Daniel E. Hurtado

Introduction: Digital twins of the respiratory system have shown promise in predicting the patient-specific response of lungs connected to mechanical ventilation. However, modeling the spatiotemporal response of the lung tissue through high-fidelity numerical simulations involves computing times that largely exceed those required in clinical applications. In this work, we present a multi-fidelity deep learning surrogate model to efficiently and accurately predict the poromechanical fields that arise in lungs connected to mechanical ventilation.Methods: We generate training datasets with two fidelity levels from non-linear finite-element simulations on coarse (low-fidelity) and fine (high-fidelity) discretizations of the lungs domain. Further, we reduce the output spatiotemporal dimensionality using singular value decomposition, capturing over 99% of the variance in both displacement and alveolar pressure fields with only a few principal components. Based on this procedure, we learn both the input-output mappings and fidelity correlations by training a reduced-order multi-fidelity neural network model (rMFNN) that leverages the abundant low-fidelity data to enhance predictions from scarce high-fidelity simulations.Results: Compared to a reduced-order single-fidelity neural network (rSFNN) surrogate, the rMFNN achieves superior predictive accuracy in predicting spatiotemporal displacement and alveolar pressure fields (R² ≥ 93% (rMFNN) vs R² ≥ 75% (rSFNN)). In addition, we show that rMFNN outperforms rSFNN in terms of accuracy for the same level of training cost. Further, the rMFNN model provides inference times of less than a minute, offering speed-ups up to 462× when compared to finite-element numerical simulations.Discussion: These results demonstrate the potential of the rMFNN lung model to enable patient-specific predictions in acceptable computing times that can be used to personalize mechanical ventilation therapy in critical patients.

Ventilatory thresholds (VTs) are key physiological parameters used to evaluate physical performance and determine aerobic and anaerobic transitions during exercise. Current assessment of these parameters requires ergospirometry, limiting evaluation to laboratory or clinical settings. In this work, we introduce a wearable respiratory system that continuously tracks breathing during exercise and estimates VTs during ramp tests. We validate the respiratory rate and VTs predictions in 17 healthy adults using ergospirometry analysis. In addition, we use the wearable system to evaluate VTs in 107 recreational athletes during ramp tests outside the laboratory and show that the mean population values agree with physiological variables traditionally used to exercise prescription. We envision that respiratory wearables can be useful in determining aerobic and anaerobic parameters with promising applications in health telemonitoring and human performance.

Introduction: Chronic Obstructive Pulmonary Disease (COPD) is a prevalent respiratory disease that presents a high rate of underdiagnosis during onset and early stages. Studies have shown that in mild COPD patients, remodeling of the small airways occurs concurrently with morphological changes in the proximal airways. Despite this evidence, the geometrical study of the airway tree from computed tomography (CT) lung images remains underexplored due to poor representations and limited tools to characterize the airway structure.Methods: We perform a comprehensive morphometric study of the proximal airways based on geometrical measures associated with the different airway generations. To this end, we leverage the geometric flexibility of the Snakes IsoGeometric Analysis method to accurately represent and characterize the airway luminal surface and volume informed by CT images of the respiratory tree. Based on this framework, we study the airway geometry of smoking pre-COPD and mild COPD individuals.Results: Our results show a significant difference between groups in airway volume, length, luminal eccentricity, minimum radius, and surface-area-to-volume ratio in the most distal airways.Discussion: Our findings suggest a higher degree of airway narrowing and collapse in COPD patients when compared to pre-COPD patients. We envision that our work has the potential to deliver a comprehensive tool for assessing morphological changes in airway geometry that take place in the early stages of COPD.

Ventilatory thresholds (VTs) are key physiological parameters to evaluate physical performance and determine aerobic and anaerobic transitions during exercise. Current assessment of these parameters requires ergospirometry, limiting the evaluation to laboratory or clinical settings. In this work, we introduce a wearable respiratory system that continuously tracks breathing during exercise and estimates VTs during ramp–tests. We validate the respiratory rate and VTs predictions in 17 healthy adults using ergospirometry analysis. In addition, we use the wearable system to evaluate the VTs in 107 recreational athletes through ramp tests outside the laboratory and show that the mean population values agree with previous studies in large groups. We envision that respiratory wearables can be useful in determining aerobic and anaerobic parameters outside clinical setting with promising applications in health telemonitoring and human performance.