Evaluating the Effectiveness of a Smart Screening and Tiered Management Tool for Diabetic Kidney Disease in Primary Care: A Cluster Randomized Trial

This is a cluster-randomized controlled trial aiming to evaluate the effectiveness of an intelligent standardized screening and risk-stratified management tool for diabetic kidney disease (DKD) among adults with type 2 diabetes in primary care settings.

Background China has a high prevalence of type 2 diabetes, and 30%-40% of diabetic patients develop DKD, the leading cause of end-stage kidney disease. Primary care facilities lack convenient, standardized digital tools to screen, grade and manage DKD systematically, leading to delayed detection and suboptimal kidney protection for diabetic patients. This study develops a localized intelligent DKD management system integrated into primary care electronic medical records (HIS) to solve this gap.

Study Design \& Participants

We will recruit 30 primary healthcare institutions (15 urban community health centers, 15 rural township health centers) across Longyou County, with at least 200 registered type 2 diabetes patients at each site. A total of 3,000 eligible adults aged 18-75 years diagnosed with type 2 diabetes will be enrolled, randomly assigned in a 1:1 cluster ratio to two groups:

Intervention group (15 sites, 1,500 patients): Receive the intelligent DKD screening and graded management plug-in embedded in local HIS. The tool automatically calculates estimated glomerular filtration rate (eGFR), generates DKD risk stratification, sends reminders for regular urine albumin creatinine ratio (UACR) testing, and provides individualized treatment, follow-up and referral guidance.

Control group (15 sites, 1,500 patients): Receive routine standard diabetes management following national primary care diabetes guidelines, without access to the intelligent DKD digital support system.

Study Procedures All participants complete a baseline screening visit (V1) to sign informed consent, review medical history, complete physical examinations, and undergo lab tests including UACR, serum creatinine, fasting blood glucose, glycated hemoglobin, lipid profile and urinalysis. Follow-up visits are scheduled at 3 months (V2), 6 months (V3), and 12 months (V4) after baseline, repeating physical checks and core laboratory testing. An optional extended observational follow-up continues until 24 months, with biospecimens collected and shipped to the central research laboratory for unified testing. Participants may withdraw voluntarily at any time without impact on routine clinical care, and unscheduled visits will be arranged if adverse events or abnormal lab results occur.

Key Study Outcomes Primary Outcome: Change in log-transformed urine albumin creatinine ratio (UACR) from baseline to the 12-month follow-up, comparing the two management models.

Secondary Outcomes: 12-month DKD screening rate, DKD diagnosis rate, standardized DKD treatment rate, and change in eGFR over 12 months. The study also assesses the operability of the intelligent management tool and patient treatment adherence in primary care.

Risks \& Benefits Potential Risks: Participants will undergo routine fasting blood draws and urine collection at each visit, which may cause minor temporary pain, bruising, or rare vasovagal reactions during venipuncture.

Benefits: All participants receive free regular DKD-related laboratory testing covered by the research team. Intervention group patients receive personalized, automated kidney risk management recommendations to slow DKD progression. Any study-related injury will receive free medical treatment and corresponding compensation from the research project.

Data Protection \& Ethics All participant personal information and biological samples are fully anonymized with unique study codes and stored in encrypted databases with restricted access. The study strictly complies with the Declaration of Helsinki, Chinese GCP, and domestic clinical research regulations. All participants provide written informed consent before enrollment, with full rights to withdraw at any stage without penalty. Study results will be published in peer-reviewed journals and presented at academic conferences to improve nationwide primary care DKD prevention and control.

Statistical Analysis All analyses will use intention-to-treat, modified intention-to-treat, per-protocol, and safety analysis datasets. Mixed models for repeated measures, t-tests, rank-sum tests, and Fisher's exact tests will be applied to compare between-group differences, with multiple imputation used to handle missing primary endpoint data. All adverse events will be coded using MedDRA and summarized to evaluate the safety profile of the intervention strategy.