Predictive Nomogram for ICU Pressure Injury Deterioration: A Retrospective Study

278 ICU patients with Stage 1 pressure injuries were used to develop a predictive model. LASSO regression identified diabetes, maximum norepinephrine dose, and albumin level at admission as three independent predictors. The resulting nomogram achieved an AUC of 0.800 in the training set and 0.785 in the validation set.

Use Cases

• Developing risk stratification tools for ICU patients based on admission data
• Training logistic regression models for clinical outcome prediction
• Evaluating model performance using metrics like AUC and calibration
• Creating visual decision aids (nomograms) for clinical use

Strengths

• Model performance is validated with specific AUC scores (0.800 training, 0.785 validation)
• Predictors are clearly identified with odds ratios and confidence intervals
• Data split is defined (195 training, 83 validation patients)

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 very small (22.7 KB), suggesting limited scope

Provenance

Source

Author Chenyan Zhang, platform figshare

Collection Method

Retrospective cohort study of ICU patients

Freshness

Last updated 2026-05-18 05:47:44; freshness should be verified