Pulmonary hypertension often goes undiagnosed in part because of low suspicion and screening tools not being easily accessible. A deep learning study, published on the Journal of the American Heart Association, has developed a novel screening method for pulmonary hypertension using digital stethoscope recordings (phonocardiograms).
By analyzing approximately 6,000 PCG recordings with echocardiogram data, researchers created an algorithm that can detect elevated pulmonary artery systolic pressures with 71% sensitivity and 73% specificity.
The approach may offer a low-cost, non-invasive screening tool for early pulmonary hypertension detection, potentially addressing the challenge of undiagnosed cases.
Read more at this link on the Journal of the American Heart Association
Citation
Guo L, Khobragade N, Kieu S, Ilyas S, Nicely PN, Asiedu EK, Lima FV, Currie C, Lastowski E, Choudhary G. Development and Evaluation of a Deep Learning-Based Pulmonary Hypertension Screening Algorithm Using a Digital Stethoscope. J Am Heart Assoc. 2025 Feb 4;14(3):e036882. doi: 10.1161/JAHA.124.036882. Epub 2025 Feb 3. PMID: 39895552.
