Hypnogram-Driven Automatic Sleep Staging and a Quality-Index Assessment Through a Two-Stage LSTM-DNN Ensemble Learning Approach Using Multi-Biosignal Features for Sleep Disorder Detection.

Sleep monitoring and analysis are essential for understanding overall health, improving sleep quality, and detecting potential disorders early. This study presents a multimodal approach for automatic sleep staging and quality assessment using a reduced set of bio-signals: a single electroencephalographic (EEG) lead (F4-F3), a single EOG lead, and the photo-plethysmographic (PPG) signal. The proposed methodology includes a hierarchical sleep staging classifier, an automatic sleep staging algorithm, and a subject-specific Sleep Quality Index (SQI) for objective sleep quality assessment. The 5-class sleep staging classifier employs a cascaded architecture of two sequential 3-class models (Wake-REM-NREM and N1-N2-N3), trained and tested on multimodal features derived from physiological signals (EEG, EOG, and PPG) of the BOAS (Bitbrain Open Access Sleep) dataset. The resulting 5-class classifier achieved 90.8% accuracy with a reduced memory footprint (3.14 MB). To assess subject-independent generalization and prevent data leakage between training and test sets, a Leave-One-Subject-Out (LOSO) validation was performed, confirming the robustness of the proposed classifier across unseen subjects. The classifier was subsequently integrated into an automatic sleep staging algorithm. Validation on 14 unseen subjects yielded accuracies ranging from 80.26% to 91.99% using heuristic post-processing rules, while a Hidden Markov Model (HMM)-based approach further improved performance, reaching a peak accuracy of 91.99%. The proposed SQI combines sleep-related metrics extracted from staging, considering multiple sleep aspects (i.e., duration, intensity, and continuity-fragmentation). A calibration strategy was proposed to customize the SQI based on sleep scoring parameters and the subjective quality score derived from sleep diaries and questionnaires (PSQI). This subject-specific strategy was validated on a public dataset, optimizing weights across multiple nights, followed by an independent test on a subsequent night and demonstrating strong alignment between the calculated SQI and the subjective sleep quality score (MAE = 10.81). Finally, the framework provides resource-efficient sleep staging and custom quality estimation, validating its readiness for practical, long-term sleep monitoring.