Inclusion and Exclusion Criteria for a CT-FFR Deep Learning Study on In-Stent Restenosis

A dataset containing the inclusion and exclusion criteria for a multicenter, prospective diagnostic study. The study, registered as ChiCTR2200058822, aims to establish a deep learning-based CT-FFR model for assessing in-stent restenosis, using invasive FFR as a reference standard. It was authored by Shiqi Liu and involves patient recruitment from Beijing Anzhen Hospital and six subcenters in China starting June 2022.

Use Cases

• Designing patient selection protocols for similar cardiac imaging studies based on the described criteria.
• Benchmarking AI model validation methodologies against the described multicenter, prospective trial design.
• Analyzing study recruitment strategies for deep learning applications in cardiology based on the planned enrollment of 331 patients.

Strengths

• Specific study design details are provided, including a multicenter, prospective approach and a target enrollment of 331 patients.
• Clear reference standard is defined (invasive FFR) for validating the deep learning-based CT-FFR model.
• Dataset is openly licensed under CC-BY-4.0.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), suggesting it contains only criteria lists or metadata, not the primary research data.

Provenance

Source

figshare, authored by Shiqi Liu.

Collection Method

Criteria defined for a prospective clinical study.

Time Range

Patient recruitment ongoing since June 2022.

Freshness

Last updated 2026-05-06 17:29:23; freshness should be verified.

Geography

Beijing Anzhen Hospital and six subcenters in China.