Performance evaluation of the open-source Yet Another Spindle Algorithm sleep staging algorithm against gold standard
Davide Benedetti1, Emma Frati2, Orsolya Kiss3
1Center for Health Sciences, SRI International, Menlo Park, California, USA; Department of Translational Research and of New Surgical and Medical Technologies, University of Pisa, Pisa, Italy.
Goal And Aims:
To evaluate an automatic sleep scoring algorithm against manual polysomnography sleep scoring.
Focus Method/Technology:
Yet Another Spindle Algorithm automatic sleep staging algorithm.
Reference Method/Technology:
Manual sleep scoring.
Sample:
327 nights (151 healthy adolescents), from the NCANDA study.
Design:
Participants underwent one-to-three overnight polysomnography recordings, one consisting of an event-related-potential paradigm.
Core Analytics:
Epoch by Epoch and discrepancy analyses (Bland Altman plots) were conducted on the overall sample.
Additional Analytics And Exploratory Analyses:
Epoch by Epoch and discrepancy analysis were repeated separately on standard polysomnography nights and event-related potential nights. Regression models were estimated on age, sex, scorer, and site of recording, separately on standard polysomnography nights and event-related potential nights.
Core Outcomes:
The Yet Another Spindle Algorithm sleep scoring algorithm's average sensitivity of 93.04% for Wake, 87.67% for N2, 84.46% for N3, 86.02% for rapid-eye-movement, and 40.39% for N1. Specificity was 96.75% for Wake, 97.31% for N1, 88.87% for N2, 97.99% for N3, and 97.70% for rapid-eye-movement. The Matthews Correlation Coefficient was highest in rapid-eye-movement sleep (0.85) while lowest in N1 (0.39). Cohen's Kappa mirrored Matthews Correlation Coefficient results. In Bland-Altman plots, the bias between Yet Another Spindle Algorithm and human scoring showed proportionality to the manual scoring measurement size.
Important Additional Outcomes:
Yet Another Spindle Algorithm performance was reduced in event-related-potential/polysomnography nights for N3 and rapid-eye-movement. According to the Matthews Correlation Coefficient, the Yet Another Spindle Algorithm performance was affected by younger age, male sex, recording sites, and scorers.
Core Conclusion:
Results support the use of Yet Another Spindle Algorithm to score adolescents' polysomnography sleep records, possibly with classification outcomes supervised by an expert scorer.
