TY - JOUR
T1 - SleepMambaNet
T2 - a lightweight multimodal framework for sleep staging and sleep disorder screening with multicenter validation
AU - Zhang, Chao
AU - Wang, Queliang
AU - Liu, Yaping
AU - Li, Xiaoliang
AU - Jiang, Fan
AU - Li, Shuyan
AU - Cui, Weirong
AU - Guo, Jingjing
N1 - Publisher Copyright:
© 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved. This article is available under the terms of the IOP-Standard License.
PY - 2026/10
Y1 - 2026/10
N2 - Objective. Manual sleep staging is labor-intensive, whereas many automated systems remain computationally demanding and are validated on a single dataset. This study aimed to develop a lightweight multimodal framework for automated sleep staging and exploratory sleep-disorder screening from polysomnographic (PSG) signals. Approach. SleepMambaNet combines efficient channel attention to integrate complementary information across PSG channels with bidirectional Mamba modules to model long-range temporal dependencies between sleep epochs. The framework was evaluated on the public ISRUC-S1 and ISRUC-S3 datasets and a multicenter clinical cohort of 185 PSG recordings. Main results. In subject-independent experiments, SleepMambaNet achieved accuracy, macro-F1, and Cohen’s kappa of 0.852, 0.824, and 0.803 on ISRUC-S3; 0.830, 0.801, and 0.773 on ISRUC-S1; and 0.854, 0.819, and 0.806 on the combined public and clinical data, respectively. The external cross-dataset evaluation yielded accuracy, macro-F1, and kappa of 0.828, 0.812, and 0.779. For exploratory sleep-disorder screening, the model achieved accuracy of 0.892, F1 score of 0.887, sensitivity of 0.956, specificity of 0.842, and precision-recall area under the curve of 0.831. Significance. These results show that cross-channel physiological information and inter-epoch temporal context can be modeled effectively with only 0.47 million trainable parameters across heterogeneous public and clinical PSG data. The combination of computational efficiency and cross-dataset performance provides a practical basis for prospective evaluation of automated PSG decision support, while the binary screening output should not be interpreted as a disease-specific or standalone clinical diagnosis.
AB - Objective. Manual sleep staging is labor-intensive, whereas many automated systems remain computationally demanding and are validated on a single dataset. This study aimed to develop a lightweight multimodal framework for automated sleep staging and exploratory sleep-disorder screening from polysomnographic (PSG) signals. Approach. SleepMambaNet combines efficient channel attention to integrate complementary information across PSG channels with bidirectional Mamba modules to model long-range temporal dependencies between sleep epochs. The framework was evaluated on the public ISRUC-S1 and ISRUC-S3 datasets and a multicenter clinical cohort of 185 PSG recordings. Main results. In subject-independent experiments, SleepMambaNet achieved accuracy, macro-F1, and Cohen’s kappa of 0.852, 0.824, and 0.803 on ISRUC-S3; 0.830, 0.801, and 0.773 on ISRUC-S1; and 0.854, 0.819, and 0.806 on the combined public and clinical data, respectively. The external cross-dataset evaluation yielded accuracy, macro-F1, and kappa of 0.828, 0.812, and 0.779. For exploratory sleep-disorder screening, the model achieved accuracy of 0.892, F1 score of 0.887, sensitivity of 0.956, specificity of 0.842, and precision-recall area under the curve of 0.831. Significance. These results show that cross-channel physiological information and inter-epoch temporal context can be modeled effectively with only 0.47 million trainable parameters across heterogeneous public and clinical PSG data. The combination of computational efficiency and cross-dataset performance provides a practical basis for prospective evaluation of automated PSG decision support, while the binary screening output should not be interpreted as a disease-specific or standalone clinical diagnosis.
KW - bidirectional state space model
KW - efficient channel attention
KW - sleep disorder screening
KW - sleep medicine
KW - sleep staging
UR - https://www.scopus.com/pages/publications/105052188621
U2 - 10.1088/1361-6579/aeab40
DO - 10.1088/1361-6579/aeab40
M3 - Article
C2 - 42817663
AN - SCOPUS:105052188621
SN - 0967-3334
VL - 47
JO - Physiological Measurement
JF - Physiological Measurement
IS - 10
M1 - 105002
ER -