7% of total importance, respectively.

CONCLUSION

Machine learning can be used to predict patients that will be SF at the time of URS. Total stone volume appears to be more important than stone size in predicting SF status. Our findings could be used to optimise patient counselling and highlight an increasing role of stone volume to guide endourological practice and future guidelines.

Harnessing Artificial Intelligence for Enhanced Renal Analysis: Automated Detection of Hydronephrosis and Precise Kidney Segmentation

Background and objective

Hydronephrosis is essential in the diagnosis of renal colic. We automated the detection of hydronephrosis from ultrasound images to standardize the therapy and reduce the misdiagnosis of renal colic.

Methods

Anonymously collected ultrasound images of human kidneys, both normal and hydronephrotic, were preprocessed for neural networks. Six "state of the art" models were trained and cross-validated for the detection of hydronephrosis, and two convolutional networks were used for kidney segmentation. In the testing phase, performance metrics included true positives, true negatives, false positives, false negatives, accuracy, and F1 score, while the evaluation of the segmentation task involved accuracy, precision, dice, jaccard, recall, and ASSD.

Key findings and limitations

A total of 523 sonographic kidney images (423 nonhydronephrotic and 100 hydronephrotic) were collected from three different ultrasound devices. After training on this dataset, all models were used to evaluate 200 new ultrasound kidney images (142 nonhydronephrotic and 58 hydronephrotic kidneys). The highest validation accuracy (98.5%) was achieved by the AlexNet model (GoogLeNet 97%, AlexNet_v2 96%, ResNet50 96%, ResNet101 97.5%, and ResNet152 95%). The deeplabv3_resnet50 and deeplabv3_resnet101 reached a dice coefficient of 94.74% and 94.48%, respectively, on the task of automated kidney segmentation. The study is limited by analyzing only hydronephrosis, but this specific focus enabled high detection accuracy.

Conclusions and clinical implications

We show that our automated ultrasound deep learning model can be trained and used to interpret and segmentate ultrasound images from different sources with high accuracy. This method will serve as an automated tool in the diagnostic algorithm of acute renal failure in the future.

Patient summary

Hydronephrosis is crucial in the diagnosis of renal colic. Recent advances in artificial intelligence allow automated detection of hydronephrosis in ultrasound images with high accuracy. These methods will help standardize the diagnosis and treatment renal colic.

Multicentric evaluation of high and low power lasers on RIRS success using propensity score analysis

In this study, we aimed to evaluate the effect of HPL on different parameters by different centers and urologists. While doing this, we evaluated different parameters by comparing HPL(High Power laser) and LPL(Low-power laser). This is an observational, retrospective, comparative, multicentric study of prospectively organised database. A total of 217 patients who underwent RIRS for kidney stones smaller than 2 cm in three different centers were included in the study. The patients were divided into two groups; LPL used (Group1, n:121 patients) and HPL used (Group2, n:96). Propensity score matching was done in the data analysis part. After matching, a total of 192 patients, 96 patients in both groups, were evaluated. There was no difference between the groups regarding age, gender, stone side, and stone location. The stone-free rate on the first day was 80.3% in Group 1, it was 78.1% in Group 2 (p = 0.9). In the third month, it was 90.7% in Group 1 and 87.5% in Group 2 (p:0.7).Hospitalization duration was significantly higher in Group 1. (2.35 ± 2.27 days vs. 1.42 ± 1.10 days; p < 0.001).The operation duration was 88.70 ± 29.72 min in Group1 and 66.17 ± 41.02 min in Group2 (p < 0.001). The fluoroscopy time (FT) was 90.73 ± 4.79 s in Group 1 and 50.78 ± 5.64 s in Group 2 (p < 0.001). Complications according to Clavien Classification, were similar between the groups(p > 0.05). According to our study similar SFR and complication rates were found with HPL and LPL. In addition, patients who used HPL had lower operation time, hospital stay, and fluoroscopy time than the LPL group. Although high-power lasers are expensive in terms of cost, they affect many parameters and strengthen the hand of urologists thanks to the wide energy and frequency range they offer.

Design and internal validation of S.I.C.K.: a novel nomogram predicting infectious and hemorrhagic events after percutaneous nephrolithotomy

BACKGROUND

Hemorrhagic and infectious events represent severe complications after percutaneous nephrolithotomy (PCNLs). Existing nephrolithometric nomograms have been introduced but their reliability in predicting complications is debated. We present a newly designed nomogram with intention to predict hemorrhagic/infectious events after PCNLs.

METHODS

We conducted a multicentric prospective study on adult patients undergoing standard (24 Fr) or mini (18 Fr) PCNL. Dataset was derived from previous RCT, where patients have been assigned to mini-PCNL or standard-PCNL to treat renal stones up to 40 mm. Aim of the study was to identify preoperative risk factors for early postoperative infectious/hemorrhagic complications including fever, septic shock, transfusion or angioembolization.

RESULTS

A total of 1980 patients were finally included. 992 patients (50.1%) received mini-PCNL and 848 standard PCNL (49.9%). The overall SFR was 86.1% with a mean maximum stone diameter of 29 mm (SD 25.0-35.0). 178 patients (8.9%) had fever,14 (0.7%) urosepsis, 24 patients (1.2%) required transfusion and 18 (0.9%) angioembolization. The overall complication was (11.7%). After multivariable analysis, the included elements in the nomogram were age (P=0.041), BMI (P=0.018), maximum stone diameter (P<0.001), preoperative hemoglobin (P=0.005), type 1/2 diabetes (P=0.05), eGFR<30 (P=0.0032), hypertension (>135/85 mmHg, P=0.001), previous PCNL or pyelo/nephrolithotomy (P=0.0018), severe hydronephrosis (P=0.002). After internal validation, the AUC of the model was 0.73.

CONCLUSIONS

This is the first nomogram predicting infections and bleedings after PCNLs, it shows a good accuracy and can support clinicians in their patients' peri-operative workout and management.

Use of artificial intelligence for sepsis risk prediction after flexible ureteroscopy: a systematic review

INTRODUCTION

flexible ureteroscopy is a minimally invasive surgical technique used for the treatment of renal lithiasis. Postoperative urosepsis is a rare but potentially fatal complication. Traditional models used to predict the risk of this condition have limited accuracy, while models based on artificial intelligence are more promising. The objective of this study is to carry out a systematic review regarding the use of artificial intelligence to detect the risk of sepsis in patients with renal lithiasis undergoing flexible ureteroscopy.

METHODS

the literature review is in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA). The keyword search was performed in MEDLINE, Embase, Web of Science and Scopus and resulted in a total of 2,496 articles, of which 2 met the inclusion criteria.

RESULTS

both studies used artificial intelligence models to predict the risk of sepsis after flexible uteroscopy. The first had a sample of 114 patients and was based on clinical and laboratory parameters. The second had an initial sample of 132 patients and was based on preoperative computed tomography images. Both obtained good measurements of Area Under the Curve (AUC), sensitivity and specificity, demonstrating good performance.

CONCLUSION

artificial intelligence provides multiple effective strategies for sepsis risk stratification in patients undergoing urological procedures for renal lithiasis, although further studies are needed.

International Alliance of Urolithiasis guideline on retrograde intrarenal surgery

OBJECTIVES

To set out the second in a series of guidelines on the treatment of urolithiasis by the International Alliance of Urolithiasis that concerns retrograde intrarenal surgery (RIRS), with the aim of providing a clinical framework for urologists performing RIRS.

MATERIALS AND METHODS

After a comprehensive search of RIRS-related literature published between 1 January 1964 and 1 October 2021 from the PubMed database, systematic review and assessment were performed to inform a series of recommendations, which were graded using modified GRADE methodology. Additionally, quality of evidence was classified using a modification of the Oxford Centre for Evidence-Based Medicine Levels of Evidence system. Finally, related comments were provided.

RESULTS

A total of 36 recommendations were developed and graded that covered the following topics: indications and contraindications; preoperative imaging; preoperative ureteric stenting; preoperative medications; peri-operative antibiotics; management of antithrombotic therapy; anaesthesia; patient positioning; equipment; lithotripsy; exit strategy; and complications.

CONCLUSION

The series of recommendations regarding RIRS, along with the related commentary and supporting documentation, offered here should help provide safe and effective performance of RIRS.

Machine Learning Approaches with Textural Features to Calculate Breast Density on Mammography

BACKGROUND

breast cancer (BC) is the world's most prevalent cancer in the female population, with 2.3 million new cases diagnosed worldwide in 2020. The great efforts made to set screening campaigns, early detection programs, and increasingly targeted treatments led to significant improvement in patients' survival. The Full-Field Digital Mammograph (FFDM) is considered the gold standard method for the early diagnosis of BC. From several previous studies, it has emerged that breast density (BD) is a risk factor in the development of BC, affecting the periodicity of screening plans present today at an international level.

OBJECTIVE

in this study, the focus is the development of mammographic image processing techniques that allow the extraction of indicators derived from textural patterns of the mammary parenchyma indicative of BD risk factors.

METHODS

a total of 168 patients were enrolled in the internal training and test set while a total of 51 patients were enrolled to compose the external validation cohort. Different Machine Learning (ML) techniques have been employed to classify breasts based on the values of the tissue density. Textural features were extracted only from breast parenchyma with which to train classifiers, thanks to the aid of ML algorithms.

RESULTS

the accuracy of different tested classifiers varied between 74.15% and 93.55%. The best results were reached by a Support Vector Machine (accuracy of 93.55% and a percentage of true positives and negatives equal to TPP = 94.44% and TNP = 92.31%). The best accuracy was not influenced by the choice of the features selection approach. Considering the external validation cohort, the SVM, as the best classifier with the 7 features selected by a wrapper method, showed an accuracy of 0.95, a sensitivity of 0.96, and a specificity of 0.90.

CONCLUSIONS

our preliminary results showed that the Radiomics analysis and ML approach allow us to objectively identify BD.

Risk of Sepsis in Retrograde Intrarenal Surgery: A Systematic Review of the Literature

Context

Objective

Evidence acquisition

Evidence synthesis

Conclusions

Patient summary

Current status of nomograms and scoring systems in paediatric endourology: A systematic review of literature

INTRODUCTION

The incidence of paediatric kidney stone disease is increasing worldwide, with the requirement for endourological interventions mirroring this. Multiple nomograms, grading tools and scoring systems now exist in the adult setting, which aim to enhance the pre-operative planning and decision-making associated with these surgeries. In recent years, there has been increasing interest in nomograms dedicated for use in the paediatric setting. This study provides an up-to-date review and assessment of available paediatric endourology nomograms and scoring systems.

METHODS

A comprehensive search of worldwide literature was conducted according PRISMA methodology. Studies describing paediatric-specific endourology nomograms, scoring systems or grading tools and studies externally validating these tools, or existing adult tools in a paediatric population, were evaluated and included in the narrative data synthesis.

RESULTS

A total of 7 endourology nomograms were identified. 4 were paediatric-specific, 2 for shockwave lithotripsy, 1 for percutaneous nephrolithotomy or ureteroscopy and 1 for percutaneous nephrolithotomy specifically. Only the 2 shockwave lithotripsy nomograms have been externally validated in 4 further studies and showed efficacy in predicting treatment success. 3 adult tools, all specific to PCNL have been investigated and validated in a paediatric setting in 11 studies. In general, they showed efficacy in the prediction of stone free rate but were poor at predicting likelihood of complications.

CONCLUSION

A limited number of paediatric-specific endourology predictive nomograms are available to aid in the management of kidney stone disease, with the strongest evidence supporting those designed for shockwave lithotripsy. Although 3 adult tools have been implemented, there are problems applying these to the paediatric setting and further development of paediatric-specific tools is necessary.

Advances in Ureteroscopy: New technologies and current innovations in the era of Tailored Endourological Stone Treatment (TEST)

Ureteroscopy has undergone many advances in recent decades. As a result, it is able to treat an increasing range of patient groups including special populations such as pregnancy, anomalous kidneys and extremes of age. Such advances include Holmium laser, high-power systems and pulse modulation. Thulium fibre laser is a more recent introduction to clinical practice. Ureteroscopes have also been improved alongside vision and optics. This article provides an up-to-date guide to these topics as well as disposable scopes, pressure control and developments in operating planning and patient aftercare. These advances allow for a custom strategy to be applied to the individual patient in what we describe using a new term: Tailored endourological stone treatment (TEST).

Level of evidence: 5

Role of low- versus high-power laser in the treatment of lower pole stones: prospective non-randomized outcomes from a university teaching hospital

Introduction:

Ureteroscopy and laser stone fragmentation [flexible ureteroscopy and laser lithotripsy (FURSL)] has risen over the last two decades. Laser technology has also evolved over the time, shifting from low- to high-power lasers with the addition of MOSES technology that allows for ‘dusting and pop-dusting’ of stones. The aim of the study was to look at the outcomes of FURSL in lower pole stones (LPS) using low- and high-power lasers.

Patient and Methods:

In this study, we compared the outcomes of low-power holmium laser (group A, 20 W) and high-power holmium laser (group B, including both 60 W MOSES integrated system and 100 W lasers) for all patients with LPS treated with laser lithotripsy. Data were collected for patient demographics, stone location, size, pre- and postoperative stent, length of stay, complications and stone free rate (SFR).

Results:

A total of 284 patients who underwent FURSL procedure for LPS were analysed (168 group A, 116 group B). Outcomes showed that compared with group A, group B had a higher SFR (91.6% versus 96.5%, p = 0.13) and shorter operative time (52 versus 38 min, p < 0.001). The median length of stay was <24 h in all groups (day-case procedures). The complication rate was comparable between the two groups but with more infectious complications (n = 7) noted in group A compared with group B (n = 3) (p = 0.53).

Conclusion:

Compared with low-power laser, the use of high-power laser for LPS significantly reduced the use of ureteral access sheath (UAS), postoperative stent and procedural time. Although non-statistically significant, the SFR was higher in the high-power group even for relatively larger stone sizes, which was also reflected in a reduction of sepsis-related complication rates with these lasers.

Special Issue 'Minimally Invasive Urological Procedures and Related Technological Developments'

The landscape of minimally invasive urological intervention is changing [...].