December 21, 2025Open Access

AI-Enabled Accurate Non-Invasive Assessment of Pulmonary Hypertension Progression via Multi-Modal Echocardiography

View Full Paper

Ask AI

Bookmark

To develop an AI model for more accurate assessment of pulmonary hypertension progression using non-invasive echocardiography.
Developed a vision-language model called MePH.
Constructed a large dataset of echocardiogram videos and spectral images.
Evaluated MePH against right heart catheterization data of 1,237 patients.
MePH reduced mean absolute error for mPAP and PVR by 49.73% and 43.81%, respectively.
Achieved an area under the curve of 0.921 in predicting pulmonary hypertension severity.
Demonstrated the ability to predict treatment efficacy for patients.

Discussion

No takes yet. Share an insight, caveat, or question.

AI-enabled assessment improves accuracy of pulmonary hypertension diagnosis and management, indicating benefits for healthcare management.

Yang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

AI-enabled assessment improves accuracy of pulmonary hypertension diagnosis and management, indicating benefits for healthcare management.