Deep learning and physiology based approach to derive and link obstructive sleep apnoea phenotypes and symptomatology

  • Toyras, Juha (Primary Chief Investigator (PCI))
  • Terrill, Philip Ian (Chief Investigator (CI))
  • Leppanen, Timo (Chief Investigator (CI))
  • Sands, Scott, Harvard Medical School (Chief Investigator (CI))
  • Smith, Simon (Chief Investigator (CI))
  • Perrin, Dimitri (Chief Investigator (CI))
  • Joosten, Simon (Chief Investigator (CI))

Project: Research

Project Details

Project Description

Obstructive sleep apnoea (OSA) is a highly prevalent nocturnal breathing disorder strongly related to daytime sleepiness, accident risk and reduced quality of life. However, the current severity index, the apnoea-hypopnoea index, poorly predicts daytime sleepiness and vigilance. In this project we elegantly combine physiological insight and artificial intelligence to develop and evaluate novel clinically applicable computational tools for detailed quantification of OSA severity and its symptoms.
Effective start/end date1/01/2131/12/23


  • obstructive sleep apnoea
  • sleep disordered breathing
  • daytime sleepiness
  • biomedical engineering
  • artificial neural networks