SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
Researchers have developed SleepMaMi, a novel sleep foundation model designed to integrate both long-term sleep architecture and fine-grained biosignal analysis. This model employs a hierarchical dual-encoder structure, with a Macro-Encoder for temporal dependencies and a Micro-Encoder for signal morphologies. Trained on over 20,000 polysomnography recordings, SleepMaMi demonstrates superior generalizability and efficient adaptation for clinical sleep analysis tasks, outperforming existing state-of-the-art models. AI
IMPACT This model could advance clinical sleep analysis by providing more accurate and efficient diagnostic tools.