Abstract: There is provided a computer-implemented method of training a machine learning model for computing an estimate of a ventilation inhomogeneity parameter indicating a ventilation inhomogeneity state of a subject, comprising: creating a training dataset comprising a plurality of records, each record including a plurality of measurements of a single breath maneuver of a respective subject measured by at least one sensor including at least one CO2 sensor and at least one pressure sensor, labelled with a ground truth label of the ventilation inhomogeneity parameter indicating the ventilation inhomogeneity state, and training a machine learning model on the training dataset for generating an outcome of an estimate of a target ventilation inhomogeneity parameter for a target subject in response to an input of a target plurality of measurements of a single breath maneuver of the subject sensed by the at least one sensor.

Abstract: The present disclosure provides examples of a method, including: providing a representative inhale-exhale cycle breathing volume over time profile; and when the subject performs at least one inhale-exhale cycle that meets a correspondence criterion related to the representative profile, using data relating to oxygen consumption or carbon dioxide production during the inhale-exhale cycle that met the correspondence criterion to determine a metabolic property in the subject.

Abstract: The present disclosure provides examples of a method, including: providing a representative inhale-exhale cycle breathing volume over time profile; and when the subject performs at least one inhale-exhale cycle that meets a correspondence criterion related to the representative profile, using data relating to oxygen consumption or carbon dioxide production during the inhale-exhale cycle that met the correspondence criterion to determine a metabolic property in the subject.