Three-Factor Nomogram Predicting Mechanical Ventilation in Preterm Infants

A clinical prediction model developed from a retrospective cohort of 1,059 preterm infants admitted between July 2023 and June 2024. The model uses three perinatal indicators to predict the need for invasive mechanical ventilation within 72 hours after birth. It was created by Li Guo and is available under a CC-BY-4.0 license.

Use Cases

• Validate predictive models for neonatal respiratory outcomes based on early clinical indicators.
• Benchmark logistic regression models for medical risk prediction based on Apgar scores and sepsis.
• Assess model calibration and decision curve analysis in clinical settings based on reported AUC and Brier scores.
• Study the interaction between pulmonary surfactant administration and sepsis in preterm infant outcomes.

Strengths

• Model was developed and validated on a cohort of 1,059 preterm infants.
• Achieved an AUC of 0.816 in the validation set with good calibration (Brier score 0.096).
• Parsimonious model uses only three predictors, enhancing potential for clinical implementation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is from a single-center retrospective study; external validation is noted as warranted.

Provenance

Source

figshare

Collection Method

Single-center retrospective cohort study.

Time Range

July 2023–June 2024

Freshness

Last updated 2026-04-29 05:57:19; freshness should be verified.