Impact of Artificial Intelligence-Enhanced Optical Coherence Tomography Software on Percutaneous Coronary Intervention Decisions
Bibliographic record
Abstract
Background Integration of intravascular imaging into percutaneous coronary intervention (PCI) workflow demands physician time and expertise. Artificial intelligence (AI)-enabled software that automates the identification of key intravascular imaging parameters has the potential to streamline physician workflow, increase accuracy, and reduce variability in PCI planning decisions. This study investigated if AI-enabled software, Ultreon (Abbott), compared with traditional software, AptiVue (Abbott), improved physician decision-making accuracy, variability, and efficiency in optical coherence tomography (OCT)-based PCI planning. Methods In this multireader, multicase study, 30 interventional cardiologists of varying OCT imaging experience evaluated 21 pre-PCI OCT pullbacks using both Ultreon and AptiVue platforms. Physician PCI planning decisions about lesion morphology, length, and diameter were compared to published best practices. Decision accuracy, variability, and time efficiency were assessed using statistical models. Results Physician OCT-based planning decisions were more accurate using Ultreon compared to AptiVue in the identification of calcium severity by 1.77 (95% CI, 1.27-2.50; P < .001), vessel preparation strategy by 2.00 (95% CI, 1.12-3.4; P = .018), and stent diameter by 2.83 (95% CI, 1.79-4.50; P < .001). Physicians exhibited less variability in assessments using Ultreon, especially for distal and proximal stent landing zone, and planned stent length ( P < .0001). The efficiency of OCT assessments was improved with Ultreon, reducing the duration of OCT assessments by 0.5 minutes ( P < .0001). The benefits were observed irrespective of the physician's prior OCT experience. Conclusions Physician OCT-based PCI planning decisions were more accurate, less variable, and more efficient with AI-enhanced Ultreon software. This could potentially aid in the fuller adoption of intravascular imaging in PCI workflow.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.324 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".