Abstract: The present invention provides a predictive tool for predicting Apopnea Hypopnea Index (AHI) in the diagnosis of Obstructive sleep apnea (OSA). The predictive tool is developed by recording pulse oximetry readings, obtaining delta index, oxygen saturation times and oxygen desaturation events from the oximetry readings. A multivariate non-parametric analysis and bootstrap aggregation is performed to obtain predictive models which can be used to predictive AHI in an individual and to classify an individual as having or not having OSA.

Abstract: The present invention discloses a method for developing a diagnostic method for CSR. The method comprises the steps of performing overnight oximetry recordings in patients suspected of OSA who have been identified as having or not having CSR by clinical studies. Spectral analysis is performed on the oximetry recordings from which a classification tree is generated. The present invention also discloses a method for the identification of Cheyne-Stokes respiration in an individual. The method comprises the steps of performing spectral analysis of overnight oximetry recordings. The key features are then input into a classification tree to determine the presence or absence of CSR.

Abstract: A method for predicting respiratory disturbances, and a method for developing such an artificial neural network. The inputs to the method and to the artificial neural network of the present invention are the answers given by a person to a series of questions. The output of the artificial neural network is a predicted respiratory disturbance index.