Sleep Stage Specificity to Window Length Variations: A Decision Fusion Strategy for Enhanced Scoring

Sleep stage scoring is a fundamental component of sleep medicine, enabling a comprehensive assessment of sleep architecture and quality. While the standard 30-second (30s) epoch defined by the American Academy of Sleep Medicine represents the clinical gold standard, most automatic sleep stage scoring algorithms process these fixed segments in isolation. This approach may hinder the detection of transient arousal events, sleep spindles, K-complexes, and other phasic sleep characteristics that occur on finer timescales, thus necessitating analysis at sub-epoch resolution. To leverage complementary information across temporal scales, we propose a Multi-scale Decision Fusion Sleep Network (MDFSleepNet). Our systematic analysis across window lengths (1-30 seconds) reveals significant stage-specific temporal preferences: N1 and N3 stages achieve higher accuracy with 30s windows capturing comprehensive context, while N2 stage classification benefits markedly from shorter windows (1-2 seconds) optimized for transient micro-structure detection. REM stage preferences exhibit dataset variability. Motivated by these findings, MDFSleepNet integrates these complementary scales through a dual-stream architecture combining multi-scale segmentation, scale-specific feature learning, and cross-scale fusion. Evaluated on ISRUC-S1 and ISRUC-S3 (by fusing 5s and 30s windows), MDFSleepNet achieves state-of-the-art accuracies of 83.5% and 84.8% (Cohen's Kappa: 0.786, 0.804). On Sleep-EDF-20 (fusing 15s and 30s windows), it reaches 90.9% accuracy (Cohen's Kappa: 0.875), demonstrating robust performance through complementary multi-scale fusion. The source code for this study is publicly available at https://github.com/wzw999/MDFSleepNet.