A Unified Flexible Large Polysomnography Model for Sleep Staging and Mental Disorder Diagnosis.

Abstract

Sleep disorders affect billions worldwide, yet clinical polysomnography (PSG) analysis remains hindered by labor-intensive manual scoring and limited generalizability of automated sleep staging tools across heterogeneous protocols. We present LPSGM, a large-scale PSG model designed to address two critical challenges in sleep medicine: cross-center generalization and adaptable diagnosis of neuropsychiatric disorders. Trained on 220,500 hours of multi-center PSG data (24,000 full-night recordings from 16 public datasets), LPSGM integrates domain-adaptive pre-training, flexible channel configurations, and a unified architecture to mitigate variability in equipment, montages, and populations during sleep staging while enabling downstream fine-tuning for mental disorder detection. In prospective validation, LPSGM achieves expert-level consensus in sleep staging (κ = 0.845 ± 0.066 vs. inter-expert κ = 0.850 ± 0.102) and matches the performance of fully supervised models on two independent private cohorts. When fine-tuned, it attains 88.01% accuracy in narcolepsy detection and 100% accuracy in identifying major depressive disorder (MDD), highlighting shared physiological biomarkers between sleep architecture and neuropsychiatric symptoms. By bridging automated sleep staging with real-world clinical deployment, LPSGM establishes a scalable, data-efficient framework for integrated sleep and mental health diagnostics. The code and pre-trained model are publicly available at https://github.com/Deng-GuiFeng/LPSGM to advance reproducibility and translational research in sleep medicine.