Insomnia prediction using temporal feature of spindles

Hao Yu, Ying Zhang, Jin Chen, Shiqiang Tao, Taylor D. Smith, Guo Qiang Zhang, Xiaojin Li, Xiaoqian Jiang, Xiaoling Wang, Xinyu Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


Insomnia is prevalent in the general population and is often difficult to be identified reliably. The sleep spindle is a key electroencephalograph (EEG) signal that plays an important role in the preservation of sleep continuity. Previous studies on the relationship between spindle and insomnia mainly focus on the density distribution of spindle waves. In this article, we leverage the large amount of sleep data in the National Sleep Research Resource (NSRR) to develop two sequence models to take into consideration the temporal features of sleep spindles in the whole night sleep recording, and treat the interplay between insomnia and sleep spindle wave as a continuous process. The experimental results on two study cohorts of NSRR show that our method achieved the best performance among all the compared methods, indicating that it is the temporal feature of spindles, rather than stationary features (i.e., frequency, duration, amplitude) that are critical for identifying insomnia patients.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Healthcare Informatics, ICHI 2019
ISBN (Electronic)9781538691380
StatePublished - Jun 2019
Event7th IEEE International Conference on Healthcare Informatics, ICHI 2019 - Xi'an, China
Duration: Jun 10 2019Jun 13 2019

Publication series

Name2019 IEEE International Conference on Healthcare Informatics, ICHI 2019


Conference7th IEEE International Conference on Healthcare Informatics, ICHI 2019

Bibliographical note

Funding Information:
In this paper, we adopt EEG data from MrOS Sleep Study and Multi-Ethnic Study of Atherosclerosis (MESA) made available by National Sleep Research Resource (NSRR) [20], [21]. MrOS is an ancillary study funded by NIH that focuses on understanding the relationship between sleep disorders and falls, fractures, mortality, and vascular disease, containing EEG data for 2,911 men 65 years or older. MESA is an NHLBI-sponsored 6-center collaborative longitudinal investigation of factors associated with the development of subclinical cardiovascular disease and the progression of subclinical to clinical cardiovascular disease. MESA captures EEG data for 2,237 subjects with ages from 54 to 95 at baseline in 2000-2002.

Publisher Copyright:
© 2019 IEEE.


  • EEG
  • Insomnia
  • Signal Processing
  • Sleep Spindle
  • String Matching

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Health Informatics
  • Biomedical Engineering


Dive into the research topics of 'Insomnia prediction using temporal feature of spindles'. Together they form a unique fingerprint.

Cite this