Factors Associated with In-Hospital Mortality in Acute COPD Exacerbations

Yang Liu's study retrospectively collected data from 425 patients with acute exacerbations of COPD (AECOPD). The dataset likely contains clinical variables used to build a logistic regression and nomogram model predicting in-hospital mortality. The model was validated on a subset of 127 patients.

Use Cases

• Predicting in-hospital mortality risk based on patient age, blood oxygen saturation, and lab values.
• Training logistic regression models for clinical outcome prediction using identified risk factors.
• Evaluating nomogram model performance via ROC and calibration curve analysis.
• Conducting decision curve analysis to assess the clinical utility of a predictive model.

Strengths

• The model achieved an AUC of 0.871 in the training set and 0.867 in the validation set, indicating good discrimination.
• The study identified four independent influencing factors for mortality: age, blood oxygen saturation, alanine aminotransferase, and C-reactive protein.
• Data from 425 patients were collected and split into a training set (298) and validation set (127) for model development.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The study is a single-center analysis, which may limit generalizability.

Provenance

Source

Yang Liu

Collection Method

Retrospective data collection from patients with AECOPD.

Freshness

Last updated 2026-05-07 04:44:24; freshness should be verified.