Artificial Intelligence–Based Fully Automated Quantitative Coronary Angiography vs Optical Coherence Tomography–Guided PCI

doi:10.1016/j.jcin.2024.10.025

Coronary disease & ACSRandomised controlled trial

Artificial Intelligence–Based Fully Automated Quantitative Coronary Angiography vs Optical Coherence Tomography–Guided Percutaneous Coronary Intervention (PCI)

JACC Cardiovasc IntervPublished 30 Oct 2024

Randomised controlled trial
non-inferiority
multicentre (13 centres, South Korea)
1:1 randomisation

Read the original article ↗

Authors' conclusion

This study demonstrated the noninferiority of AI-QCA-assisted PCI to OCT-guided PCI in achieving MSA with comparable OCT-defined endpoints.

Study context

Population: Patients with significant CAD undergoing PCI395 analysed
Participants: 400 patients

Comparison: AI-QCA-assisted PCI vs optical coherence tomography (OCT)-guided PCI
AI-QCAn = 199
OCTn = 196reference
Primary endpoint: Post-PCI minimal stent area (MSA) assessed by OCT (non-inferiority margin 0.8 mm²)

Primary result

Post-PCI MSA

Difference

−0.16

95% CI −0.59 to 0.28

P < 0.001 for non-inferiority

By group

AI-QCA6.3± 2.2 · mm²

OCT6.2± 2.2 · mm²

AI-QCA vs OCT

difference −0.16 (95% CI −0.59 to 0.28); P for non-inferiority < 0.001

Non-inferiority margin 0.8 as printed, not drawn

As reported in the abstract

Further findings

Stent underexpansion (OCT-defined)

P = 0.48

AI-QCA50.8%

OCT54.6%

Dissection (OCT-defined)

P = 0.42

AI-QCA15.6%

OCT12.8%

Untreated reference segment disease (OCT-defined)

P = 0.61

AI-QCA15.1%

OCT13.3%

Outcome	AI-QCA	OCT	P value
Stent malapposition (OCT-defined) · higher with AI-QCA	13.6%	5.6	P = 0.007

Original publication

Artificial Intelligence–Based Fully Automated Quantitative Coronary Angiography vs Optical Coherence Tomography–Guided PCI. JACC Cardiovasc Interv. Published 30 October 2024. doi:10.1016/j.jcin.2024.10.025

Read the original article ↗PubMedCite RIS · BibTeX

Summarised from the published abstract; every number is checked against it