phat 16(8): e4

Research Article

Symbolic Fusion: A Novel Decision Support Algorithm for Sleep Staging Application

Download1093 downloads
  • @ARTICLE{10.4108/eai.14-10-2015.2261933,
        author={Chen CHEN and Xue Liu and Adrien UGON and Xun ZHANG and Amara AMARA and Patrick GARDA and Jean-Gabriel GANASCIA and Carole PHILIPPE and Andrea PINNA},
        title={Symbolic Fusion: A Novel Decision Support Algorithm for Sleep Staging Application},
        journal={EAI Endorsed Transactions on Pervasive Health and Technology},
        volume={2},
        number={8},
        publisher={ACM},
        journal_a={PHAT},
        year={2015},
        month={12},
        keywords={symbolic fusion; decision support; sleep staging; polysomnography (psg)},
        doi={10.4108/eai.14-10-2015.2261933}
    }
    
  • Chen CHEN
    Xue Liu
    Adrien UGON
    Xun ZHANG
    Amara AMARA
    Patrick GARDA
    Jean-Gabriel GANASCIA
    Carole PHILIPPE
    Andrea PINNA
    Year: 2015
    Symbolic Fusion: A Novel Decision Support Algorithm for Sleep Staging Application
    PHAT
    EAI
    DOI: 10.4108/eai.14-10-2015.2261933
Chen CHEN1,*, Xue Liu1, Adrien UGON2, Xun ZHANG3, Amara AMARA3, Patrick GARDA1, Jean-Gabriel GANASCIA1, Carole PHILIPPE4, Andrea PINNA1
  • 1: Pierre and Marie Curie University
  • 2: Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances en e-Santé
  • 3: Institut Supérieur d'Electronique de Paris
  • 4: AP-HP Hôpital Universitaire Pitié Salpêtrière
*Contact email: ccxx2417@gmail.com

Abstract

With the rapid extension of clinical data and knowledge, decision making becomes a complex task for manual sleep staging. In this process, there is a need for integrating and analyzing information from heterogeneous data sources with high accuracy. This paper proposes a novel decision support algorithm—Symbolic Fusion for sleep staging application. The proposed algorithm provides high accuracy by combining data from heterogeneous sources, like EEG, EOG and EMG. This algorithm is developed for implementation in portable embedded systems for automatic sleep staging at low complexity and cost. The proposed algorithm proved to be an efficient design support method and achieved up to 76% overall agreement rate on our database of 12 patients.