Skip to main content

Table 6 The correlation coefficients between estimated sleep parameters and ground truth after applying the energy score threshold (0.80) for each dataset

From: InsightSleepNet: the interpretable and uncertainty-aware deep learning network for sleep staging using continuous Photoplethysmography

 

MESA

CFS

CAP

TST

r = 0.981, r2 = 0.964

r = 0.938, r2 = 0.880

r = 0.889, r2 = 0.791

Light sleep fraction

r = 0.688, r2 = 0.473

r = 0.900, r2 = 0.810

r = 0.915, r2 = 0.837

Deep sleep fraction

r = 0.294, r2 = 0.086

r = 0.906, r2 = 0.816

r = 0.964, r2 = 0.928

REM sleep fraction

r = 0.831, r2 = 0.691

r = 0.853, r2 = 0.727

r = 0.865, r2 = 0.749