JMIR Publications

ABSTRACT

Background:

Chronic kidney disease (CKD) is a significant public health concern, with an escalating global prevalence ranging from 11% to 13%. Therefore, practical strategies for slowing CKD progression and improving patient outcomes are imperative. There is limited evidence to substantiate the efficacy of mobile app-based nursing systems for decelerating CKD progression.

Objective:

This study aimed to evaluate the long-term efficacy of the KidneyOnline intelligent care system in slowing the progression of non-dialysis-dependent CKD.

Methods:

In this retrospective study, the KidneyOnline app was utilized for CKD patients in China who were registered between January 2017 and April 2023. Patients were divided into two groups: an intervention group using the app's nurse-led, patient-oriented management system and a conventional care group that didn't use the app. Patients' uploaded health data underwent processing via deep learning optical character recognition, and the AI system provided personalized healthcare plans and interventions. Conversely, the conventional care group received suggestions from nephrologists during regular visits without AI assistance. Monitoring extended for an average duration of 2.1 years post-recruitment, with the study’s objective being to assess the app's effectiveness in preserving kidney function. The primary outcome was the eGFR slope over the follow-up period, and secondary outcomes included changes in albumin-to-creatinine ratio (ACR) and mean arterial pressure (MAP).

Results:

A total of 12297 eligible patients who registered on the KidneyOnline app from January 2017 to April 2023 were enrolled for the analysis. Among them, 808 patients were successfully matched using 1:1 propensity score matching, resulting in 404(50%) patients in the KidneyOnline care system group and another 404(50%) patients in the conventional care group. The eGFR slope in the KidneyOnline care group was significantly lower than the conventional care group (-1.3 mL/min/1.73m2 per year vs -2.8 mL/min/1.73m2 per year, P=0.009). Subgroup analysis revealed that the effect of the KidneyOnline care group was more significant in males, patients over 45 years old, and patients with worse baseline kidney function, higher blood pressure, and heavier proteinuria. During the follow-up period, the MAP of KidneyOnline patients was significantly lower and remained stable(P<0.001)). The average ACR in both groups decreased, with the KidneyOnline care group showing a more significant reduction after 3 and 6 months (P=0.074, 0.027)); however, there was no significant difference in ACR between the two groups at the end of the follow-up period (P=0.904).

Conclusions:

The utilization of KidneyOnline, an AI-based, nurse-led, patient-centered care system, may be beneficial in slowing the progression of non-dialysis-dependent CKD.