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

Abstract

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.

Keywords: Deep learning; Low V/Q; MIGET; Machine learning; Shunt; Simulation; Single—FiO2.

Fig. 1

Architecture of the ‘reverse engineering’ method. ‘ML’ is Machine Learning. ‘Venad’ is venous admixture, calculated as per Eq. 10 in Supplementary Material. Other abbreviations as in Tables 1 and 2

Fig. 2

Shunt estimates versus true values. Three subplots share the same X-axis scale. The kernel density estimate (KDE) plot (upper graph) illustrates the distribution of observations for the independent variable along with goodness of fit. The Y-axis in the KDE plot is dimensionless. The solid line (true shunt values) and the dashed line (shunt estimates) are closely aligned. Close agreement, slightly reduced at Shunt ≤ 15%, is evident in the error plot (middle graph), and in the plot of true shunt versus shunt estimates (lower graph)

Fig. 3

Variation of mean PACO₂ (mean alveolar PCO₂) measurements above and below the ‘true’ value with corresponding venous admixture and shunt percentages

Fig. 4

Variation of PaCO₂, VCO₂, cardiac output and R (respiratory exchange ratio) values above and below ‘true’ values with corresponding venous admixture and shunt percentages

Fig. 5

Variation of PaO₂, SaO₂, pH and Hb above and below the ‘true’ values with corresponding effects on venous admixture and shunt percentages