Characterising Insomnia: A Graph Spectral Theory Approach

Beena Ahmed1, Dean Cvetkovic, Ramiro Chaparro-Vargas, Thomas Penzel2

  • 1Texas A&M University at Qatar
  • 2Charité Universitätsmedizin Berlin

Details

Category

Contributed papers (Oral)

Theme

01. Biomedical Signal Processing

Sessions

08:30 - 10:00 | Wed 26 Aug | Space 1 | 1.3

Biomedical Signal Classification V: Sleep Studies

Abstract

This paper introduces a computational approach to characterise healthy controls and insomniacs based on graph spectral theory. Based upon expert-generated hypnograms of sleep onset periods, a network of sleep stages transitions is derived to compute four similarity distances amongst subjectsÂ’ sleeping patterns. A subsequent statistical analysis is performed to differentiate the 16-subject healthy group from a 16-patient disordered cohort. Our findings demonstrated that the similarity distances based on eigenvalues determination, i.e. d1 and d4 were the most reliable and robust measures to characterise insomniacs, discriminating 93% and 87% of the affected population, respectively.

Additional Information

No information added

Video

No videos found