Data mining techniques for detection of sleep arousals

Arousals are considered one of the main causes of daytime sleepiness. They impede the proper flow of sleep cycles and cause weariness. Manual scoring of arousals is time-consuming, requires expert knowledge, and has high inter-scorer variability. A major difficulty in detecting arousals automatically is the existing variance across patients. Based on data mining techniques, we present a different approach to the automatic detection of arousals that overcomes the hurdle of differences in signal characteristics across patients. Offline we used a training-set of adult patients to define a set of general rules to detect arousals (termed meta-rules). This was done by analyzing the correlations between occurrences of arousals and the EEG, EMG, pulse and SaO2 signals as follows: (1) each signal was mathematically projected into several spaces (termed projected-signals); (2) from each such projected-signal, the algorithm extracted time points that indicated meaningful changes (termed critical-points); (3) data mining techniques were applied to all the critical-points to discover patterns of repeating behavior; (4) classes of patterns which were highly correlated with manually scored arousals were formalized as meta-rules. Online we used a test-set of adult patients from two other different sleep laboratories. Using the meta-rules, the algorithm extracted individual rules for each patient (termed actual-rules), and used them to automatically detect the patients' arousals. These arousals were significantly correlated (R = 0.88, p < 0.0001; sensitivity = 75.2%, positive predictive value = 76.5%) with those detected manually by experts. Since the total number of arousals is a measure of sleep quality, this algorithm constitutes a novel approach to automatically estimate sleep quality.