Real-time treatment monitoring for patients receiving home-based peritoneal dialysis and prediction of heart failure risk: mHealth tools development and modeling study (Preprint)

Abstract

BACKGROUND Peritoneal dialysis is one of the major renal replacement modalities for end-stage renal disease patients. Heart failure is a common adverse event among peritoneal dialysis patients, especially for those who operate continuous ambulatory peritoneal dialysis (CAPD) at home because of the lack of professional input-output volume monitoring and management during treatment. OBJECTIVE This study aimed to develop novel mHealth tools to improve the quality of home-based CAPD treatment, and build prediction model of heart failure based on the systems’ daily treatment monitoring data. METHODS The mHealth tools with four-layer system were designed and developed using Spring Boot, MyBatis Plus, MySQL and Redis as back-end technology stack, and Vue, Element UI and Wechat Mini Program as front-end technology stack. Patients were recruited to use the tool during daily peritoneal dialysis treatment from January 1, 2017 to April 20, 2023. Logistic regression model based on the real-time treatment monitoring data were used for heart failure prediction. Sensitivity, specificity, accuracy and Youden index were calculated to evaluate the performance of the prediction model. RESULTS A WeChat Mini Program named Futou Bao for patients and a patients data management platform for doctors were developed. The Futou Bao included intelligent data upload function module and auxiliary function module. Four function modules made up the doctor’s data management platform, including patient management, data visualization and marking, data statistics and system management. During the study period, a total of 6635 peritoneal dialysis patients’ records were uploaded by Futou Bao with 0.71% of them (47 patients) occurring heart failure. The prediction model that included sex, age and diastolic blood pressure was considered as the optimal model, of which the sensitivity, specificity, accuracy and Youden index were 0.75, 0.91, 0.89 and 0.66, respectively, with an area under the curve (AUC) value of 0.879 (95%CI: 0.772-0.986) using the validation dataset. CONCLUSIONS This study provided a new home-based peritoneal dialysis management paradigm that realized the real-time monitoring and early warning of heart failure risk. This novel paradigm was of great value to improve the efficiency, security and personalization of peritoneal dialysis.