U-Sleep: resilient to AASM guidelines
AASM guidelines are the results of decades of efforts to try to standardize the sleep scoring procedure as to have a commonly used methodology. The guidelines cover several aspects from the technical/digital specifications, e.g., recommended EEG derivations, to the sleep scoring rules, e.g., different rules for adults, children and infants. In the context of sleep scoring automation, in the last decades, deep learning has demonstrated better performance compared to many other approaches. In most of the cases, clinical knowledge and guidelines have been exploited to support the automated sleep scoring algorithms in solving the task. In this paper we show that, actually, a deep learning based sleep scoring algorithm may not need to fully exploit the clinical knowledge or to strictly follow the AASM guidelines. Specifically, we demonstrate that U-Sleep, a state-of-the-art sleep scoring algorithm, can be strong enough to solve the scoring task even using clinically non-recommended or non-conventional derivations, and with no need to exploit information about the chronological age of the subjects. We finally strengthen a well-known finding that using data from multiple data centers always results in a better performing model compared with training on a single cohort. Indeed, we show that this latter statement is still valid even by increasing the size and the heterogeneity of the single data cohort. In all our experiments we used 28528 polysomnography studies from 13 different clinical studies.
READ FULL TEXT