Development and Validation of a Machine Learning Model for Differentiating Diabetic Kidney Disease and Non-Diabetic Kidney Disease in Type 2 Diabetes

NCT07672639 | Completed DMC

• 1 other identifier: TREC2022-KY126
• Study Type: observational
• Target: 2,201
• Locations: 1 country
• Sites: 1

Brief Summary

This multicenter retrospective observational study aims to develop and validate an interpretable machine learning model for differentiating diabetic kidney disease (DKD) from non-diabetic kidney disease (NDKD) in patients with type 2 diabetes mellitus. Clinical, laboratory, and pathological data from biopsy-confirmed patients were collected from 14 medical centers in China. Multiple machine learning algorithms were evaluated and externally validated. The final model was implemented as a web-based clinical decision support tool.

Conditions

Diabetic Kidney Disease; Type 2 Diabetes; Chronic Kidney Disease

Outcome Measures

Primary Outcomes (1)

• Diagnostic classification of DKD versus NDKD

  Pathological diagnosis based on kidney biopsy findings.

  During procedure

Secondary Outcomes (4)

• Area under the receiver operating characteristic curve (AUC)

  Through study completion (December 2024)

• Sensitivity (%)

  Through study completion (December 2024)

• Specificity (%)

  Through study completion (December 2024)

• Accuracy (%)

  Through study completion (December 2024)

Eligibility Criteria

• Age: 18 Years - 70 Years
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consisted of adults aged 18-70 years with type 2 diabetes mellitus who underwent clinically indicated kidney biopsy at 14 medical centers in China. Participants were identified retrospectively from biopsy records between January 2019 and December 2022. Patients with definitive pathological diagnoses of diabetic kidney disease (DKD) or non-diabetic kidney disease (NDKD) and available clinical data were included in model development. An independent cohort of biopsy-confirmed patients enrolled between January 2022 and December 2024 was used for external validation.

You may qualify if:

• Age 18-70 years
• Diagnosis of type 2 diabetes mellitus according to ADA criteria
• Underwent kidney biopsy
• Definitive pathological diagnosis available
• Availability of required clinical and laboratory data

You may not qualify if:

• Type 1 diabetes mellitus
• Secondary diabetes
• Missing key clinical data
• Non-diagnostic kidney biopsy
• Incomplete pathological information

Sponsors & Collaborators

• Beijing Tongren Hospital: lead

Study Sites (1)

Beijing Tongren Hospital

Beijing, Beijing Municipality, 100730, China

Location

MeSH Terms

Conditions

Diabetic Nephropathies; Diabetes Mellitus, Type 2; Renal Insufficiency, Chronic

Condition Hierarchy (Ancestors)

Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases; Diabetes Complications; Diabetes Mellitus; Endocrine System Diseases; Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases; Renal Insufficiency; Chronic Disease; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 15, 2026
• First Posted: June 29, 2026
• Study Start: January 1, 2019
• Primary Completion: December 1, 2022
• Study Completion: December 1, 2024
• Last Updated: June 29, 2026

Record last verified: 2026-06

Locations

CN (1)