RESUMEN
INTRODUCTION: For mild to moderate male stress urinary incontinence (SUI), transobturator male slings remain an effective option for management. We aimed to use a machine learning (ML )-based model to predict those who will have a long-term success in managing SUI with male sling. METHODS: All transobturator male sling cases from August 2006 to June 2012 by a single surgeon were reviewed. Outcome of interest was defined as 'cure': complete dryness with 0 pads used, without the need for additional procedures. Clinical variables included in ML models were: number of pads used daily, age, height, weight, race, incontinence type, etiology of incontinence, history of radiation, smoking, bladder neck contracture, and prostatectomy. Model performance was assessed using area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1-score. RESULTS: A total of 181 patients were included in the model. The mean followup was 56.4 months (standard deviation [SD ] 41.6). Slightly more than half (53.6%, 97/181) of patients had procedural success. Logistic regression, K-nearest neighbor (KNN ), naive Bayes, decision tree, and random forest models were developed using ML. KNN model had the best performance, with AUROC of 0.759, AUPRC of 0.916, and F1-score of 0.833. Following ensemble learning with bagging and calibration, KNN model was further improved, with AUROC of 0.821, AUPRC of 0.921, and F-1 score of 0.848. CONCLUSIONS: ML-based prediction of long-term transobturator male sling is feasible. The low numbers of patients used to develop the model prompt further validation and development of the model but may serve as a decision-making aid for practitioners in the future.
RESUMEN
With the goal of establishing a new clinically-relevant bioscaffold format to enable the delivery of high densities of human adipose-derived stromal cells (ASCs) for applications in soft tissue regeneration, a novel "cell-assembly" method was developed to generate robust 3-D scaffolds comprised of fused networks of decellularized adipose tissue (DAT)-derived beads. In vitro studies confirmed that the assembly process was mediated by remodelling of the extracellular matrix by the seeded ASCs, which were well distributed throughout the scaffolds and remained highly viable after 8 days in culture. The ASC density, sulphated glycosaminoglycan content and scaffold stability were enhanced under culture conditions that included growth factor preconditioning. In vivo testing was performed to compare ASCs delivered within the cell-assembled DAT bead foams to an equivalent number of ASCs delivered on a previously-established pre-assembled DAT bead foam platform in a subcutaneous implant model in athymic nude mice. Scaffolds were fabricated with human ASCs engineered to stably co-express firefly luciferase and tdTomato to enable long-term cell tracking. Longitudinal bioluminescence imaging showed a significantly stronger signal associated with viable human ASCs at timepoints up to 7 days in the cell-assembled scaffolds, although both implant groups were found to retain similar densities of human ASCs at 28 days. Notably, the infiltration of CD31+ murine endothelial cells was enhanced in the cell-assembled implants at 28 days. Moreover, microcomputed tomography angiography revealed that there was a marked reduction in vascular permeability in the cell-assembled group, indicating that the developing vascular network was more stable in the new scaffold format. Overall, the novel cell-assembled DAT bead foams represent a promising platform to harness the pro-regenerative paracrine functionality of human ASCs and warrant further investigation as a clinically-translational approach for volume augmentation.
