Predicting Peritoneal Dialysis Failure Within the Next Three Months Based on Deep Learning and Important Features Analysis

Abstract

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.

Ähnliche Arbeiten