Title: Learning rules from multisource data for cardiac monitoring

Authors: Elisa Fromont, Rene Quiniou, Marie-Odile Cordier

Addresses: UMR CNRS 5516, Laboratoire Hubert Curien, Universite de Lyon, Universite de Saint Etienne, 18 Rue du Professeur Benoit Lauras, 42000 Saint-Etienne, France. ' INRIA/IRISA, Campus de Beaulieu, F-35042 Rennes Cedex, France. ' Universite de Rennes 1/IRISA, Campus de Beaulieu, F-35042 Rennes Cedex, France

Abstract: This paper formalises the concept of learning symbolic rules from multisource data in a cardiac monitoring context. Our sources, electrocardiograms and arterial blood pressure measures, describe cardiac behaviours from different viewpoints. To learn interpretable rules, we use an Inductive Logic Programming (ILP) method. We develop an original strategy to cope with the dimensionality issues caused by using this ILP technique on a rich multisource language. The results show that our method greatly improves the feasibility and the efficiency of the process while staying accurate. They also confirm the benefits of using multiple sources to improve the diagnosis of cardiac arrhythmias.

Keywords: multisource data; ILP; inductive logic programming; declarative bias; cardiac arrhythmias; cardiac monitoring; heart monitoring; symbolic rules; electrocardiograms; EGCs; arterial blood pressure; cardiac behaviours; medical diagnosis.

DOI: 10.1504/IJBET.2010.029655

International Journal of Biomedical Engineering and Technology, 2010 Vol.3 No.1/2, pp.133 - 155

Published online: 30 Nov 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article