Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms.

Guy Carrault 1, * Marie-Odile Cordier 2 René Quiniou 2 F. Wang 1
* Corresponding author
2 DREAM - Diagnosing, Recommending Actions and Modelling
Inria Rennes – Bretagne Atlantique , IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
Abstract : This paper proposes a novel approach to cardiac arrhythmia recognition from electrocardiograms (ECGs). ECGs record the electrical activity of the heart and are used to diagnose many heart disorders. The numerical ECG is first temporally abstracted into series of time-stamped events. Temporal abstraction makes use of artificial neural networks to extract interesting waves and their features from the input signals. A temporal reasoner called a chronicle recogniser processes such series in order to discover temporal patterns called chronicles which can be related to cardiac arrhythmias. Generally, it is difficult to elicit an accurate set of chronicles from a doctor. Thus, we propose to learn automatically from symbolic ECG examples the chronicles discriminating the arrhythmias belonging to some specific subset. Since temporal relationships are of major importance, inductive logic programming (ILP) is the tool of choice as it enables first-order relational learning. The approach has been evaluated on real ECGs taken from the MIT-BIH database. The performance of the different modules as well as the efficiency of the whole system is presented. The results are rather good and demonstrate that integrating numerical techniques for low level perception and symbolic techniques for high level classification is very valuable.
Complete list of metadatas

https://www.hal.inserm.fr/inserm-00134396
Contributor : Lotfi Senhadji <>
Submitted on : Thursday, March 1, 2007 - 9:53:20 PM
Last modification on : Thursday, November 15, 2018 - 11:57:04 AM

Identifiers

Citation

Guy Carrault, Marie-Odile Cordier, René Quiniou, F. Wang. Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms.. Artificial Intelligence in Medicine, Elsevier, 2003, 28 (3), pp.231-63. ⟨10.1016/S0933-3657(03)00066-6⟩. ⟨inserm-00134396⟩

Share

Metrics

Record views

318