Search Results (2)

This study aims to develop a deep learning model to predict peritoneal dialysis (PD) failure within the next three months using data from the preceding three months. Background: PD patients typically perform treatments at home and visit the clinic only once per month, leading to significant gaps in clinical care and increased risks of PD failure, which may necessitate a transition to hemodialysis (HD). Current studies on PD patients largely focus on predicting PD failure, mortality risk, and hospitalization through traditional machine learning methods, with limited application of deep learning for this purpose. Methods: We collected comprehensive patient data, including demographic information, comorbidities, medication history, biochemical test results, dialysis prescriptions, and peritoneal equilibrium test outcomes. After preprocessing, we employed time-series deep learning models to train and make predictions. Results: The model achieved a prediction accuracy of 89% and an AUROC of 92%, outperforming previous methods used for PD failure prediction. Conclusion: This approach not only improves prediction accuracy but also identifies key features that can aid clinicians in developing more precise treatment plans and enhancing patient care. Full article

The water channel Aquaporin 1 (AQP1) plays a fundamental role in water ultrafiltration during peritoneal dialysis (PD) and its reduced expression or function may be responsible for ultrafiltration failure (UFF). In humans, AQP1 is expressed in the endothelium of the peritoneal capillaries but its expression in mesothelial cells (MC) and its functional role in PD is still being debated. Here, we studied a cohort of 30 patients using PD in order to determine the presence of AQP1 in peritoneal biopsies, AQP1 release in the PD effluent through exosomes and the correlation of AQP1 abundance with the efficiency of peritoneal ultrafiltration. The experiments using immunofluorescence showed a strong expression of AQP1 in MCs. Immunoblotting analysis on vesicles isolated from PD effluents showed a consistent presence of AQP1, mesothelin and Alix and the absence of the CD31. Thus, this suggests that they have an exclusive mesothelial origin. The immunoTEM analysis showed a homogeneous population of nanovesicles and confirmed the immunoblotting results. Interestingly, the quantitative analysis by ELISA showed a positive correlation between AQP1 in the PD effluent and ultrafiltration (UF), free water transport (FWT) and Na-sieving. This evidence opens the discussion on the functional role of mesothelial AQP1 during PD and suggests that it may represent a potential non-invasive biomarker of peritoneal barrier integrity, with predictive potential of UFF in PD patients. Full article