Evaluating AI-Gatekeeper Software in Coronary Artery Stenosis Screening: a Multicenter RCT

INFINITT Healthcare450 enrolled

Overview

The purpose of this study is to determine the efficacy, safety, and cost-effectiveness of AI-Gatekeeper software to assist clinicians in the diagnosis of coronary artery disease by predicting coronary artery stenosis (≥50%) from a multimodal AI technology that integrates clinical risk factors and baseline blood tests, including chest X-ray, electrocardiogram, and echocardiogram, in patients with suspected coronary artery disease (coronary stenosis).

Coronary artery disease (CAD) is a leading cause of global mortality, accounting for over 50% of heart disease-related deaths. Initial evaluations for CAD typically involve chest X-rays, electrocardiograms (ECG), risk factor assessments, and basic blood tests. However, these primary tests can't conclusively diagnose CAD. When CAD is suspected, coronary CTA (CCTA) or invasive coronary angiography (ICA) is performed, determining the need for procedures like stenting or revascularization. Interestingly, over 50% of patients undergoing CCTA or ICA don't require treatment, as CAD is either absent or not severe enough. This leads to unnecessary procedures and significant healthcare costs. For instance, in the U.S., the cost of unnecessary ICAs reaches billions annually, with similar trends in South Korea. AI-Gatekeeper software assists clinicians in diagnosing coronary artery disease by predicting coronary artery stenosis (≥50%) using multimodal AI technology. It integrates clinical risk factors and baseline blood tests, including chest X-ray, electrocardiogram, and echocardiogram, in patients with suspected coronary artery disease The purpose of this study is to determine the efficacy, safety, and cost-effectiveness of the AI-Gatekeeper software in a prospective, multicenter, randomized control trial.

Study Type

INTERVENTIONAL

Allocation

RANDOMIZED

Purpose

DIAGNOSTIC

Masking

NONE

Enrollment

450

Conditions

Coronary Artery Disease Diagnosis

Interventions

Assisted by the AI-Gatekeeper software groupDIAGNOSTIC_TEST

The group will be received a AI-Gatekeeper software report on the probability of having coronary artery stenosis (≥50%) based on the routine test.

Eligibility

Sex: ALLMin age: 19 YearsMax age: 80 Years

Medical Language ↔ Plain English

Inclusion Criteria: * A patient with symptoms such as chest pain suggestive of coronary artery disease, who underwent routine evaluations including blood tests, electrocardiogram, chest X-ray, and echocardiography * Low to Intermediate risk of pretest probabilities of obstructive CAD * Voluntarily agreed to participate in this clinical trial and signed the written consent form Exclusion Criteria: * Acute chest pain (in patients who have not been ruled out for ACS) * Previously diagnosed and treated coronary artery disease (myocardial infarction, PCI, CABG) * Patients with a life expectancy of less than 2 years due to conditions other than heart disease * Those who have not consented to the protocol * Participated in a drug or medical device clinical trial within the last 3 months * Pregnant or lactating women * Allergic to iodine preparations * Serum creatine level greater than 1.5 mg/dL or eGFR less than 30 mL/min * Baseline irregular and uncontrolled heart rhythm * Heart rate greater than 100 beats/minute * Systolic blood pressure of 90 mm Hg or less * Contraindications to beta blockers or nitroglycerin * Patients with complex congenital heart disease * Body mass index greater than or equal to 35

Locations (5)

Soonchunhyang University Bucheon Hospital

Bucheon-si, Gyeonggi-do, South Korea

Seoul National University Bundang Hospital

Seongnam-si, Gyeonggi-do, South Korea

Yongin Severance Hospitall, Yonsei University College of Medicine

Yongin, Gyeonggi-do, South Korea

Catholic Kwandong University International St. Mary's Hospital

Incheon, South Korea

Outcomes

Primary Outcomes

MACE (major adverse cardiovascular events)

All-cause death, non-fatal MI, stroke, admission due to acute coronary syndrome

Time frame: 24 weeks

Unnecessary utilization of advanced cardiac imaging

Defined as either (1) confirmation of non-significant coronary artery disease (stenosis ≤50%) by advanced cardiac imaging (CCTA or ICA) or (2) incorrect prediction of significant CAD by the AI-Gatekeeper software.

Time frame: 24 weeks

Secondary Outcomes

Comparison of total healthcare costs

This analysis focuses on comparing the overall financial impact of different healthcare interventions or treatments. It encompasses all associated expenses, from diagnostic procedures to treatment and follow-up care, providing a comprehensive assessment of the economic burden on the healthcare system.

Time frame: 24 weeks

Proportion of subjects classified as positive by the AI-Gatekeeper model analysis who are diagnosed with coronary artery stenosis (≥50%)

This measure assesses the accuracy of the AI-Gatekeeper model in identifying patients with coronary artery stenosis of 50% or greater among those it classifies as positive.

Time frame: 24 weeks

Proportion of subjects identified as negative by the AI-Gatekeeper model who are confirmed to have non-significant stenosis (<50%)

This measure assesses the accuracy of the AI-Gatekeeper model in identifying patients with non-significant coronary artery stenosis (\<50%) among those it classifies as negative.

Time frame: 24 weeks

Comparison of changes in angina symptom score

This comparison evaluates the variation in patients' angina symptoms severity and frequency as measured by the Seattle Angina Questionnaire (SAQ), a standardized tool for assessing chest pain related to heart conditions.

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.