Data Sheet 1_Machine learning-based identification of inflammatory biomarkers for predicti

42 pediatric patient records from a retrospective case-control study conducted between January 2020 and December 2024. The data was used to identify lactate dehydrogenase (LDH), C-reactive protein (CRP), and erythrocyte sedimentation rate (ESR) as core inflammatory markers for predicting pulmonary consolidation via machine learning. An online risk assessment system built on these markers achieved an area under the curve of 0.993.

Use Cases

• Training predictive models for pulmonary consolidation based on LDH, CRP, and ESR levels.
• Validating feature selection methods like LASSO and SVM-RFE on small clinical datasets.
• Developing web-based clinical risk calculators using routine laboratory parameters.

Strengths

• Consensus validation across five machine learning algorithms identified three core biomarkers.
• The developed risk assessment system demonstrated high predictive performance with an AUC of 0.993.
• Bootstrap resampling validation with 1,000 iterations confirmed model robustness.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is small, with 88.5 KB total size, limiting the scope of analysis.

Provenance

Source

figshare

Collection Method

Retrospective case-control study.

Time Range

January 2020 to December 2024

Freshness

Last updated 2026-05-04 05:33:15; freshness should be verified.