Development, multi-institutional external validation, and algorithmic audit of an artificial intelligence-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA) for patients undergoing radical prostatectomy: a retrospective cohort study.

BACKGROUND: Accurate prediction of side-specific extraprostatic extension (ssEPE) is essential for performing nerve-sparing surgery to mitigate treatment-related side-effects such as impotence and incontinence in patients with localised prostate cancer. Artificial intelligence (AI) might provide robust and personalised ssEPE predictions to better inform nerve-sparing strategy during radical prostatectomy. We aimed to develop, externally validate, and perform an algorithmic audit of an AI-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA). METHODS: Each prostatic lobe was treated as an individual case such that each patient contributed two cases to the overall cohort. SEPERA was trained on 1022 cases from a community hospital network (Trillium Health Partners; Mississauga, ON, Canada) between 2010 and 2020. Subsequently, SEPERA was externally validated on 3914 cases across three academic centres: Princess Margaret Cancer Centre (Toronto, ON, Canada) from 2008 to 2020; L'Institut Mutualiste Montsouris (Paris, France) from 2010 to 2020; and Jules Bordet Institute (Brussels, Belgium) from 2015 to 2020. Model performance was characterised by area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), calibration, and net benefit. SEPERA was compared against contemporary nomograms (ie, Sayyid nomogram, Soeterik nomogram [non-MRI and MRI]), as well as a separate logistic regression model using the same variables included in SEPERA. An algorithmic audit was performed to assess model bias and identify common patient characteristics among predictive errors. FINDINGS: Overall, 2468 patients comprising 4936 cases (ie, prostatic lobes) were included in this study. SEPERA was well calibrated and had the best performance across all validation cohorts (pooled AUROC of 0·77 [95% CI 0·75-0·78] and pooled AUPRC of 0·61 [0·58-0·63]). In patients with pathological ssEPE despite benign ipsilateral biopsies, SEPERA correctly predicted ssEPE in 72 (68%) of 106 cases compared with the other models (47 [44%] in the logistic regression model, none in the Sayyid model, 13 [12%] in the Soeterik non-MRI model, and five [5%] in the Soeterik MRI model). SEPERA had higher net benefit than the other models to predict ssEPE, enabling more patients to safely undergo nerve-sparing. In the algorithmic audit, no evidence of model bias was observed, with no significant difference in AUROC when stratified by race, biopsy year, age, biopsy type (systematic only vs systematic and MRI-targeted biopsy), biopsy location (academic vs community), and D'Amico risk group. According to the audit, the most common errors were false positives, particularly for older patients with high-risk disease. No aggressive tumours (ie, grade >2 or high-risk disease) were found among false negatives. INTERPRETATION: We demonstrated the accuracy, safety, and generalisability of using SEPERA to personalise nerve-sparing approaches during radical prostatectomy. FUNDING: None.

Multi-institutional Validation of Improved Vesicoureteral Reflux Assessment With Simple and Machine Learning Approaches.

PURPOSE: Vesicoureteral reflux grading from voiding cystourethrograms is highly subjective with low reliability. We aimed to demonstrate improved reliability for vesicoureteral reflux grading with simple and machine learning approaches using ureteral tortuosity and dilatation on voiding cystourethrograms. MATERIALS AND METHODS: Voiding cystourethrograms were collected from our institution for training and 5 external data sets for validation. Each voiding cystourethrogram was graded by 5-7 raters to determine a consensus vesicoureteral reflux grade label and inter- and intra-rater reliability was assessed. Each voiding cystourethrogram was assessed for 4 features: ureteral tortuosity, proximal, distal, and maximum ureteral dilatation. The labels were then assigned to the combination of the 4 features. A machine learning-based model, qVUR, was trained to predict vesicoureteral reflux grade from these features and model performance was assessed by AUROC (area under the receiver-operator-characteristic). RESULTS: A total of 1,492 kidneys and ureters were collected from voiding cystourethrograms resulting in a total of 8,230 independent gradings. The internal inter-rater reliability for vesicoureteral reflux grading was 0.44 with a median percent agreement of 0.71 and low intra-rater reliability. Higher values for each feature were associated with higher vesicoureteral reflux grade. qVUR performed with an accuracy of 0.62 (AUROC=0.84) with stable performance across all external data sets. The model improved vesicoureteral reflux grade reliability by 3.6-fold compared to traditional grading (P < .001). CONCLUSIONS: In a large pediatric population from multiple institutions, we show that machine learning-based assessment for vesicoureteral reflux improves reliability compared to current grading methods. qVUR is generalizable and robust with similar accuracy to clinicians but the added prognostic value of quantitative measures warrants further study.

Explainable artificial intelligence to predict the risk of side-specific extraprostatic extension in pre-prostatectomy patients.

INTRODUCTION: We aimed to develop an explainable machine learning (ML) model to predict side-specific extraprostatic extension (ssEPE) to identify patients who can safely undergo nerve-sparing radical prostatectomy using preoperative clinicopathological variables. METHODS: A retrospective sample of clinicopathological data from 900 prostatic lobes at our institution was used as the training cohort. Primary outcome was the presence of ssEPE. The baseline model for comparison had the highest performance out of current biopsy-derived predictive models for ssEPE. A separate logistic regression (LR) model was built using the same variables as the ML model. All models were externally validated using a testing cohort of 122 lobes from another institution. Models were assessed by area under receiver-operating-characteristic curve (AUROC), precision-recall curve (AUPRC), calibration, and decision curve analysis. Model predictions were explained using SHapley Additive exPlanations. This tool was deployed as a publicly available web application. RESULTS: Incidence of ssEPE in the training and testing cohorts were 30.7 and 41.8%, respectively. The ML model achieved AUROC 0.81 (LR 0.78, baseline 0.74) and AUPRC 0.69 (LR 0.64, baseline 0.59) on the training cohort. On the testing cohort, the ML model achieved AUROC 0.81 (LR 0.76, baseline 0.75) and AUPRC 0.78 (LR 0.75, baseline 0.70). The ML model was explainable, well-calibrated, and achieved the highest net benefit for clinically relevant cutoffs of 10-30%. CONCLUSIONS: We developed a user-friendly application that enables physicians without prior ML experience to assess ssEPE risk and understand factors driving these predictions to aid surgical planning and patient counselling (https://share.streamlit.io/jcckwong/ssepe/main/ssEPE_V2.py).

Do post-operative phone calls enhance family satisfaction and outcomes after outpatient pediatric urological surgeries? A prospective study.

INTRODUCTION: This study assesses whether post-operative check-in phone calls (POPC) performed within 48 h of outpatient pediatric urological surgeries by a non-medical professional (NMP) would increase patient/family satisfaction and minimize extraneous resource use by increasing email/telephone communication, while reducing emergency department (ED) visits within 30 days of that procedure. METHODS: Families of patients undergoing ambulatory pediatric urology surgeries were enrolled over 8 weeks. Group 1 did not receive POPC. Group 2 received a POPC within 48 h of their operation by a NMP. Both groups received a phone-call survey 2 weeks after surgery to assess families' perioperative satisfaction. RESULTS: In total, 74 families were enrolled (Group 1 = 44, Group 2 = 31). The response rates to phone surveys for Groups 1 and 2 were 59.1% and 77.4%, respectively. POPC did not improve perioperative satisfaction, nor did it significantly promote the use of nursing email/telephone communication (19.2% vs. 4.2%, p = 0.128) or reduce ED visits (15.4% vs. 0.0%, p = 0.111). However, all families in Group 2 thought POPC was timed appropriately and 79.1% perceived it to be helpful in reducing post-operative anxiety. CONCLUSION: POPC by a NMP within 48 h of surgery may not affect perioperative satisfaction of families of patients undergoing same-day pediatric urology surgery but may have an impact in reducing post-operative anxiety.

Variability among Canadian pediatric surgeons and pediatric urologists in the management of cryptorchidism in boys before the publication of major guidelines: a retrospective review of a single tertiary centre

Background: Before 2014, there was a lack of recommendations on managing cryptorchidism, or undescended testis (UDT), from a large pediatric urological or surgical organization. We assessed the variability in management of UDT among pediatric urologists and pediatric surgeons at a single tertiary pediatric referral centre before publication of major guidelines. Methods: We performed a retrospective review of the electronic records of patients who underwent primary unilateral or bilateral orchidopexy at our centre between January 2012 and January 2014. Results: A total of 488 patients (616 testes) were identified, of whom 405 (83.0%) and 83 (17.0%) were managed by pediatric urologists and pediatric surgeons, respectively. There was no difference in baseline characteristics, including age seen in clinic or at surgery, testis location/palpability and availability of preoperative ultrasonograms, of patients seen by the 2 groups. Pediatric surgeons ordered preoperative ultrasonography more often than pediatric urologists (25.3% v. 3.7%, p < 0.001). With palpable UDTs, although both groups used open approaches, pediatric urologists preferred a scrotal approach (56.9%), and pediatric surgeons approached most testes inguinally (98.8%). With nonpalpable UDTs, laparoscopic approaches were preferred by both groups; however, pediatric urologists used a 2-stage Fowler­Stephens approach more often than pediatric surgeons (48.4% v. 15.8%, p < 0.001). Conclusion: There was wide variation in the management of primary UDT between pediatric urologists and pediatric surgeons before the publication of guidelines. The most prominent difference between the 2 groups was in the ordering of preoperative ultrasonography. Future assessment of change in practice patterns may elucidate whether guidelines are an effective tool for standardization of practice.

Contexte: Avant 2014, on ne disposait pas de recommandations émanant d'une grande organisation urologique ou chirurgicale pédiatrique pour la prise en charge de la cryptorchidie (absence d'un ou des deux testicules dans le scrotum). Nous avons évalué les divers types de prise en charge de la cryptorchidie chez les urologues et les chirurgiens pédiatriques dans un seul centre tertiaire de référence pédiatrique avant la publication de lignes directrices majeures. Méthodes: Nous avons procédé à une revue rétrospective des dossiers électroniques de patients ayant subi une orchidopexie unilatérale ou bilatérale primaire dans notre centre entre janvier 2012 et janvier 2014. Résultats: En tout, 488 patients (616 testicules) ont été identifiés, dont 405 (83,0 %) et 83 (17,0 %) ont été traités respectivement par des urologues et des chirurgiens pédiatriques. On n'a noté aucune différence quant aux caractéristiques de départ des patients vus par les 2 groupes, telles que l'âge lors de la consultation à la clinique ou lors de la chirurgie, la localisation/palpabilité des testicules et le recours à l'échographie préopératoire. Les chirurgiens pédiatriques ont demandé une échographie préopératoire plus souvent que les urologues pédiatriques (25,3 % c. 3,7 %, p < 0,001). En présence de cryptorchidie palpable, même si les 2 groupes ont utilisé une approche ouverte, les urologues pédiatriques ont préféré l'approche scrotale (55,4 %) et les chirurgiens pédiatriques l'approche inguinale (98,8 %). En présence de cryptorchidie non palpable, les approches laparoscopiques ont été privilégiées par les 2 groupes; toutefois, les urologues pédiatriques ont utilisé une approche Fowler­Stephens en 2 temps plus souvent que les chirurgiens pédiatriques (48,4 % c. 15,8 %, p < 0,001). Conclusion: On a noté une grande variation dans la prise en charge de la cryptorchidie primaire entre les urologues et les chirurgiens pédiatriques avant la publication des lignes directrices. La principale différence entre les 2 groupes concernait le recours à l'échographie préopératoire. L'évaluation future des changements affectant la pratique permettrait de déterminer si les lignes directrices sont un outil efficace pour sa standardisation.

Testing quality improvement interventions.

The quality of health care is in drastic need of improvement. Surgeons are key players in the health care delivery system, and as such, they should be involved by leading or participating in the improvements that should take place. This article posits some suggestions as to how surgeons can participate in the efforts to make the health care provided to patients better and make the system a better place to work for surgeons and for other health professionals. Participation in quality improvement (QI) initiatives has the potential to bring much personal satisfaction for surgeons who help the process to move forward, even though it takes some effort and even forces them to learn some new skills and attitudes to what can be accomplished by QI teams. This article provides a methodologic guide to conducting and evaluating QI research.

Vesicoureteral reflux and complete ureteral duplication. Conservative or surgical management?

PURPOSE: The management of vesicoureteral reflux (VUR) in a duplicated collecting system (DS) is controversial. Available literature is sparse and it does not assess all co-factors. We compared the outcome of VUR in DS cases with VUR in single system (SS) cases, given similar clinical management in the 2 groups. MATERIALS AND METHODS: A retrospective cohort study was done to compare the outcome of VUR in 35 children (44 units) with a DS and in 95 (150 units) with an SS. Patients with secondary reflux, incomplete duplication and ureterocele were excluded. Two groups were similar in terms of prognostic factors. Mean followup in the DS and SS groups was 43 and 48 months, respectively. Outcomes of interest were spontaneous resolution or uncomplicated persistence vs surgical correction. The same criteria were used to intervene surgically in the 2 groups. RESULTS: In the DS group 24 of 35 patients (69%) underwent surgery compared with 25 of 95 (25%) in the SS group. Multivariate analysis showed an association between surgery due to complications and the presence of DS (p = 0.0001). Higher grade and female gender were independent predictors (p = 0.02 and 0.0007, respectively). The likelihood of undergoing surgery was the same for low grade VUR (I and II) in the DS and SS groups (p = 0.16). No resolution was seen in the duplex group with severe VUR at a mean followup of 42 months. CONCLUSIONS: Low grade VUR in DS cases has an outcome similar to that of VUR in SS cases. Females with moderate or high grade VUR and a DS should be treated differently because they present more often with complications.

Retroperitoneal-assisted laparoscopic pyeloplasty in children: initial experience.

PURPOSE: To demonstrate a novel application of laparoscopy to assist in the correction of ureteropelvic junction (UPJ) obstruction. PATIENTS AND METHODS: A retroperitoneal space is created, and the UPJ is identified and dissected from the surrounding tissue with a 1 x 10-mm 0 degrees telescope and 2 x 5-mm endoscopic instruments. Using a 5-0 Prolene stay suture, the UPJ is brought up through the 10-mm trocar site to the skin level, and the pyeloplasty is performed ex vivo over a double-J stent with loop magnification. Between July 2002 and March 2003, nine male and two female patients with UPJ obstruction underwent a pyeloplasty using this retroperitoneal-assisted laparoscopic pyeloplasty (RALP). The operative time, hospital stay, pain management, and follow-up radiologic studies were reviewed. RESULTS: In nine patients, RALP (bilateral in one patient) was performed (nine on the left side and one on the right). In the remaining two patients, mobilization of the UPJ was inadequate, and open conversion was performed. The average RALP operative time was 160 minutes (range 121-193 minutes). Postoperative pain management was optimal using oral codeine in eight patients, while one patient (RALP and pyelolithotomy) received parenteral analgesic postoperatively. The average length of stay in the hospital was 2 days (range 1-3 days). Follow-up (5-14 months) radiologic studies after stent removal showed improvement in the hydronephrosis in all except one patient. Furosemide renal scan at 3 to 6 months postoperatively was done in all patients and showed no obstruction. CONCLUSION: We consider RALP as the technique of choice for surgeons who want to increase their reconstructive laparoscopic skills. It provides an additional technique when skilled laparoscopists are faced with technically difficult pyeloplasties.