Pattern recognition of obstructive sleep apnoea and Cheyne-Stokes respiration

The aim of this study was to assess the validity of an artificial neural network based on flow-related spectral entropy as a diagnostic test for obstructive sleep apnoea and Cheyne-Stokes respiration. A data set of 37 subjects was used for spectral analysis of the airflow by performing a fast Fourier transform. The examined intervals were divided into epochs of 3 min. Spectral entropy S was applied as a measure for the spread of the related power spectrum. The spectrum was divided into several frequency areas with various subsets of spectral entropy. We studied 11 subjects with obstructive apnoeas (n = 267 epochs), 10 subjects with obstructive hypopnoeas (n = 80 epochs), 11 subjects with Cheyne-Stokes respiration (n = 253 epochs) and 5 subjects with normal breathing in non-REM sleep (n = 174 epochs). Based on spectral entropy an artificial neural network was built, and we obtained a sensitivity of 90.2% and a specificity of 90.9% for distinguishing between obstructive apnoeas and Cheyne-Stokes respiration, and a sensitivity of 91.3% and a specificity of 94.6% for discriminating between obstructive hypopnoeas and normal breathing in non-REM sleep. This resulted in an accuracy of 91.5% for identifying flow patterns of obstructive sleep apnoea, Cheyne-Stokes respiration and normal breathing in non-REM sleep. It is concluded that the use of an artificial neural network relying on spectral analysis of the airflow could be a useful method as a diagnostic test for obstructive sleep apnoea and Cheyne-Stokes respiration.