CT Histogram Measures for Predicting IPF Outcomes in 66 Patients

A 2026 study of 66 patients with idiopathic pulmonary fibrosis (IPF) analyzed CT scan attenuation histograms from inspiration and expiration. The dataset, created by Sarah C. Scharm, includes CT-derived histogram measures and baseline forced vital capacity (FVC%) used to model three-year outcomes of death/transplantation versus survival.

Use Cases

• Building logistic regression models to predict patient survival based on CT histogram skewness.
• Comparing the predictive performance of imaging biomarkers against traditional clinical measures like FVC%.
• Analyzing the correlation between CT-derived histogram measures and alveolar collapse in IPF.
• Conducting statistical tests (e.g., Mann-Whitney U) to assess differences in imaging features between patient subgroups.

Strengths

• Includes specific performance metrics for predictive models (AUC=0.793 for skewness model).
• Dataset is based on a clearly defined patient cohort (66 patients, mean age 69.5, 58 males).
• Study design is explicitly described as a single-center retrospective longitudinal analysis.

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 study, which may limit generalizability.

Provenance

Source

figshare, authored by Sarah C. Scharm.

Collection Method

Retrospective analysis of clinical CT scans from a single center.

Time Range

Observation period spans three years from baseline CT.

Freshness

Last updated 2026-03-17 17:29:22; freshness should be verified.

Geography

Geography is not specified in the provided description.