Related Experiment Video
Updated: Jun 3, 2025
Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
Predicting mortality after transcatheter aortic valve replacement using AI-based fully automated left
Emese Zsarnoczay1, Akos Varga-Szemes2, U Joseph Schoepf2
1Department of Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, USA; Department of Radiology, Medical Imaging Centre, Semmelweis University, Budapest, Hungary.
Artificial intelligence (AI) automated assessment of left atrioventricular coupling index (LACI) independently predicts mortality in severe aortic stenosis patients undergoing TAVR. This AI tool offers valuable prognostic information beyond traditional risk factors.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Severe aortic stenosis (AS) patients undergoing transcatheter aortic valve replacement (TAVR) have complex risk profiles.
- Traditional risk factors may not fully capture mortality risk in these patients.
Purpose of the Study:
- To evaluate the incremental prognostic value of AI-derived left atrioventricular coupling index (LACI) in predicting mortality.
- To assess LACI's predictive performance compared to established risk factors in severe AS patients before TAVR.
Main Methods:
- Retrospective analysis of 656 severe AS patients who underwent coronary CT angiography (CCTA) before TAVR.
- AI software automatically calculated LACI from left atrial and ventricular volumes.
- Cox proportional hazard models were used to identify mortality predictors, adjusting for clinical factors and STS-PROM score.
Main Results:
- A LACI ≥43.7% independently predicted all-cause mortality (adjusted HR 1.52) after adjusting for clinical confounders.
- LACI remained a significant independent predictor even after adjustment for the STS-PROM score (adjusted HR 1.47).
- In patients with preserved left ventricular ejection fraction, LACI was also a significant predictor (adjusted HR 1.72).
Conclusions:
- AI-based automated LACI assessment provides independent prognostic information for mortality prediction in severe AS patients undergoing TAVR.
- This AI tool is valuable for risk stratification, including in patients with preserved left ventricular ejection fraction.
