Machine learning modeling of lung mechanics: Assessing the variability and propagation of uncertainty in respiratory-system compliance and airway resistance

Simple item page
dc.article.number107888
dc.catalogadorgjm
dc.contributor.authorBarahona Yáñez, José Miguel
dc.contributor.authorSahli Costabal, Francisco
dc.contributor.authorHurtado Sepúlveda, Daniel
dc.date.accessioned2024-05-30T16:23:23Z
dc.date.available2024-05-30T16:23:23Z
dc.date.issued2024
dc.description.abstractBackground and Objective: Traditional assessment of patient response in mechanical ventilation relies on respiratory-system compliance and airway resistance. Clinical evidence has shown high variability in these parameters, highlighting the difficulty of predicting them before the start of ventilation therapy. This motivates the creation of computational models that can connect structural and tissue features with lung mechanics. In this work, we leverage machine learning (ML) techniques to construct predictive lung function models informed by non-linear finite element simulations, and use them to investigate the propagation of uncertainty in the lung mechanical response. Methods: We revisit a continuum poromechanical formulation of the lungs suitable for determining patient response. Based on this framework, we create high-fidelity finite element models of human lungs from medical images. We also develop a low-fidelity model based on an idealized sphere geometry. We then use these models to train and validate three ML architectures: single-fidelity and multi-fidelity Gaussian process regression, and artificial neural networks. We use the best predictive ML model to further study the sensitivity of lung response to variations in tissue structural parameters and boundary conditions via sensitivity analysis and forward uncertainty quantification. Codes are available for download at https://github.com/comp-medicine-uc/ML-lung-mechanics-UQ. Results: The low-fidelity model delivers a lung response very close to that predicted by high-fidelity simulations and at a fraction of the computational time. Regarding the trained ML models, the multi-fidelity GP model consistently delivers better accuracy than the single-fidelity GP and neural network models in estimating respiratory-system compliance and resistance. In terms of computational efficiency, our ML model delivers a massive speed-up of with respect to high-fidelity simulations. Regarding lung function, we observed an almost matched and non-linear behavior between specific structural parameters and chest wall stiffness with compliance. Also, we observed a strong modulation of airways resistance with tissue permeability. Conclusions: Our findings unveil the relevance of specific lung tissue parameters and boundary conditions in the respiratory-system response. Furthermore, we highlight the advantages of adopting a multi-fidelity ML approach that combines data from different levels to yield accurate and efficient estimates of clinical mechanical markers. We envision that the methods presented here can open the way to the development of predictive ML models of the lung response that can inform clinical decisions.
dc.format.extent14 páginas
dc.fuente.origenORCID
dc.identifier.doi10.1016/j.cmpb.2023.107888
dc.identifier.urihttps://doi.org/10.1016/j.cmpb.2023.107888
dc.identifier.urihttp://www.scopus.com/inward/record.url?eid=2-s2.0-85176296662&partnerID=MN8TOARS
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/86067
dc.information.autorucEscuela de Ingeniería; Barahona Yáñez, José Miguel; S/I; 1217288
dc.information.autorucEscuela de Ingeniería; Sahli Costabal, Francisco; S/I; 154857
dc.information.autorucEscuela de Ingeniería; Hurtado Sepúlveda, Daniel; 0000-0001-6261-9106; 3569
dc.language.isoen
dc.nota.accesocontenido parcial
dc.revistaComputer Methods and Programs in Biomedicine
dc.rightsacceso restringido
dc.subjectLung modeling
dc.subjectRespiratory mechanics
dc.subjectMachine learning
dc.subjectMulti-fidelity Gaussian process
dc.subjectSensitivity analysis
dc.subjectUncertainty quantification
dc.subject.ddc600
dc.subject.deweyTecnologíaes_ES
dc.titleMachine learning modeling of lung mechanics: Assessing the variability and propagation of uncertainty in respiratory-system compliance and airway resistance
dc.typeartículo
dc.volumen243
sipa.codpersvinculados1217288
sipa.codpersvinculados154857
sipa.codpersvinculados3569
sipa.trazabilidadORCID;2024-05-27
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Machine learning modeling of lung mechanics - Assessing the variability and propagation of uncertainty in respiratory-system compliance and airway resistance.pdf
Size:
3.13 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas