Prognostic value of combined FFR-CT and quantitative plaque analysis in patients with new-onset stable angina: A seven-year follow-up analysis
Bibliographic record
Abstract
Abstract Background The prognostic value of combining fractional flow reserve derived from coronary CT angiography (FFR-CT) with artificial intelligence enabled coronary plaque analysis (AI-CPA) has not yet been fully uncovered. Purpose The purpose of this study was to investigate how the combined information derived from FFR-CT and AI-CPA, is associated with the long-term risk of cardiovascular death (CVD) and spontaneous myocardial infarction (MI) in patients with new-onset stable angina pectoris (SAP). Methods The study cohort consisted of consecutively enrolled patients with new-onset SAP at three Danish centres participating in the Assessing Diagnostic Value of Non-invasive FFR-CT in Coronary Care registry (ADVANCE-DK). All patients (n=841) had ≥1 coronary stenosis >30% verified on CTA with subsequent successful core laboratory FFR-CT and AI-CPA analysis. Mean follow-up time was 7.0 years (range: 6.3-8.2). An abnormal FFR-CT was defined as a lesion-specific (2cm distal-to-stenosis) value ≤0.80. AI-CPA was considered abnormal when patient level total plaque burden (total plaque volume mm^3/total vessel volume mm^3*100) was ≥ the 50%-percentile. Patients were divided into; 1) abnormal FFR-CT + abnormal AI-CPA, 2) abnormal FFR-CT + normal AI-CPA, 3) normal FFR-CT + abnormal AI-CPA and 4) normal FFR-CT + normal AI-CPA. The endpoint was a composite of CVD or non-fatal spontaneous MI. Event data were extracted from the Western Denmark Heart Registry and electronic hospital patient files. An external independent event committee adjudicated all events. Results In 841 patients, FFR-CT was abnormal in 347 (41%) and AI-CPA in 419 (50%). Overall, two normal test results were present in 305 (36%) patients, normal FFR-CT + abnormal AI-QCPA in 189 (22%), abnormal FFR-CT + normal AI-QCPA in 117 (14%) and two abnormal test results in 230 (27%). Baseline characteristics for patients within each group are provided in Table 1. During the follow-up, 69 endpoints occurred of which 35/69 (51%) were spontaneous MIs. Risk of the endpoint was lowest in the category of normal FFR-CT + normal AI-CPA with a significant positive trend towards higher risk if abnormal FFR-CT + normal AI-CPA or normal FFR-CT + abnormal AI-CPA followed by the highest risk observed for abnormal FFR-CT + abnormal AI-CPA, Figure 1. Conclusion In patients with new-onset SAP the combined information derived from FFR-CT and AI-CPA stratified patients into low (double normal), intermediate (one normal one abnormal) and high (double abnormal) risk of adverse outcomes. These findings indicate that FFR-CT and plaque-assessment provides independent and additive long-term prognostic information in patients with intermediate range coronary stenosis.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| 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".