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.

Real world propensity score matched analysis evaluating the influence of en-bloc vs. non en-bloc techniques, energy and instrumentation on enucleation outcomes for large and very large prostates.

PURPOSE: The primary aim of the study was to evaluate if en-bloc vs. non en-bloc made a difference to intra-, peri- and post-operative surgical outcomes of anatomical endoscopic enucleation (AEEP) in large (> 80 cc) and very large prostates (> 200 cc). The secondary aim was to determine the influence of energy and instruments used. METHODS: Data of patients with > 80 cc prostate who underwent surgery between 2019 and 2022 were obtained from 16 surgeons across 13 centres in 9 countries. Propensity score matching (PSM) was used to reduce confounding. Logistic regression was performed to evaluate factors associated with postoperative urinary incontinence (UI). RESULTS: 2512 patients were included with 991 patients undergoing en-bloc and 1521 patients undergoing non-en-bloc. PSM resulted in 481 patients in both groups. Total operation time was longer in the en-bloc group (p < 0.001), enucleation time was longer in the non en-bloc group (p < 0.001) but morcellation times were similar (p = 0.054). Overall, 30 day complication rate was higher in the non en-bloc group (16.4% vs. 11.4%; p = 0.032). Rate of late complications (> 30 days) was similar (2.3% vs. 2.5%; p > 0.99). There were no differences in rates of UI between the two groups. Multivariate analysis revealed that age, Qmax, pre-operative, post-void residual urine (PVRU) and total operative time were predictors of UI. CONCLUSIONS: In experienced hands, AEEP in large prostates by the en-bloc technique yields a lower rate of complication and a slightly shorter operative time compared to the non en-bloc approach. However, it does not have an effect on rates of post-operative UI.

One-Year Outcomes of Transurethral Treatment of Bladder Neck Stenosis Following Transurethral Resection of the Prostate. Results from a Large, Multicenter Series.

Purpose: To assess management and outcomes of bladder neck stenosis (BNS) post-transurethral resection of the prostate (TURP) in 12 centers. Patients and Methods: A retrospective analysis of patients who underwent transurethral BN incision for stenosis following TURP from January 2015 and January 2023 was performed. Inclusion criteria included endoscopic diagnosis of BNS associated with obstruction and/or lower urinary tract symptoms. Data are presented as median and interquartile range. Two distinct univariable logistic regression analyses were performed to identify factors associated with overall urinary incontinence and recurrent stenosis. Results: Three hundred and seventy-two men were included. 95.2% of patients developed BNS following bipolar TURP. 21.0% of patients were on an indwelling catheter before BNS incision. Bipolar electrocautery was the most commonly employed energy for incision (66.5%). Collings knife was the most commonly employed (61.2%) instrument for incision, followed by end-firing holmium lasering (35.3%). Median operation time was 30 (25-45) minutes. The overall complication rate was 12.4%, with 19 (5.1%) patients suffering from acute urinary retention, 6 (1.6%) patients requiring prolonged irrigation due to persistent hematuria, and a surgical hemostasis was necessary in 8 cases (2.2%). Overall postoperative incontinence rate was 17.2%, with urge incontinence accounting for the most common type (45.3%). Incontinence lasted more than 3 months in 9/46 (14.3%) patients. Recurrent BNS occurred in 29 (7.8%) patients and was managed by re-endoscopic incision in 21 (5.6%) patients and dilatation only in 6 (1.6%) patients. Two (0.5%) patients underwent urethroplasty for recalcitrant stenosis. Logistic regression analysis showed that Collings knife was associated with higher odds of having postoperative incontinence (OR 3.93 95% CI 1.45-11.13, p=0.008) and BN recurrence (OR 3.589 95% CI 1.157-15.7, p=0.047). Conclusion: Transurethral BN incision provides satisfactory short-term results with an acceptable rate of complications.

Catalyzing Precision Medicine: Artificial Intelligence Advancements in Prostate Cancer Diagnosis and Management.

BACKGROUND: The aim was to analyze the current state of deep learning (DL)-based prostate cancer (PCa) diagnosis with a focus on magnetic resonance (MR) prostate reconstruction; PCa detection/stratification/reconstruction; positron emission tomography/computed tomography (PET/CT); androgen deprivation therapy (ADT); prostate biopsy; associated challenges and their clinical implications. METHODS: A search of the PubMed database was conducted based on the inclusion and exclusion criteria for the use of DL methods within the abovementioned areas. RESULTS: A total of 784 articles were found, of which, 64 were included. Reconstruction of the prostate, the detection and stratification of prostate cancer, the reconstruction of prostate cancer, and diagnosis on PET/CT, ADT, and biopsy were analyzed in 21, 22, 6, 7, 2, and 6 studies, respectively. Among studies describing DL use for MR-based purposes, datasets with magnetic field power of 3 T, 1.5 T, and 3/1.5 T were used in 18/19/5, 0/1/0, and 3/2/1 studies, respectively, of 6/7 studies analyzing DL for PET/CT diagnosis which used data from a single institution. Among the radiotracers, [68Ga]Ga-PSMA-11, [18F]DCFPyl, and [18F]PSMA-1007 were used in 5, 1, and 1 study, respectively. Only two studies that analyzed DL in the context of DT met the inclusion criteria. Both were performed with a single-institution dataset with only manual labeling of training data. Three studies, each analyzing DL for prostate biopsy, were performed with single- and multi-institutional datasets. TeUS, TRUS, and MRI were used as input modalities in two, three, and one study, respectively. CONCLUSION: DL models in prostate cancer diagnosis show promise but are not yet ready for clinical use due to variability in methods, labels, and evaluation criteria. Conducting additional research while acknowledging all the limitations outlined is crucial for reinforcing the utility and effectiveness of DL-based models in clinical settings.

Artificial Intelligence in Urologic Robotic Oncologic Surgery: A Narrative Review.

With the rapid increase in computer processing capacity over the past two decades, machine learning techniques have been applied in many sectors of daily life. Machine learning in therapeutic settings is also gaining popularity. We analysed current studies on machine learning in robotic urologic surgery. We searched PubMed/Medline and Google Scholar up to December 2023. Search terms included "urologic surgery", "artificial intelligence", "machine learning", "neural network", "automation", and "robotic surgery". Automatic preoperative imaging, intraoperative anatomy matching, and bleeding prediction has been a major focus. Early artificial intelligence (AI) therapeutic outcomes are promising. Robot-assisted surgery provides precise telemetry data and a cutting-edge viewing console to analyse and improve AI integration in surgery. Machine learning enhances surgical skill feedback, procedure effectiveness, surgical guidance, and postoperative prediction. Tension-sensors on robotic arms and augmented reality can improve surgery. This provides real-time organ motion monitoring, improving precision and accuracy. As datasets develop and electronic health records are used more and more, these technologies will become more effective and useful. AI in robotic surgery is intended to improve surgical training and experience. Both seek precision to improve surgical care. AI in ''master-slave'' robotic surgery offers the detailed, step-by-step examination of autonomous robotic treatments.

Regional versus general anaesthesia in percutaneous nephrolithotomy: a systematic review and meta-analysis.

Introduction: Several studies have compared the safety and effectiveness of general and regional anaesthesia in percutaneous nephrolithotomy (PCNL). This study aimed to compare the perioperative and postoperative outcomes of general anaesthesia and regional anaesthesia for patients undergoing PCNL. Material and methods: For relevant articles, three electronic databases, including PubMed, Scopus, and Web of Science, were searched from their inception until March 2023. A meta-analysis has been reported in line with PRISMA 2020 and AMSTAR Guidelines. The risk ratio (RR) and mean difference (MD) were applied for the comparison of dichotomous and continuous variables with 95% confidence intervals (CI). Results: The final cohort analysis, comprised 3871 cases of PCNL, (2154 regional anaesthesia and 1717 general anaesthesia). Compared to general anaesthesia, the regional anaesthesia group had a significantly shorter length of stay (MD = -0.34 days, 95% CI -0.56 to -0.12, p = 0.002), lower postoperative nausea and vomiting rates (RR = 0.16, 95% CI 0.03 to 0.80, p = 0.026), lower complications grade III-V rates (RR = 0.68, 95% CI 0.53 to 0.88, p = 0.004), and lower postoperative visual analogue pain score (VAS) at 1 hour (MD = -3.5, 95% CI -4.1 to -2.9, p <0.001). There were no significant differences in other outcomes between the two groups. Conclusions: Our results show that PCNL under regional anaesthesia is safe and feasible, with comparable results to those done under general anaesthesia. While patient selection is important, counselling and decision-making for these procedures must go hand in hand to achieve the best clinical outcome.

Patient experiences and perceptions of kidney stone surgery: what lessons can be learned from TikTok?

Introduction: The aim of this study was to perform an evaluation of patient experiences and perceptions regarding kidney stone surgery on the social media platform TikTok. An increasing number of the public use social media (SoMe) as a platform to share their views regarding their experiences related to surgical treatment. Methods: Using the hashtag #kidneystonesurgery, the 100 most recent video posts as of 01.01.2024 on TikTok were included. As well as demographic data such as gender and location, thematic content was also collected. To achieve this, a previously published framework was used and adapted for application in the setting of kidney stone surgery. This was piloted on 20 sample videos to assess its feasibility before revision and establishment of the final framework. This included the following key areas: Pain, Complications, Anxiety, Recovery, Return to work, Finances, Treatment delays, Diet and Prevention and stent complaints. Results: The majority of posts (95%) were from North America, 80% by females and the mean number of video views was 92,826 (range: 261-2,000,000). 76% of the videos discussed ureteroscopy (URS). 49% were filmed at the hospital, which was named in 9% of the videos. Top three topics discussed were: Recovery (65%), pain (62%) and stents (55%). This was followed by anxiety (39%) and complications (24%). 12% of these videos uploaded by lay people included basic medical information that was wholly incorrect. More than half of the posts (51%) were negative in tone. Treatment delays (5%) and a lack of sufficient preoperative information (4%) were also raised, that appeared to contribute to the negative reports. However, the main cause for negative tone owed to the 80% of the patients (n = 44) who discussed stents that focused their video on the pain suffered from the post operative stent. Conclusion: There is a high level of usership and engagement on TikTok on the subject of kidney stone surgery. The proportion of negative videos is high and much of this is related to the bothersome stent symptoms and complications. This could easily lead to misperceptions among potential patients about the true burden of such adverse events.

Current status of the adjustable transobturator male system (ATOMSTM) for male stress urinary incontinence.

Male stress urinary incontinence is a debilitating condition, which can occur after prostate surgery. In persistent cases, surgery is indicated and a number of options are available. This includes one of the male slings, Adjustable transobturator male system (ATOMSTM, A.M.I, Austria). There are now an increasing number of studies published. This review provides an overview of the current status of this implant device including technical considerations, surgical outcomes and potential advantages and disadvantages compared to alternatives such as the artificial urinary sphincter.

Reoperation Rate for Residual/Regrowth Adenoma Following Transurethral Interventions for Benign Prostatic Enlargement: Results from a Systematic Review and Meta-Analysis of Comparative Randomized Studies.

Objective: To perform a systematic review to assess the incidence of reoperation rate for residual/regrowth adenoma after transurethral surgeries for benign prostatic enlargement. Materials and Methods: A systematic literature search was performed on November 12, 2023, using Cochrane Central Register of Controlled Trials, PubMed, and Scopus. We only included randomized studies comparing monopolar (M)/bipolar (B) transurethral resection of the prostate (TURP) vs ablation vs enucleation procedures. Incidence of reoperation was assessed using the Cochran-Mantel-Haenszel Method and reported as risk ratio (RR), 95% confidence interval (CI), and p-values. Statistical significance was set at p < 0.05. Evidence synthesis: Forty-eight studies were included. Six studies compared enucleation vs TURP, 41 ablation vs TURP, and 1 study enucleation vs ablation vs TURP, encompassing 457 patients in enucleation, 2259 in ablation, and 2517 in the TURP group. The pooled incidence of reoperation was 6.2%, 0.7%, 2.3%, and 4.3% after ablation, enucleation, M-TURP, and B-TURP, respectively. Meta-analysis showed that the incidence of reoperation was significantly lower in the enucleation group (RR 0.28, 95% CI 0.10-0.81, p = 0.02), but the difference accounted only in studies with follow-up between 1 and 3 years (RR 0.18, 95% CI 0.04-0.85, p = 0.03). The incidence of reoperation was significantly lower in the enucleation compared with the B-TURP group (RR 0.14, 95% CI 0.03-0.77, p = 0.02). Meta-analysis showed that the incidence of reoperation was significantly higher in the ablation group (RR 1.81, 95% CI 1.33-2.47, p = 0.0002), but there was no difference in studies with follow-up up to 1 year (odds ratio 1.78 95% CI 0.97-3.29, p = 0.06) longer than 5 years (RR 2.02, 95% CI 0.71-5.79, p = 0.19). The incidence of reoperation was significantly higher in the ablation compared with the M-TURP group (RR 1.91, 95% CI 1.44-2.54, p < 0.0001). Conclusions: In mid-term follow-up, reoperation rate for residual/regrowth adenoma was significantly lower after enucleation, although was significantly higher after ablation compared with TURP.

High-power holmium laser versus thulium fiber laser for endoscopic enucleation of the prostate in patients with glands larger than 80 ml: Results from the Prostate Endoscopic EnucLeation study group.

Background: Endoscopic enucleation of the prostate (EEP) has gained acceptance as an equitable alternative to transurethral resection of the prostate for benign prostate hyperplasia (BPH). Our primary aim is to compare peri-operative outcomes of EEP using thulium fiber laser (TFL) against high-power holmium laser (HPHL) in hands of experienced surgeons for large prostates (≥80 ml in volume). Secondary outcomes were assess complications within 1 year of follow up. Materials and Methods: We retrospectively reviewed patients with benign prostatic hyperplasia who underwent EEP with TFL or HPHL in 13 centers (January 2019-January 2023). Patients with prostate volume ≥80 ml were included, while those with concomitant prostate cancer, previous prostate/urethral surgery, and pelvic radiotherapy were excluded. Results: Of 1,929 included patients, HPHL was utilized in 1,459 and TFL in 470. After propensity score matching (PSM) for baseline characteristics, 247 patients from each group were analyzed. Overall operative time (90 [70, 120] vs. 52.5 [39, 93] min, P < 0.001) and enucleation time (90 [70, 105] vs. 38 [25, 70] min, P < 0.001) were longer in the TFL group, with comparable morcellation time (13 [10, 19.5] vs. 13 [10, 16.5] min, P = 0.914). In terms of postoperative outcomes, there were no differences in 30-day complications such as acute urinary retention, urinary tract infection or sepsis. In the PSM cohort, univariable analyses showed that higher age, lower preoperative Qmax, higher preoperative PVRU, and longer operation time were associated with higher odds of postoperative incontinence, while 2-lobe enucleation had lower odds of incontinence compared to 3-lobe enucleation. Conclusions: This real-world study reaffirms that HPHL and TFL in large prostates are equally efficacious in terms of 30-day complications. TFL with the en-bloc technique has a shorter operative time which significantly improves short- and medium-term functional outcomes.

Percutaneous Nephrolithotomy for De Novo Urolithiasis After Kidney Transplantation: A Systematic Review of the Literature.

Introduction and Objective: Renal transplantation is the treatment for end-stage renal disease that offers better quality of life and survival. Among the possible complications that might affect allografts, urolithiasis might have severe consequences, causing acute kidney injury (AKI) or septic events in immunocompromised patients. Allograft stones might be treated with percutaneous nephrolithotomy (PCNL). The aim of this Cochrane style review was to assess the safety and efficacy of PCNL in patients with renal transplant. Methods: A comprehensive search in the literature was performed including articles between July 1982 and June 2023, with only English original articles selected for this review. Results: The final review encompassed nine articles (108 patients). The mean age was 46.4 ± 8.7 years, with a male:female ratio of 54:44. The average time from transplantation to urolithiasis onset was 47.54 ± 23.9 months. Predominant symptoms upon presentation were AKI (32.3%), followed by urinary tract infection and fever (24.2%), and oliguria (12.9%). The mean stone size was 20.1 ± 7.3 mm, with stones located in the calices or pelvis (41%), ureteropelvic junction (23.1%), or proximal ureter (28.2%). PCNL (22F-30F) was more frequently performed than mini-PCNLs (16F-20F) (52.4% vs 47.6%). Puncture was guided by ultrasound (42.9%), fluoroscopy (14.3%), or both (42.9%). The stone-free rate (SFR) and complication rates were 92.95% (range: 77%-100%) and 5.5%, respectively, with only one major complication reported. Postoperatively, a ureteral stent and nephrostomy were commonly placed in 47%, with four patients needing a second look PCNL. During an average follow-up of 32.5 months, the recurrence rate was 3.7% (4/108), and the mean creatinine level was 1.37 ± 0.28 mg/dL. Conclusions: PCNL remains a safe and effective option in de novo allograft urolithiasis, allowing to treat large stones in one-step surgery. A good SFR is achieved with a low risk of minor complications. These patients should be treated in an endourology center in conjunction with the renal or transplant team.

Challenges and expectations of international medical graduates moving to the UK: An online survey.

INTRODUCTION: International medical graduates (IMGs) account for 41% of the UK doctor's workforce but often work in isolated roles, receive minimal constructive feedback regarding their work and offered limited opportunities for career progression. We conducted a survey researching the views of IMGs or doctors from ethnic minority backgrounds on the support given to them. METHODS: A survey was carried out on physician demographics, grade and date of first NHS appointment, familiarity and support offered in NHS, induction and study leave, Professional and Linguistic Assessments Board exams and General Medical Council (GMC) referrals. It was drafted via surveymonkey.co.uk platform and circulated via relevant closed medical groups. RESULTS: A total of 173 IMGs and 16 British trained doctors (controls) took the survey. In the IMGs first job, there was no dedicated supervisor, mentor, induction, shadowing period and study leave for 56%, 86%, 52%, 59% and 52%, respectively. Suggestions given for improvements included teaching sessions, mentors, work orientation, supernumerary period and paid induction by 80%, 78%, 76%, 61% and 41% respectively. While 59% of participants knew of another IMG referred to the GMC, the primary reasons given were lack of knowledge of NHS, bias, communication difficulties and cultural differences. CONCLUSION: This paper reflects the views of doctors regarding the support given to IMGs during their first NHS appointment and subsequent jobs in the NHS. IMGs require a focused and detailed induction, mentorship, educational and clinical supervision throughout their transition to the NHS.

Safety and Efficacy of "Dusting and Pop-Dusting" with High-Power Laser for Treatment of Large Pediatric Stones with Ureteroscopy and Lasertripsy: Prospective Outcomes from a University Teaching Hospital.

Introduction: The wide use of high-power laser has changed the landscape of ureteroscopy and lasertripsy (URSL). We wanted to look at the role and outcomes of high-power holmium:yttrium-aluminum-garnet laser for URSL in pediatric stone disease. Methods: A prospective analysis of consecutive pediatric patients treated with "Dusting and Pop-dusting" using a high-power laser was done between January 2016 and March 2022. The project was registered with our audit committee. Data were analyzed for patient demographics, stone characteristics, operative details, procedural outcomes, and complications. Stone-free rate (SFR) was defined as fragments ≤2 mm on postoperative ultrasound imaging 2-3 months after the procedure. Results: A total of 35 patients underwent 43 procedures (1.2 procedure/patient) during the study period with a mean age of 9.4 years (range 1-16 years) and a male:female ratio of 13:22. The stone location was in the kidney in 32 (91.4%) patients of which 8 were in multiple renal locations. The mean stone size was 18 mm (range 10-39 mm), with the pre- and post-stent rates of 37% and 56%, respectively. An access sheath was used in 19 (44%) procedures. The overall SFR on ultrasound scan was 94% (n = 33) with no procedural complications noted in our series and a mean length of stay of 0.9 days. Conclusion: Pediatric URSL using a high-power laser achieves a high SFR even for large and multiple renal stones with no complications noted in our prospective series. Parents must, however, be counseled about the need for staged procedures, which might be needed for large stones.

Defining minimal invasive surgical therapy for benign prostatic obstruction surgery: Perspectives from a global knowledge, attitude, and practice survey.

Objective: To scrutinize the definitions of minimal invasive surgical therapy (MIST) and to investigate urologists' knowledge, attitudes, and practices for benign prostatic obstruction surgeries. Methods: A 36-item survey was developed with a Delphi method. Questions on definitions of MIST and attitudes and practices of benign prostatic obstruction surgeries were included. Urologists were invited globally to complete the online survey. Consensus was achieved when more than or equal to 70% responses were "agree or strongly agree" and less than or equal to 15% responses were "disagree or strongly disagree" (consensus agree), or when more than or equal to 70% responses were "disagree or strongly disagree" and less than or equal to 15% responses were "agree or strongly agree" (consensus disagree). Results: The top three qualities for defining MIST were minimal blood loss (n=466, 80.3%), fast post-operative recovery (n=431, 74.3%), and short hospital stay (n=425, 73.3%). The top three surgeries that were regarded as MIST were Urolift® (n=361, 62.2%), Rezum® (n=351, 60.5%), and endoscopic enucleation of the prostate (EEP) (n=332, 57.2%). Consensus in the knowledge section was achieved for the superiority of Urolift®, Rezum®, and iTIND® over transurethral resection of the prostate with regard to blood loss, recovery, day surgery feasibility, and post-operative continence. Consensus in the attitudes section was achieved for the superiority of Urolift®, Rezum®, and iTIND® over transurethral resection of the prostate with regard to blood loss, recovery, and day surgery feasibility. Consensus on both sections was achieved for EEP as the option with the better symptoms and flow improvement, lower retreatment rate, and better suitable for prostate more than 80 mL. Conclusion: Minimal blood loss, fast post-operative recovery, and short hospital stay were the most important qualities for defining MIST. Urolift®, Rezum®, and EEP were regarded as MIST by most urologists.

Urological Guidelines for Kidney Stones: Overview and Comprehensive Update.

BACKGROUND: Evidence-based guidelines are published by urological organisations for various conditions, including urolithiasis. In this paper, we provide guidance on the management of kidney stone disease (KSD) and compare the American Urological Association (AUA) and European Association of Urologists (EAU) guidelines. METHODS: We evaluate and appraise the evidence and grade of recommendation provided by the AUA and EAU guidelines on urolithiasis (both surgical and medical management). RESULTS: Both the AUA and EAU guidelines provide guidance on the type of imaging, treatment options, and medical therapies and advice on specific patient groups, such as in paediatrics and pregnancy. While the guidelines are generally aligned and based on evidence, some subtle differences exist in the recommendations, but both are generally unanimous for the majority of the principles of management. CONCLUSIONS: We recommend that the guidelines should undergo regular updates based on recently published material, and while these guidelines provide a framework, treatment plans should still be personalised, respecting patient preferences, surgical expertise, and various other individual factors, to offer the best outcome for kidney stone patients.

Use of Temporally Validated Machine Learning Models To Predict Outcomes of Percutaneous Nephrolithotomy Using Data from the British Association of Urological Surgeons Percutaneous Nephrolithotomy Audit.

BACKGROUND AND OBJECTIVE: Machine learning (ML) is a subset of artificial intelligence that uses data to build algorithms to predict specific outcomes. Few ML studies have examined percutaneous nephrolithotomy (PCNL) outcomes. Our objective was to build, streamline, temporally validate, and use ML models for prediction of PCNL outcomes (intensive care admission, postoperative infection, transfusion, adjuvant treatment, postoperative complications, visceral injury, and stone-free status at follow-up) using a comprehensive national database (British Association of Urological Surgeons PCNL). METHODS: This was an ML study using data from a prospective national database. Extreme gradient boosting (XGB), deep neural network (DNN), and logistic regression (LR) models were built for each outcome of interest using complete cases only, imputed, and oversampled and imputed/oversampled data sets. All validation was performed with complete cases only. Temporal validation was performed with 2019 data only. A second round used a composite of the most important 11 variables in each model to build the final model for inclusion in the shiny application. We report statistics for prognostic accuracy. KEY FINDINGS AND LIMITATIONS: The database contains 12 810 patients. The final variables included were age, Charlson comorbidity index, preoperative haemoglobin, Guy's stone score, stone location, size of outer sheath, preoperative midstream urine result, primary puncture site, preoperative dimercapto-succinic acid scan, stone size, and image guidance (https://endourology.shinyapps.io/PCNL_Demographics/). The areas under the receiver operating characteristic curve was >0.6 in all cases. CONCLUSIONS AND CLINICAL IMPLICATIONS: This is the largest ML study on PCNL outcomes to date. The models are temporally valid and therefore can be implemented in clinical practice for patient-specific risk profiling. Further work will be conducted to externally validate the models. PATIENT SUMMARY: We applied artificial intelligence to data for patients who underwent a keyhole surgery to remove kidney stones and developed a model to predict outcomes for this procedure. Doctors could use this tool to advise patients about their risk of complications and the outcomes they can expect after this surgery.

Adverse events related to accessory devices used during ureteroscopy: Findings from a 10-year analysis of the Manufacturer and User Facility Device Experience (MAUDE) database.

Objectives: The objective of this study was to evaluate adverse events and device events related to accessories used during ureteroscopy (URS). Materials and methods: Analysis was performed of the records available in the Manufacturer and User Facility Device Experience database in the United States. Information was collected on characteristics of problem, timing, manufacturer verdict, successful completion of planned surgery, prolonged anaesthesia and injury to patient or staff. Results: Five-hundred seventy-one events related to URS accessories were recorded. These were associated with the following devices: baskets (n = 347), access sheath (n = 86), guidewires (n = 78), balloon dilators (n = 27), ARDs (n = 17) and ureteral catheters (n = 16). Of the events, 12.7% resulted in patient injuries. Forty-eight per cent of the events resulted in prolonged anaesthesia, but the planned surgery was successfully completed in 78.4% of all cases. Collectively, the manufacturers accepted responsibility due to actual device failure in only 0.5% of cases. Common problems for baskets were failure to deploy (39.5%) and complete detachment of basket head (34.6%) and partial breakage of the basket head (12.4%). Of the basket group, 4.3% required open or percutaneous surgery to remove stuck basket. Full break of the body of the access sheath occurred in 41.9% and complete ureteral avulsion in 3.5%. For balloon dilators, there was a burst in 37% of cases. Broken guidewires were associated with 11.5% requiring repeat intervention for retrieval and 6.4% required JJ stent due to perforation to the collecting system. No injuries to operating staff were recorded with accessory usage. Conclusion: Accessories used during URS are fragile. Potential for serious injury does exist as a direct result of their use. Surgeons should familiarise themselves with these events and how they can be prevented.