Prospective evaluation of an AI algorithm for real-time LVEF assessment in acute coronary syndrome using left coronary angiograms: the CathEF multicenter study
Bibliographic record
Abstract
Abstract Background Acute assessment of Left Ventricular Ejection Fraction (LVEF) is critical at time of percutaneous coronary intervention to optimize clinical management. The CathEF artificial intelligence algorithm offers a novel approach for real-time, intra-procedural LVEF assessment using routinely obtained left coronary artery angiograms without additional dye use[1]. Our objective was to evaluate the real-time application of the CathEF algorithm for LVEF measurement during coronary angiogram procedures in patients with acute coronary syndrome (ACS) and to compare its performance with transthoracic echocardiography (TTE) and left ventriculography. Methods The CathEF study is a prospective multi-center study that recruited ACS patients undergoing coronary angiography at two institutions from July 2022 to July 2023. Using the CathEF algorithm and the PACS-AI software, we analyzed 2 to 4 left coronary angiogram videos per procedure for LVEF assessment to compare to ventriculography (if indicated) and echocardiography performed during the same hospitalization. Operators were blinded to the CathEF AI-generated results. The primary measure was the algorithm's area under the receiving-operating characteristic curve (AUC) in identifying LVEF <40% or ≥40% compared to TTE-LVEF. Results 240 patients (32% female, average age 66 ± 12 years) were enrolled, with 207 undergoing TTE during index hospitalization (coronary angiogram to TTE mean delay of 0.8±6.3 days). The CathEF algorithm analyzed 881 coronary angiogram videos, averaging 3.12±1.66 per patient. Indications for angiography included unstable angina (18%), NSTEMI (47%), and STEMI (35%). The algorithm took under one minute to apply. CathEF’s performance yielded an AUC of 0.90 (95% CI, 0.840-0.96) and an MAE of 6.81% ± 0.43, with a Spearman correlation of 0.52. Conclusions This study provides proof-of-concept for prospective deployment of an AI algorithm at point-of-care with reliable LVEF measurement in real-time during ACS. This innovation holds the potential to ensure all ACS patients can receive prompt and appropriate care based on their LVEF.CathEF algorithm applied to an angiogramPACS-AI : Platform used to apply CathEF
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 | 0.010 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| 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".