From Sleep Staging to Spindle Detection: Evaluating End-to-End Automated Sleep Analysis

TL;DR

This study demonstrates that fully automated sleep analysis using advanced machine learning models can replicate key findings from expert studies, enabling large-scale sleep research with reduced manual effort.

Contribution

The paper evaluates a fully automated multi-step sleep analysis pipeline combining sleep staging and spindle detection, showing it can reproduce expert findings and perform at or above inter-rater agreement.

Findings

Automated analysis replicated key bipolar disorder sleep spindle findings.

Models performed at or above inter-rater agreement.

Tools and platform are publicly available for large-scale sleep research.

Abstract

Automation of sleep analysis, including both macrostructural (sleep stages) and microstructural (e.g., sleep spindles) elements, promises to enable large-scale sleep studies and to reduce variance due to inter-rater incongruencies. While individual steps, such as sleep staging and spindle detection, have been studied separately, the feasibility of automating multi-step sleep analysis remains unclear. Here, we evaluate whether a fully automated analysis using state-of-the-art machine learning models for sleep staging (RobustSleepNet) and subsequent spindle detection (SUMOv2) can replicate findings from an expert-based study of bipolar disorder. The automated analysis qualitatively reproduced key findings from the expert-based study, including significant differences in fast spindle densities between bipolar patients and healthy controls, accomplishing in minutes what previously took months to complete manually. While the results of the automated analysis differed quantitatively from the expert-based study, possibly due to biases between expert raters or between raters and the models, the models individually performed at or above inter-rater agreement for both sleep staging and spindle detection. Our results demonstrate that fully automated approaches have the potential to facilitate large-scale sleep research. We are providing public access to the tools used in our automated analysis by sharing our code and introducing SomnoBot, a privacy-preserving sleep analysis platform.