Cardiovascular-Kidney-Metabolic Syndrome Risk Prediction Model Data

Jiawen Tu developed a prediction model for Cardiovascular-Kidney-Metabolic syndrome progression using multicenter retrospective data. The model was validated on cohorts from 2016-2021 and achieved AUCs between 0.718 and 0.747. The dataset, last updated in March 2026, likely contains routine clinical indicators and new lipid-metabolism metrics.

Use Cases

• Training risk prediction models based on routine clinical indicators and lipid-metabolism metrics.
• Evaluating model discrimination and calibration using AUC and decision curve analysis.
• Analyzing the link between diabetes and metabolic dysfunction-associated steatotic liver disease (MASLD) on syndrome progression.
• Conducting subgroup analyses to confirm stable model performance across different clinical subgroups and centers.

Strengths

• Model validation across multiple cohorts (2016-2019, 2020, 2021) with AUCs reported.
• Dataset includes 21,026 participants with baseline CKM stages 1 or 2.
• Predicted-risk quartiles are provided (1.8%, 7.6%, 11.4%, 24.9%).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data is unknown, which may limit suitability assessment.
• The primary file format is DOCX, which may not be optimal for direct data analysis.

Provenance

Source

figshare

Collection Method

Multicenter retrospective study.

Time Range

Cohorts from 2016 to 2021.

Freshness

Last updated 2026-03-19 06:48:53