Prevention & lipids

Comparison of Artificial Intelligence-Driven Echocardiographic Assessment of Diastolic Function With the ASE Guidelines

JACC AdvPublished Comparison of a previously validated deep learning (DL) model with the 2016 ASE/EACVI and 2025 ASE guidelines

Authors' conclusion

In settings where not all guideline-recommended parameters are available, the DL model may improve prognostic and diagnostic performance compared with both guideline versions. Nevertheless, these exploratory findings require further validation to confirm that the observed advantages persist when all guideline-recommended parameters are systematically acquired.

Study context

Population
ARIC (Atherosclerosis Risk In Communities) cohort and hemodynamic validation cohorts from the United States and Japan, in which ≥1 guideline-recommended parameters were unavailable in a substantial proportion of patientsper cohort · ARIC cohort 5,450 · United States hemodynamic validation cohort 83 · Japanese hemodynamic validation cohort 130
Index test or model
DL model vs 2016 ASE/EACVI and 2025 ASE guidelines for diagnosing elevated left ventricular filling pressure (hemodynamic validation cohorts) and for prognostication (ARIC cohort)
Target condition
elevated left ventricular filling pressure
Methodological detailsexploratory, 3 cohorts: ARIC cohort for prognostication; 2 hemodynamic validation cohorts (United States, Japan) for diagnosis
  • Exploratory
  • 3 cohorts: ARIC cohort for prognostication; 2 hemodynamic validation cohorts (United States, Japan) for diagnosis

Performance

As reported in the abstract

Test or modelAUC
DL model0.879
2025 ASE guidelines0.822
2016 ASE/EACVI guidelines0.812

AUC

DL model0.879
2025 ASE guidelines0.822
2016 ASE/EACVI guidelines0.812
  • DL model vs 2025 ASE guidelines: P = 0.041 — higher AUC with DL model
  • DL model vs 2016 ASE/EACVI guidelines: P = 0.138 — similar AUC

Further findings

OutcomeDL model2016 ASE/EACVI guidelines2025 ASE guidelines
Prognostication, C-index — ARIC cohort
C-index0.6760.6380.602
Elevated left ventricular filling pressure, AUC — Japanese cohort
AUC0.8160.6940.634
  • Prognostication, C-index — ARIC cohort: DL model higher than both guidelines: both P < 0.001
  • Elevated left ventricular filling pressure, AUC — Japanese cohort: DL model higher than both guideline versions: both P < 0.05

Original publication

Comparison of Artificial Intelligence-Driven Echocardiographic Assessment of Diastolic Function With the ASE Guidelines. JACC Adv. Published September 2026. doi:10.1016/j.jacadv.2026.103115

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.