A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Point out the mistakes : An HMM-based anomaly detection algorithm for sleep stage classification (2025)
Wang, Z., Liu, H., Cai, Y., Li, H., Yang, C., Zhang, X., & Cong, F. (2025). Point out the mistakes : An HMM-based anomaly detection algorithm for sleep stage classification. Biomedical Signal Processing and Control, 99, Article 106805. https://doi.org/10.1016/j.bspc.2024.106805
JYU-tekijät tai -toimittajat
Julkaisun tiedot
Julkaisun kaikki tekijät tai toimittajat: Wang, Ziyi; Liu, Hang; Cai, Yukai; Li, Hongjin; Yang, Chuanshuai; Zhang, Xinlei; Cong, Fengyu
Lehti tai sarja: Biomedical Signal Processing and Control
ISSN: 1746-8094
eISSN: 1746-8108
Julkaisuvuosi: 2025
Ilmestymispäivä: 19.09.2024
Volyymi: 99
Artikkelinumero: 106805
Kustantaja: Elsevier
Julkaisumaa: Britannia
Julkaisun kieli: englanti
DOI: https://doi.org/10.1016/j.bspc.2024.106805
Julkaisun avoin saatavuus: Ei avoin
Julkaisukanavan avoin saatavuus:
Tiivistelmä
Accurate sleep stage scoring is essential for diagnosing sleep disorders. Current automated sleep staging methods often exhibit staging errors, which can be interpreted as anomalies. Detecting these anomalies is crucial for improving staging accuracy. Most existing approaches modify staging based on predefined conditions but lack effective methods for localizing and identifying anomalies. In this study, we propose an anomaly detection method utilizing the Hidden Markov Model (HMM), a time-series modeling technique, to detect anomalies in sleep staging results. Evaluating our approach with four classical models as pre-classifiers, we achieve anomaly detection precisions of 0.760, 0.577, 0.631, and 0.613. Assuming that all detected anomalies are corrected, the pseudo-accuracies improve to 0.964, 0.929, 0.950, and 0.929, respectively. Our results indicate that the proposed method significantly enhances stage recognition accuracy, especially for stage N1, which is critical for diagnosing sleep-related disorders. Notably, approximately 28.6% of epochs require reinterpretation by sleep technicians to achieve these improvements.
YSO-asiasanat: neuroverkot; unitutkimus; anomaliat; EEG; aivotutkimus
Vapaat asiasanat: automatic sleep stage scoring; hidden markov model (HMM); deep neural network; anomaly detection
Liittyvät organisaatiot
OKM-raportointi: Kyllä
JUFO-taso: 1
Alustava JUFO-taso: 1