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).

Insights into the renal pathogenesis in Schimke immuno-osseous dysplasia: A renal histological characterization and expression analysis.

Schimke immuno-osseous dysplasia (SIOD) is a pleiotropic disorder caused by mutations in the SWI/SNF2-related, matrix-associated, actin-dependent regulator of chromatin, subfamily a-like-1 (SMARCAL1) gene, with multiple clinical features, notably end-stage renal disease. Here we characterize the renal pathology in SIOD patients. Our analysis of SIOD patient renal biopsies demonstrates the tip and collapsing variants of focal segmental glomerulosclerosis (FSGS). Additionally, electron microscopy revealed numerous glomerular abnormalities most notably in the podocyte and Bowman's capsule. To better understand the role of SMARCAL1 in the pathogenesis of FSGS, we defined SMARCAL1 expression in the developing and mature kidney. In the developing fetal kidney, SMARCAL1 is expressed in the ureteric epithelium, stroma, metanephric mesenchyme, and in all stages of the developing nephron, including the maturing glomerulus. In postnatal kidneys, SMARCAL1 expression is localized to epithelial tubules of the nephron, collecting ducts, and glomerulus (podocytes and endothelial cells). Interestingly, not all cells within the same lineage expressed SMARCAL1. In renal biopsies from SIOD patients, TUNEL analysis detected marked increases in DNA fragmentation. Our results highlight the cells that may contribute to the renal pathogenesis in SIOD. Further, we suggest that disruptions in genomic integrity during fetal kidney development contribute to the pathogenesis of FSGS in SIOD patients.

A case of cardiac tamponade with a "small" pericardial effusion and superior vena cava syndrome.

In this article, we report a case of a previously healthy 11-year-old male who presented to our university hospital with a mediastinal mass, a left and right pleural effusion, and a small pericardial effusion of 5 mm, detected on computed tomography scan and echocardiography. On assessment, he had all the clinical features of superior vena cava syndrome and tamponade, including muffled heart sounds, tachycardia, and pulsus paradoxus. The patient developed increasing respiratory distress requiring tracheal intubation and mechanical ventilation, and despite drainage of his larger pleural effusion, continued to experience symptoms of respiratory distress. Finally, the small pericardial effusion was confirmed on echocardiography and drained after a clinical diagnosis of cardiac tamponade, leading to dramatic improvement in the patient's cardiovascular status. Curiously, on pericardiocentesis, much less fluid was obtained than expected for his presenting symptoms and clinical course.

Suture repair versus arrow repair for symptomatic meniscus tears of the knee: a systematic review.

A healthy meniscus is important for normal function of the knee. Numerous studies support that the repair of a torn meniscus is important to prevent degenerative changes in the knee. The ability to repair torn menisci is based on several factors including location, tear orientation, chronicity, and concomitant ligamentous knee injuries. In this systematic review, meniscal repair technology is evaluated. Specifically, the retear rates are compared between the arrow repair and the suture repair techniques. After searching three databases (PubMed, Cochrane Central Register of Controlled Trials, and Embase) and reviewing annual meeting abstracts from the American Orthopaedic Society for Sports Medicine (2005 to 2010), four studies (two observational and two randomized controlled trials) were selected for this systematic review. Due to the limited study number and variability between studies (study design, sample population, outcome measures, and surgical technique), a meta-analysis was not performed. The overall quality of the literature was poor and thus conclusions are limited. No clear superiority of one technique was determined by this review.