Power of breathing determined noninvasively with use of an artificial neural network in patients with respiratory failure*

Abstract

POB can be calculated noninvasively with reasonable clinical accuracy for patients receiving ventilatory support by using an ANN. This method obviates the need for inserting an esophageal catheter and thus greatly simplifies measurement of POB. POB(N) may be a clinically useful tool for consideration when setting PSV to unload the respiratory muscles. Before considering its use in clinical practice, POB(N) would need to be incorporated within the context of load tolerance and shown to improve outcomes.

In-Hospital Mortality Prediction in Patients Receiving Mechanical Ventilation in Taiwan

“…Although they cannot deal with missing data, ANNs can simultaneously handle numerous variables by building models with reference to outliers and nonlinear interactions among variables. [4][5][6] Whereas conventional statistical methods reveal parameters that are significant only for the overall population, ANNs include parameters that are significant at the individual level even if they are not significant for the overall population. Unlike other standard statistical tests, ANNs can also manage complexity even when the sample size is small and even when the ratio between variables and records is unbalanced.…”

“…Unlike other standard statistical tests, ANNs can also manage complexity even when the sample size is small and even when the ratio between variables and records is unbalanced. [4][5][6] That is, ANNs avoid the dimensionality problem. The large and homogeneous data set in this study enabled robust network training because all clinical variables had shown potential effects on mortality in previous logistic regression models.…”

“…Once a model is trained, prediction outputs can be generated from novel records. [4][5][6] Previous comparisons of logistic regression and ANN models for predicting outcomes of mechanical ventilation have shown major shortcomings. [7][8][9][10] First, few have used pooled data analysis for more than 2 years.…”

Respiratory Mechanics in Mechanically Ventilated Patients

“…An artificial neural network can be used to estimate power of breathing noninvasively, without the need for an esophageal catheter in patients with respiratory failure. 42 In one study, a WOB/min of Ͻ 10 J/min was predictive of subjects' ability to be liberated from mechanical ventilation. 43 Adaptive support ventilation (ASV) is based on the concept of minimum WOB, which suggests that the patient will breathe at a V T and breathing frequency that minimize the elastic and resistive loads while maintaining oxygen- Fig.…”

“…WOB is calculated from the measured V I and the P calculated from the equation of motion: WOB ϭ ͐P ϫ V. Power of breathing (WOB/min) is the rate at which work is done as a measure over time, not for an individual breath. [42][43][44][45][46] This may be a better assessment of respiratory muscle load than WOB/breath. Normal power of breathing is 4 -8 J/min.…”