0273 Advanced assessment of sleep derived from hypnodensity

Abstract Introduction In a recent analysis of PSG studies with six, nine and twelve human scorers, we showed that sleep stage ambiguity is the rule rather than exception, probabilities (SSPs) calculated artificial intelligence provide an excellent estimate this ambiguity. Here investigate clinical demographic factors driving evaluate potential benefits using hypnodensity in addition to traditional hypnogram for assessment. Methods SSPs were determined 195 healthy subjects aged 20–95 years 49 apnea patients 29–73 (AHI: 5.8–105.5 events/hour). recommended parameters, derived percentage ambiguous stages (SSP ≤ 0.95), mean amount per (1-SSP), continuity (absolute difference SSP between two epochs) stability (two adjacent epochs belonging same > 0.95 each) as well NREM depth (weighted average SSPs). Results The percentages (±SD) increased significantly age (Pearson’s r=0.72; p< 0.01) from 40±9% young (20-39 years, n=61) 50±9% middle-aged (40-59 n=59) 62±11% older (≥ 60 n=75). REM did not change across (r=0.1). Apnea (77±15% compared 53±10% age- sex-matched controls; 0.01), while was only slightly (p< 0.05). Furthermore, continuity, stability, decrease are lower controls 0.01). Conclusion Artificial intelligence-based autoscoring shows 40% subjects, increasing 77% patients. Assigning single each epoch presenting architecture may be misleading, especially sleep-disordered breathing. A chart representing reflects staging ambiguity, provides all information contained hypnogram, offers insights into depth. Support (if any)