Key result
Optimizing cardiovascular lumped parameter models via genetic algorithms achieves statistical equivalence with clinical data.
Effect estimate: r = 0.99997
p-value: p=<0.001
Combining sensitivity analysis and genetic algorithms improves the accuracy of parameter estimation in patient-specific cardiovascular lumped parameter models.
Advances patient-specific modeling research; leaves open clinical adoption pending prospective validation.
Parameter estimation poses a significant challenge in developing patient-specific cardiovascular models. This study presents a framework that enhances parameter estimation in lumped parameter cardiovascular models by combining sensitivity analysis for parameter selection with multi-objective genetic algorithm optimization. Four key parameters were identified as the most influential and subsequently optimized. Model outputs, specifically mean arterial pressure (MAP), were validated against clinical values from a public database. The optimized model’s MAP demonstrated a strong correlation with clinical MAP (r = 0.99997, p < 0.001), and a t-test analysis (p = 0.752) confirmed statistical equivalence with clinical data. This approach highlights the potential of sensitivity analysis and genetic algorithms to improve accuracy in patient-specific cardiovascular modelling.
No takes yet. Share an insight, caveat, or question.
Ali et al. (2025) studied this question. Sensitivity analysis and genetic algorithm optimization vs. Clinical values from a public database was evaluated on Mean arterial pressure (MAP) (r = 0.99997, p=<0.001). A framework combining sensitivity analysis and genetic algorithm optimization produced a cardiovascular model with mean arterial pressure strongly correlated to clinical data (r = 0.99997, p < 0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: