Why the study?
Can machine learning models accurately predict key haemodynamic parameters in patients with pulmonary arterial hypertension using routinely available non-invasive data?
Population
181 patients with invasively confirmed pulmonary arterial hypertension (PAH)
Design
Cohort
Key result
Machine learning models can estimate mean pulmonary arterial pressure (r=0.80) and pulmonary vascular resistance (r=0.71) from routine clinical data obtained prior to right heart catheterization.
Authors
Loading...
May support non-invasive mPAP/PVR estimation in PAH; hypothesis-generating and requires prospective validation before clinical use.
Observational (n=181)
Can machine learning models accurately predict key haemodynamic parameters in patients with pulmonary arterial hypertension using routinely available non-invasive data?
Effect estimate: r = 0.80 for mPAP; r = 0.71 for PVR
Machine learning models can estimate mean pulmonary arterial pressure and pulmonary vascular resistance from routine non-invasive clinical data in patients with confirmed PAH.
Kramer et al. (2025) conducted an observational in Pulmonary arterial hypertension (n=181). Machine learning models was evaluated on Prediction of mean pulmonary arterial pressure (mPAP) and pulmonary vascular resistance (PVR) (r = 0.80 for mPAP; r = 0.71 for PVR). Machine learning models can estimate mean pulmonary arterial pressure (r=0.80) and pulmonary vascular resistance (r=0.71) from routine clinical data obtained prior to right heart catheterization.