Single-FiO2 lung modelling with machine learning: a computer simulation incorporating volumetric capnography.

We investigated whether machine learning (ML) analysis of ICU monitoring data incorporating volumetric capnography measurements of mean alveolar PCO2 can partition venous admixture (VenAd) into its shunt and low V/Q components without manipulating the inspired oxygen fraction (FiO2). From a 21-compartment ventilation / perfusion (V/Q) model of pulmonary blood flow we generated blood gas and mean alveolar PCO2 data in simulated scenarios with shunt values from 7.3% to 36.5% and a range of FiO2 settings, indirect calorimetry and cardiac output measurements and acid- base and hemoglobin oxygen affinity conditions. A 'deep learning' ML application, trained and validated solely on single FiO2 bedside monitoring data from 14,736 scenarios, then recovered shunt values in 500 test scenarios with true shunt values 'held back'. ML shunt estimates versus true values (n = 500) produced a linear regression model with slope = 0.987, intercept = -0.001 and R2 = 0.999. Kernel density estimate and error plots confirmed close agreement. With corresponding VenAd values calculated from the same bedside data, low V/Q flow can be reported as VenAd-shunt. ML analysis of blood gas, indirect calorimetry, volumetric capnography and cardiac output measurements can quantify pulmonary oxygenation deficits as percentage shunt flow (V/Q = 0) versus percentage low V/Q flow (V/Q > 0). High fidelity reports are possible from analysis of data collected solely at the operating FiO2.

Pulmonary gas exchange evaluated by machine learning: a computer simulation.

Using computer simulation we investigated whether machine learning (ML) analysis of selected ICU monitoring data can quantify pulmonary gas exchange in multi-compartment format. A 21 compartment ventilation/perfusion (V/Q) model of pulmonary blood flow processed 34,551 combinations of cardiac output, hemoglobin concentration, standard P50, base excess, VO2 and VCO2 plus three model-defining parameters: shunt, log SD and mean V/Q. From these inputs the model produced paired arterial blood gases, first with the inspired O2 fraction (FiO2) adjusted to arterial saturation (SaO2) = 0.90, and second with FiO2 increased by 0.1. 'Stacked regressor' ML ensembles were trained/validated on 90% of this dataset. The remainder with shunt, log SD, and mean 'held back' formed the test-set. 'Two-Point' ML estimates of shunt, log SD and mean utilized data from both FiO2 settings. 'Single-Point' estimates used only data from SaO2 = 0.90. From 3454 test gas exchange scenarios, two-point shunt, log SD and mean estimates produced linear regression models versus true values with slopes ~ 1.00, intercepts ~ 0.00 and R2 ~ 1.00. Kernel density and Bland-Altman plots confirmed close agreement. Single-point estimates were less accurate: R2 = 0.77-0.89, slope = 0.991-0.993, intercept = 0.009-0.334. ML applications using blood gas, indirect calorimetry, and cardiac output data can quantify pulmonary gas exchange in terms describing a 20 compartment V/Q model of pulmonary blood flow. High fidelity reports require data from two FiO2 settings.