Longitudinal Validation of a Deep Learning Index for Aortic Stenosis Progression

  1. Jiesuck Park
  2. Jiyeon Kim
  3. Yeonyee E. Yoon
  4. Jaeik Jeon
  5. Seung-Ah Lee
  6. Hong-Mi Choi
  7. In-Chang Hwang
  8. Goo-Yeong Cho
  9. Hyuk-Jae Chang
  10. Jae-Hyeong Park
Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Background

Aortic stenosis (AS) is a progressive disease requiring timely monitoring and intervention. While transthoracic echocardiography (TTE) remains the diagnostic standard, deep learning (DL)-based approaches offer potential for improved disease tracking. This study examined the longitudinal changes in a previously developed DL-derived index for AS continuum (DLi-ASc) and assessed its value in predicting progression to severe AS.

Methods

We retrospectively analysed 2,373 patients (7,371 TTEs) from two tertiary hospitals. DLi-ASc (scaled 0-100), derived from parasternal long- and/or short-axis views, was tracked longitudinally. The median follow-up duration was 42.8 months (IQR 22.2–75.7 months).

Results

DLi-ASc increased in parallel with worsening AS stages (p for trend <0.001) and showed strong correlations with AV maximal velocity (V max ) (Pearson correlation coefficients [PCC] = 0.69, p<0.001) and mean pressure gradient (mPG) (PCC = 0.66, p<0.001). Higher baseline DLi-ASc was associated with a faster AS progression rate (p for trend <0.001). Additionally, the annualized change in DLi-ASc, estimated using linear mixed-effect models, correlated strongly with the annualized progression of AV V max (PCC = 0.71, p<0.001) and mPG (PCC = 0.68, p<0.001). In Fine-Gray competing risk models, baseline DLi-ASc independently predicted progression to severe AS, even after adjustment for AV V max or mPG (hazard ratio per 10-point increase = 2.38 and 2.80, respectively)

Conclusion

DLi-ASc increased in parallel with AS progression and independently predicted severe AS progression. These findings support its role as a non-invasive imaging-based digital marker for longitudinal AS monitoring and risk stratification.

CLINICAL PERSPECTIVE

What Is New?

  • This is the first study to validate longitudinal changes in a deep learning-derived index (DLi-ASc) for tracking aortic stenosis (AS) progression.

  • DLi-ASc increases consistently over time in parallel with worsening AS stages and conventional AS hemodynamic parameters.

  • Baseline DLi-ASc independently predicts future severe AS progression, even after adjusting for conventional hemodynamic parameters.

What Are the Clinical Implications?

  • DLi-ASc provides a quantitative, noninvasive digital marker for monitoring AS progression in routine clinical practice.

  • DLi-ASc enables individualized risk stratification and may inform tailored follow-up strategies for patients with AS.

  • DLi-ASc may serve as a surrogate marker for future studies evaluating therapeutic interventions to slow AS progression.

Article activity feed

  1. Version published to 10.1101/2025.02.17.25322392 on medRxiv