Kawasaki Disease Coronary Artery Lesion Risk Model, 2016-2022

A retrospective study of 2,481 pediatric Kawasaki disease patients admitted to the Children’s Hospital of Soochow University between July 2016 and December 2022. The dataset was used to develop a nomogram model predicting long-term coronary artery lesion risk one year after diagnosis. The model, authored by Qianzi Ge, achieved an AUC of 0.801 in the training dataset.

Use Cases

• Developing clinical risk prediction models based on patient demographics, laboratory results, and hospitalization data.
• Validating logistic regression models for pediatric cardiology outcomes using metrics like AUC, sensitivity, and specificity.
• Analyzing the relationship between factors like prolonged fever, hyponatremia, and decreased hemoglobin with long-term coronary artery lesion risk.
• Benchmarking new predictive algorithms against a published nomogram model for Kawasaki disease.

Strengths

• Contains data from 2,481 pediatric patients, providing a substantial sample size for model development.
• Model performance is quantitatively reported with an AUC of 0.801 in training and 0.796 in validation, along with sensitivity and specificity metrics.
• Data spans a 6.5-year period (July 2016 to December 2022), offering a contemporary longitudinal view.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count within the supplementary file is unknown, which may limit suitability assessment.
• Data is sourced from a single hospital, which may limit generalizability to other populations.

Provenance

Source

Children’s Hospital of Soochow University.

Collection Method

Retrospective analysis of clinical data, laboratory tests, echocardiographic findings, and follow-up information.

Time Range

July 2016 to December 2022.

Freshness

Last updated 2026-05-28 05:58:09; freshness should be verified.

Geography

Likely Suzhou, Jiangsu, China (based on hospital location).