Clinical and Laboratory Data for Predicting Occult Diabetic Kidney Disease

A dataset of 1,916 hospitalized patients with type 2 diabetes mellitus, used to develop a machine learning model for early detection of occult diabetic kidney disease. The data includes 32 routine clinical variables, with model development and validation performed across two hospital cohorts. The dataset was uploaded by Mengyu Zhang in April 2026.

Use Cases

• Training machine learning models for early disease detection based on routine clinical variables like HGB and HbA1c.
• Developing risk stratification systems for diabetic kidney disease based on quartile-based risk scores.
• Building interactive web-based calculators for real-time clinical risk assessment.
• Conducting feature importance analysis for clinical prediction using SHAP values.
• Validating predictive models on independent external cohorts from different hospitals.

Strengths

• Includes data from 1,916 patients across two hospital cohorts for derivation and validation.
• Model performance is reported with an AUC of 0.824 in training and 0.786 in external validation.
• The final predictive model uses eight interpretable features, including HGB, HbA1c, and uric acid.
• Risk stratification shows a clear gradient, with occult DKD incidence ranging from 1.5% to 55.8% across quartiles.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data file is unknown, which may limit suitability assessment.
• The dataset is stored as a 3.4 MB DOCX file, which may require format conversion for analysis.

Provenance

Source

Mengyu Zhang, via figshare.

Collection Method

Multicenter retrospective study collecting routine clinical and laboratory data from hospitalized patients.

Time Range

The study period is not specified in the provided metadata.

Freshness

Last updated 2026-04-27 04:11:26; freshness should be verified.

Geography

Data was collected from hospitals in China (Wanbei Coal-Electricity Group General Hospital and the First Affiliated Hospital of Anhui Medical University).