Predictive Nomogram for ICU Pressure Injury Deterioration

A retrospective study of 278 ICU patients with Stage 1 pressure injuries, split into training (n=195) and validation (n=83) sets, aimed to predict wound deterioration. The research, authored by Chenyan Zhang and last updated in May 2026, developed a logistic regression model visualized as a nomogram. The model uses three admission factors: diabetes status, maximum norepinephrine dose, and albumin level.

Use Cases

• Developing a clinical decision support tool based on the three identified risk factors (diabetes, norepinephrine dose, albumin).
• Validating predictive models for pressure injury progression using the reported AUC performance metrics (0.800 training, 0.785 validation).
• Benchmarking new ICU risk models against the published logistic regression approach and its nomogram visualization.
• Studying the association between specific clinical variables (e.g., vasopressor use, serum albumin) and pressure injury outcomes in critical care.

Strengths

• Model performance is quantitatively reported with AUC values (0.800 training, 0.785 validation) and confidence intervals.
• The study design includes a validation set (n=83) for assessing model generalizability.
• Predictors are clearly defined with odds ratios and confidence intervals (e.g., diabetes OR: 2.451; 95% CI: 1.139–5.274).

Limitations

• Row count is unknown, which may limit suitability assessment for large-scale model training.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (16.5 KB), indicating limited scope, likely containing only model parameters or summary statistics.

Provenance

Source

Chenyan Zhang

Collection Method

Retrospective cohort study of ICU patients.

Freshness

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