A signal representative of a patient's respiration is split into equallength epochs. A primary feature is extracted from each epoch that acts as a compressedrepresentation of the signal events. Statistics are applied to the primary featureto produce one or more secondary features that represent the entire epoch. Eachsecondary feature is grouped with one or more other features that are extractedfrom the entire epoch rather than selected epoch events. This grouping is theepoch pattern. The pattern is manipulated with suitable classifier algorithmto produce a probability for each class within the algorithm, that the signalmay be representative of a disease state (Cheyne-Stokes, OSA etc). The epochis assigned to the class with the highest probability. Also defined are methodsof detecting Cheyne-Stokes breathing by analysing a signal to detect one or regionsof hyperpnoea and if the length of a hyperpnoea exceeds a parameter, Cheyne-Stokesis present.
