Data Sheet 2_Exploratory machine learning analysis to characterize angioscopic features as

56 patients with aortic dissection and 444 control patients with coronary artery disease underwent non-obstructive general angioscopy (NOGA). The study, authored by Satoru Takahashi and published on figshare in 2026, used machine learning to analyze 13 types of spontaneously ruptured aortic plaques and injuries (SRAPIs). A Random Forest classification model with LASSO feature selection was interpreted using SHAP and Permutation Importance.

Use Cases

• Developing classification models for aortic dissection based on angioscopic features like intramural blood and puff sign.
• Interpreting feature importance in medical diagnostics using SHAP and Permutation Importance methods.
• Analyzing the pathophysiological relevance of specific aortic injuries such as salmon-pink appearance and fissure bleeding.
• Conducting network analysis to compare structural relationships between patient groups.

Strengths

• Includes data from 500 total patients (56 cases, 444 controls).
• Analyzes 13 distinct types of spontaneously ruptured aortic plaques and injuries (SRAPIs).
• Employs multiple machine learning interpretation techniques (SHAP, Permutation Importance).

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, cross-sectional pilot study; findings require validation in larger multicenter studies.

Provenance

Source

Satoru Takahashi via figshare.

Collection Method

Single-center, cross-sectional observational pilot study using non-obstructive general angioscopy (NOGA).

Freshness

Last updated 2026-05-07 05:44:25; freshness should be verified.