An Efficient Pattern Recognition Kernel-Based Method for Atrial Fibrillation Diagnosis
| Autor: | Stephane Delliaux, Jean-Francois Pons, Bouchra Ananou, Youssef Trardi, Jean-Claude Deharo, Z. Haddi, Mustapha Ouladsine |
|---|---|
| Přispěvatelé: | Pronostic/Diagnostic Et CommAnde : Santé et Energie (PECASE), Laboratoire d'Informatique et Systèmes (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Laboratoire des Sciences de l'Information et des Systèmes (LSIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Arts et Métiers Paristech ENSAM Aix-en-Provence-Centre National de la Recherche Scientifique (CNRS), Institut d'Informatique et de Mathématiques Appliquées de Grenoble (IMAG), Université Joseph Fourier - Grenoble 1 (UJF)-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Dysoxie, suractivité : aspects cellulaires et intégratifs thérapeutiques (DS-ACI / UMR MD2), Aix Marseille Université (AMU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Centre recherche en CardioVasculaire et Nutrition (C2VN), Institut National de la Recherche Agronomique (INRA)-Aix Marseille Université (AMU)-Institut National de la Santé et de la Recherche Médicale (INSERM), Pronostic-Diagnostic Et CommAnde : Santé et Energie (PECASE), Aix Marseille Université (AMU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Centre recherche en CardioVasculaire et Nutrition = Center for CardioVascular and Nutrition research (C2VN), A*MIDEX project - 'Investissements d'Avenir' program of the French GovernmentFrench National Research Agency (ANR) [ANR-11-IDEX-0001-02], Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU), Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU), Centre National de la Recherche Scientifique (CNRS)-Arts et Métiers Paristech ENSAM Aix-en-Provence-Université de Toulon (UTLN)-Aix Marseille Université (AMU) |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Multivariate analysis
Health professionals Computer science business.industry 010401 analytical chemistry 0206 medical engineering RR interval Univariate Atrial fibrillation Pattern recognition 02 engineering and technology medicine.disease 020601 biomedical engineering 01 natural sciences 0104 chemical sciences Relevance vector machine [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering medicine Artificial intelligence Time series business Classifier (UML) ComputingMilieux_MISCELLANEOUS |
| Zdroj: | 2018 Computing in Cardiology Conference 2018 Computing in Cardiology Conference, Sep 2018, MAASTRICHT, Netherlands. ⟨10.22489/CinC.2018.090⟩ Computing in Cardiology 2018 Computing in Cardiology Conference, Sep 2018, MAASTRICHT, Netherlands. pp.4, ⟨10.22489/CinC.2018.090⟩ CinC |
| DOI: | 10.22489/CinC.2018.090⟩ |
| Popis: | International audience; The aim of this work is to develop an efficient diagnosis method for atrial fibrillation (AF) arrhythmia based on inter-beat interval time series analysis and relevance vector machine (RVM) classifier. Automatic and fast AF diagnosis is still a major concern for the healthcare professional. Several algorithms based on univariate and multivariate analysis have been developed to detect AF. The published results do not show satisfactory detection accuracy especially for brief duration as short as one minute. Although RVM has been applied on tasks such as computer vision, natural language processing, speech recognition etc., this is the first attempt to adopt RVM for AF diagnosis. Four publicly-accessible sets of clinical data (AF Termination Challenge Database, MIT-BIH AF, Normal Sinus Rhythm RR Interval Database, and MIT-BIH Normal Sinus Rhythm Databases) were used for assessment. All time series were segmented in 1 min RR interval window and then three specific features were calculated. The RVM classifier was trained on 2000 randomly selected samples from the merged database. The results showed that the RVM model performed better than do existing algorithms, with 99.20% for both sensitivity and specificity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|