Angioscopic Features for Aortic Dissection Characterization: A Single-Center Study

A single-center, cross-sectional observational pilot study includes data from 56 patients with aortic dissection and 444 control patients with coronary artery disease. The dataset likely contains classifications of 13 types of spontaneously ruptured aortic plaques and injuries (SRAPIs) analyzed using machine learning. The data was published by Satoru Takahashi on figshare under a CC-BY-4.0 license and was last updated on 2026-05-07.

Use Cases

• Training a classification model to identify aortic dissection based on angioscopic features like intramural blood and puff sign.
• Interpreting feature importance for clinical diagnosis using SHAP and Permutation Importance methods.
• Analyzing the structural relationships between different types of aortic injuries using network analysis.
• Validating findings from this pilot study in larger, multi-center research contexts.

Strengths

• Includes data from 500 total patients (56 cases, 444 controls).
• Features were analyzed using a Random Forest model with LASSO regression for feature selection.
• Results are interpreted using established methods (SHAP, Permutation Importance).

Limitations

• Row count and column-level documentation are unknown, which may limit suitability assessment.
• Data is from a single-center pilot study; the authors note a need for validation in larger multicenter studies.
• The dataset file is a DOCX document (1022.5 KB), suggesting the primary data may be embedded in a report rather than a structured data file.

Provenance

Source

figshare

Collection Method

Data collected via non-obstructive general angioscopy (NOGA) during a single-center, cross-sectional observational pilot study.

Freshness

Last updated 2026-05-07 05:44:26; freshness should be verified.