Artificial Intelligence–based Coronary Stenosis Quantification at Coronary CT Angiography versus Quantitative Coronary Angiography
Bibliographic record
Abstract
Purpose To evaluate the performance of a new artificial intelligence (AI)–based tool by comparing the quantified stenosis severity at coronary CT angiography (CCTA) with a reference standard derived from invasive quantitative coronary angiography (QCA). Materials and Methods This secondary, post hoc analysis included 120 participants (mean age, 59.7 years ± 10.8 [SD]; 73 [60.8%] men, 47 [39.2%] women) from three large clinical trials (AFFECTS, P3, REFINE) who underwent CCTA and invasive coronary angiography with QCA. Quantitative analysis of coronary stenosis severity at CCTA was performed using an AI-based coronary stenosis quantification (AI-CSQ) software service. Blinded comparison between QCA and AI-CSQ was measured on a per-vessel and per-patient basis. Results The per-vessel AI-CSQ diagnostic sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 80%, 88%, 86%, 65%, and 94%, respectively, for diameter stenosis (DS) 50% or greater; and 78%, 92%, 91%, 47%, and 98%, respectively, for DS 70% or greater. The areas under the receiver operating characteristic curve (AUCs) to predict DS of 50% or greater and 70% or greater on a per-vessel basis were 0.92 (95% CI: 0.88, 0.95; P < .001) and 0.93 (95% CI: 0.89, 0.97; P < .001), respectively. The AUCs to predict DS of 50% or greater and 70% or greater on a per-patient basis were 0.93 (95% CI: 0.88, 0.97; P < .001) and 0.88 (95% CI: 0.81, 0.94; P < .001), respectively. Conclusion AI-CSQ at CCTA demonstrated a high diagnostic performance compared with QCA both on a per-patient and per-vessel basis, with high sensitivity for stenosis detection. Keywords: CT Angiography, Cardiac, Coronary Arteries Supplemental material is available for this article. Published under a CC BY 4.0 license.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.018 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".