Authors:
Athanasia Lappa
1
and
Christos Goumopoulos
2
Affiliations:
1
Hellenic Open University, Greece
;
2
Computer Technology Institute and Press Diophantus and Aegean University, Greece
Keyword(s):
Ambient Assisted Living, Risk Detection Algorithm, Bayesian Network, Congestive Heart Failure, Deviation Index, Remote Healthcare, Multi-layered Architecture, Sensors, Pervasive Computing.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Business Analytics
;
Cardiovascular Technologies
;
Computing and Telecommunications in Cardiology
;
Data Engineering
;
Decision Support Systems
;
Decision Support Systems, Remote Data Analysis
;
Health Engineering and Technology Applications
;
Knowledge-Based Systems
;
Symbolic Systems
Abstract:
Congestive heart failure (CHF) is a progressive condition in which the heart is no longer capable of supplying adequate oxygenated blood to the body. Since the incidence of CHF increases with age, mainly due to the development of heart failure risk factors the epidemic of CHF is expected to grow further in the coming decades and thus becoming an important public health problem. In this paper we present a risk detection system for CHF that uses a Bayesian Network (BN) combined with health measurements that can be taken in a home environment using ambient assisted living technologies. The algorithm is empowered by employing statistical and medical analysis of the stored biological data and the output can be used as a basis for triggering proper preventive interventions. The BN design was established by surveying the relevant literature and consulting the domain expert. The network content combines both biometric variables that are daily monitored and data from patient’s clinical histor
y as well as additional heart failure risk factors in terms of the EuroSCORE model. The predictive validity was tested with the involvement of the domain expert who specified proper validation rules in terms of criteria for detecting a CHF risk.
(More)