Radiol Cardiothorac Imaging June 2020 PMID 33778579

Value of Machine Learning-based Coronary CT Fractional Flow Reserve Applied to Triple-Rule-Out CT Angiography in Acute Chest Pain.

Simon S Martin, Domenico Mastrodicasa, Marly van Assen, Carlo N De Cecco, Richard R Bayer, Christian Tesche, Akos Varga-Szemes, Andreas M Fischer, Brian E Jacobs, Pooyan Sahbaee, L Parkwood Griffith, Andrew J Matuskowitz, Thomas J Vogl, U Joseph Schoepf

Download social card

Mentions

Peak: 10 in Jul 2020

across 3 sources since Jun 2020

Extended reach

113,448

potential audience

Total likes

Video views

Mentions per month

Jun 2020 – Apr 2024

Where it's discussed

X / Twitter13 posts
Facebook2 posts
YouTube1 videos

AI synopsis

What people are saying

The posts highlight how AI-based CT FFR can enhance emergency diagnostics and expand clinical applications, often using enthusiastic language like 'improve efficiency' and 'added value,' which demonstrates strong support and recognition of the significance of the study’s findings.

AgreementStrong agreement

The posts strongly support the publication, emphasizing its value and positivity towards the technological advancement.

InterestHigh interest

Discussions show high interest, with mentions of expanding applications and clinical value.

EngagementModerate engagement

While some posts are brief, others actively debate potential benefits, indicating moderate deep engagement.

ImpactHigh impact

The posts suggest that the research could significantly influence clinical practice, indicating high impact.

Abstract in brief

This study evaluates the usefulness of AI-based noninvasive CT-derived fractional flow reserve (CT FFR) from triple-ruleout coronary CT angiography in diagnosing acute chest pain in emergency settings, showing it may better predict revascularization and cardiac events than traditional stenosis assessment.
CT FFR demonstrated higher agreement with additional diagnostic tests and was a more reliable predictor for adverse cardiac outcomes over a 1-year follow-up compared to standard CT angiography findings.
The findings suggest that incorporating CT FFR can improve diagnostic accuracy, potentially reducing unnecessary tests and improving patient management for those experiencing acute chest pain.

Read the full abstract

All mentions

Machine Learning-Based CT FFR for Accurate Coronary Heart Disease Diagnosis

This episode discusses a study on AI-based noninvasive CT-derived fractional flow reserve (CT FFR) from triple-rule-out coronary CT angiography for diagnosing acute chest pain, showing improved predictive accuracy over…

Radiology: Cardiothoracic Imaging · Apr 4, 2024 20 views

Salvador Pedraza

@salvasapedraza · X

RT @radiology_rsna: AI-based CT FFR can improve the efficiency of patients assigned to triple-rule-out CTA in the emergency department. @MU…

Jul 24, 2020 · 5 shares · 6,514 followers View post →

Reira Espinosa

@reira_espinosa · X

RT @radiology_rsna: AI-based CT FFR can improve the efficiency of patients assigned to triple-rule-out CTA in the emergency department. @MU…

Jul 24, 2020 · 5 shares · 188 followers View post →

RAJ DAS

@dr_raj_das · X

RT @radiology_rsna: AI-based CT FFR can improve the efficiency of patients assigned to triple-rule-out CTA in the emergency department. @MU…

Jul 24, 2020 · 5 shares · 145 followers View post →

MUSC Health

@MUSChealth · X

RT @radiology_rsna: AI-based CT FFR can improve the efficiency of patients assigned to triple-rule-out CTA in the emergency department. @MU…

Jul 24, 2020 · 5 shares · 14,622 followers View post →

Radiology

@radiology_rsna · X

Jul 24, 2020 · 6 likes · 5 shares · 60,151 followers View post →

HubOfML

@hubofml · X