Detecting Chronic Diseases from Sleep-Wake Behaviour and Clinical Features

Sarah Fallmann, Liming Chen

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

10 Citations (Scopus)

Abstract

Many chronic diseases show evidence of correlations with sleep-wake behaviour, and there is an increasing interest in making use of such correlations for early warning systems. This research presents an approach towards early chronic disease detection by mining sleep-wake measurements using deep learning. Specifically, a Long-Short-Term-Memory network is applied on actigraph data enriched with clinical history of patients. Experiments and analysis are performed targeting detection at an early and advanced disease stage based on different clinical data features. The results show for disease detection an averaged accuracy of 0.62, 0.73, 0.81, 0.77 for hypertension, diabetes, sleep apnea and chronic kidney disease, respectively. Early detection performs with an averaged accuracy of 0.49 for sleep apnea and 0.56 for diabetes. Nevertheless, compared to existing work, our approach shows an improvement in performance and demonstrates that predicting chronic diseases from sleep-wake behavior is feasible, though further investigation will be needed for early prediction.
Original languageEnglish
Title of host publication2018 5th International Conference on Systems and Informatics (ICSAI)
Place of PublicationNanjing, China
PublisherIEEE Xplore
Pages1076-1084
Number of pages8
ISBN (Electronic)978-1-7281-0120-0
ISBN (Print)978-1-7281-0121-7
DOIs
Publication statusPublished (in print/issue) - 12 Nov 2018
Event2018 5th International Conference on Systems and Informatics (ICSAI) - Nanjing
Duration: 10 Nov 201812 Nov 2018

Conference

Conference2018 5th International Conference on Systems and Informatics (ICSAI)
Period10/11/1812/11/18

Keywords

  • Deep learning
  • Chronic Disease Detection
  • Sleep Monitoring

Fingerprint

Dive into the research topics of 'Detecting Chronic Diseases from Sleep-Wake Behaviour and Clinical Features'. Together they form a unique fingerprint.

Cite this