Surgical management of parastomal hernia following radical cystectomy and ileal conduit: A french multi-institutional experience.

BACKGROUND: Parastomal incisional hernia (PH) is a frequent complication following the creation of an ileal conduit (IC), and it can be a significant detriment to quality of life. The aim of this study was to evaluate outcomes of PH repair following IC for urinary diversion. METHOD: A multicenter retrospective study was conducted of 6 academic hospitals in France. The study's population included patients who underwent surgical treatment for parastomal hernia following IC creation from 2013 to 2021. RESULTS: Fifty-one patients were included in the study. Median follow up was 15.3 months. Eighteen patients presented with a recurrence (35%), with a median time to recurrence of 11.1 months. The vast majority of PH repair was performed through an open approach (88%). With regard to technique, Keyhole was the most reported technique (46%) followed by Sugarbaker (22%) and suture only (20%). The Keyhole technique was associated with a higher risk of recurrence compared to the Sugarbaker technique (52% vs 10%, p = 0.046). Overall, there was a 7.8% rate of major complications without a statistical difference between PH repair techniques for major complications. CONCLUSION: Surgical treatment of parastomal hernia following IC was associated with a high risk of recurrence. Novel surgical approaches to PH repair should be considered.

MonoNet: enhancing interpretability in neural networks via monotonic features.

Motivation: Being able to interpret and explain the predictions made by a machine learning model is of fundamental importance. Unfortunately, a trade-off between accuracy and interpretability is often observed. As a result, the interest in developing more transparent yet powerful models has grown considerably over the past few years. Interpretable models are especially needed in high-stake scenarios, such as computational biology and medical informatics, where erroneous or biased models' predictions can have deleterious consequences for a patient. Furthermore, understanding the inner workings of a model can help increase the trust in the model. Results: We introduce a novel structurally constrained neural network, MonoNet, which is more transparent, while still retaining the same learning capabilities of traditional neural models. MonoNet contains monotonically connected layers that ensure monotonic relationships between (high-level) features and outputs. We show how, by leveraging the monotonic constraint in conjunction with other post hoc strategies, we can interpret our model. To demonstrate our model's capabilities, we train MonoNet to classify cellular populations in a single-cell proteomic dataset. We also demonstrate MonoNet's performance in other benchmark datasets in different domains, including non-biological applications (in the Supplementary Material). Our experiments show how our model can achieve good performance, while providing at the same time useful biological insights about the most important biomarkers. We finally carry out an information-theoretical analysis to show how the monotonic constraint actively contributes to the learning process of the model. Availability and implementation: Code and sample data are available at https://github.com/phineasng/mononet. Supplementary information: Supplementary data are available at Bioinformatics Advances online.