Product: Us2.v1 Company: Us2.ai
Artificial Intelligence-Based Echocardiography in Pulmonary Arterial Hypertension
Chest Journal, 2025
Abstract
BACKGROUND
Echocardiography is central when assessing pulmonary hypertension (PH), but manual interpretation can be time-consuming and prone to error.
RESEARCH QUESTION
Is a fully automated deep learning (DL) workflow in echocardiography reliable when assessing PH?
STUDY DESIGN AND METHODS
The study had two parts: the first determined the bias and precision of DL reads using Us2.ai software version 1.4.5 with core laboratory (CL) readers as the reference; the second assessed DL’s ability to discriminate milder PH in patients referred for right heart catheterization (mean pulmonary artery pressure [MPAP] between 20 and 35 mmHg). The first cohort (case-control) included 213 healthy individuals and 221 patients with pulmonary arterial hypertension (PAH). Parameters included peak tricuspid regurgitation velocity (TRV), right ventricular (RV) basal diameter, tricuspid annular plane systolic excursion (TAPSE), right atrial (RA) area, and RV fractional area change (RVFAC). The referral cohort included 196 patients, with 171 patients having measurable peak TRV signals. Robust measures of bias and precision were reported, and area under the curve (AUC) analysis assessed discrimination.
RESULTS
In patients with PAH, mean age was 48 years, 78% were female, and MPAP was 52 mmHg. No significant bias was observed for peak TRV (0.90%, -0.17 to 1.57), RA area (1.71%, 0.59 to 3.34), and TAPSE (1.28%, -0.51 to 3.18), while RVFAC exhibited a significant bias of 11.46% (8.43–14.74). For all measurements except RVFAC, robust percentile precision remained below 15%. In the case-control cohort, peak TRV had AUCs of 0. and 0.98 for CL and DL reads, respectively. The AUC for PH detection in the referral cohort was 0.79 for clinical laboratory reads and 0.75 for DL reads (p = 0.068).
INTERPRETATION
A fully automated DL workflow for echocardiography in PH is promising and likely to improve efficiency in clinical practice.
