MIS-C Severity Score Models for Pediatric ICU Admission in Ukraine

A retrospective cohort study of 51 children aged 7 months to 17 years with confirmed MIS-C. The dataset contains two resource-adapted prognostic models for predicting severe outcomes requiring PICU admission, developed by N. Y. Bodnarchuk-Sokhatska and last updated in March 2026. The models are based on clinical and laboratory predictors like hepatomegaly, ESR, IL-6, and multi-system involvement.

Use Cases

• Validate prognostic models for MIS-C severity based on clinical predictors like hepatomegaly and ESR.
• Compare performance of basic versus advanced clinical scoring systems based on resource availability.
• Benchmark machine learning models for pediatric ICU admission prediction against established clinical scores.

Strengths

• Models show high predictive performance, with the advanced model achieving an AUC of 0.936.
• Includes two distinct, resource-adapted models (Basic and Advanced) for different healthcare settings.
• Data is openly licensed under CC-BY-4.0.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Dataset is very small at 18.2 KB, indicating limited scope.

Provenance

Source

figshare

Collection Method

Retrospective cohort study using multivariable logistic regression and internal bootstrap validation.

Time Range

Study period not specified; data reflects MIS-C cases in Ukraine.

Freshness

Last updated 2026-03-18 07:42:05; freshness should be verified.

Geography

Ukraine