Key result
A 0D multicompartment model using scientific machine learning techniques estimated pulmonary arterial pressure from simulated non-invasive measurements with mean absolute percentage errors of 1.8% to 3.78%.
Why the study?
Reliable pulmonary arterial pressure quantification is essential across cardiovascular pathologies, but an accurate, routinely available non-invasive method remains elusive.
Can a 0D multicompartment model optimized with machine learning techniques accurately estimate pulmonary arterial pressure from simulated non-invasive measurements?
Can a 0D multicompartment model optimized with machine learning techniques accurately estimate pulmonary arterial pressure from simulated non-invasive measurements?
A novel computational model using machine learning and simulated non-invasive measurements can accurately estimate pulmonary arterial pressure, highlighting its potential for non-invasive diagnostic assessment.
No takes yet. Share an insight, caveat, or question.
Hypothesis-generating for non-invasive PAP estimation; requires prospective validation before clinical use.
Laubscher et al. (2022) studied Pulmonary hypertension and valvular heart disease. 0D multicompartment model optimized using scientific machine learning techniques was evaluated on Mean absolute percentage errors in estimating pulmonary arterial pressure. A 0D multicompartment model using scientific machine learning techniques estimated pulmonary arterial pressure from simulated non-invasive measurements with mean absolute percentage errors of 1.8% to 3.78%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: