#1368 A practical approach for performing remote monitoring in the care of patients with automated peritoneal dialysis using Share source analytics 1.0
作者
Mauricio Sanabria,Peter A. Rutherford,Maria Paz Dazzarola,Juan Carlos Mario Castillo,Cesar Mauricio Doria,Jorge Pulido,Fabio Rojas,Javier Cely,Jasmin I. Vesga,Lady Alba,Angela Sofia Rivera
Abstract Background and Aims Remote monitoring programs for patients with automated peritoneal dialysis (APD-RMP) have been growing worldwide and lead to improved clinical outcomes. However, a lack of standardization has been observed regarding operating procedures and practical guides on how to use the program in the day-to-day life of PD services. This study aimed to describe the Sharesource Analytics 1.0 platform and generate decision rules for practical implementation in PD programs. Method This qualitative research was conducted in six renal clinics with APD-RMP that used the Sharesource Analytics 1.0 platform for three consecutive months between April and July 2024. Expert consensus techniques and focus groups with nephrologists and PD nurses were used to develop the decision rules in response to observations in the Sharesource Analytics 1.0 platform. Results Sharesource Analytics 1.0 is an efficient platform for APD-RMP programs. It employs analysis algorithms of key clinical indicators—patient adherence, catheter health, and alarms—presents on a daily basis with 180 day rolling trends (Fig. 1). A total of 27 professionals (20 women and seven men), including nephrologists and nurses, were part of the expert consensus and focus group. Twenty participants were over 40 years old, with a mean of 11.2 years (SD 8.2) of experience in peritoneal dialysis (PD) programs. Figure 2 shows how APD-RMP with Sharesource Analytics 1.0 was used in the clinic. Decision rules regarding adherence and catheter health were created by nephrologists and nurses and are shown in Table 1. Conclusion Sharesource Analytics 1.0 is a bidirectional tool that enables clinical teams to securely view patient care data and proactively reduce complications, hospitalizations, and emergency room visits. This study generated decision rules to help its implementation in clinical practice.