Key point: The deep learning-based chest X-ray model for pulmonary hypertension detection, CXR-PH-Net, proved particularly sensitive in identifying in early-stage/mild pulmonary hypertension.
Researchers in China developed artificial intelligence programs that can analyze chest X-rays to detect pulmonary hypertension by training computer programs using chest X-rays from over 6,700 patients in Beijing hospitals, comparing those with and without pulmonary hypertension.
The artificial intelligence programs correctly identified pulmonary hypertension about 90% of the time from chest X-rays alone. They worked especially well for mild cases and younger, normal-weight patients.
These programs could potentially diagnose pulmonary hypertension without the need for invasive procedures.
Read more at this link
Originally published on Pulmonogy Advisor, 30 July 2025
Summary by Suzanne Lea, volunteer for the Alliance for Pulmonary Hypertension
Citation
Huang Z, Diao X, Huo Y, et al. Deep learning-enhanced noninvasive detection of pulmonary hypertension and subtypes via chest radiographs, validated by catheterization. Chest. Published online June 18, 2025. doi:10.1016/j.chest.2025.06.008