Heart Failure Artificial Computer Aided Diagnosis Telecare System Using Various Artificial Intelligence Techniques

In this paper we present an Artificial Intelligence- based Computer Aided Diagnosis System intended to assist the clinical decision of non-specialist staff such as General Practitioner or Nurses in the analysis of patients with Heart Failure within a Tele-monitoring project. Three AI-based techniques are used and compared for diagnosis function: a Neural Network, a Support Vector Machine, and a Fuzzy Expert System whose rules are produced by a Genetic Algorithm. A diagnosis refine and an highlighting of the worsening are provided by comparing patient follow-up checks. An outcome prediction function is actually under construction. In order to offer a complete HF analysis dashboard, state of the art algorithms (SHFM, CHARM, ADHERE, EFFECT) are used to support a score-based prognosis function and the Framingham risk score is calculated.