What question did this study set out to answer?

To develop and assess an artificial intelligence-derived radiotranscriptomic signature of coronary perivascular adipose tissue for enhanced cardiac risk prediction using coronary CT angiography.

August 7, 2019European Heart JournalOpen Access

A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography

View Full Paper

Ask AI

Bookmark

Why the study?

Does a novel AI-powered imaging biomarker (FRP) based on CCTA radiomic profiling of perivascular fat improve cardiac risk prediction compared to current state-of-the-art methods?

Key Points

To develop and assess an artificial intelligence-derived radiotranscriptomic signature of coronary perivascular adipose tissue for enhanced cardiac risk prediction using coronary CT angiography.
Extracted coronary CT angiography (CCTA)-based radiomic profiles from coronary artery perivascular adipose tissue (PVAT).
Applied machine learning to generate a novel radiotranscriptomic imaging biomarker (fat radiomic profile, or FRP) targeting structural remodeling beyond vascular inflammation.
PVAT radiomic profiling successfully identified perivascular structural remodeling linked to coronary artery disease independently of inflammation.
The AI-derived FRP biomarker demonstrated a striking qualitative improvement in cardiac risk prediction over current state-of-the-art diagnostic standards.

Structured PICO

Does a novel AI-powered imaging biomarker (FRP) based on CCTA radiomic profiling of perivascular fat improve cardiac risk prediction compared to current state-of-the-art methods?

Population

Patients undergoing coronary CT angiography (CCTA) for cardiac risk prediction

Intervention

Artificial intelligence (AI)-powered imaging biomarker (FRP) using CCTA-based radiomic profiling of coronary artery perivascular adipose tissue (PVAT)

Comparator

Current state-of-the-art cardiac risk prediction methods

Outcome

Improvement of cardiac risk predictionsurrogate

A novel AI-derived radiotranscriptomic signature of perivascular fat on CCTA improves cardiac risk prediction beyond current standard methods.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

May enhance CCTA-based risk stratification; leaves open whether FRP alters management or outcomes in prospective trials.

Cite This Study

Oikonomou et al. (2019) studied this question.

synapsesocial.com/papers/69d56ee475589c71d767d76d https://doi.org/10.1093/eurheartj/ehz592

Topics

Coronary artery disease Coronary CT angiography

View Full Paper

Ask AI

Bookmark

A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography

Key Points

Structured PICO

Discussion

Implication

Cite This Study

Topics

A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography

Key Points

Structured PICO

Discussion

Implication

Cite This Study

Keep reading

Topics

Keep reading