Proactive support of patients with chronic diseases such as Congestive Heart Failure is vital since the recovery from a critical condition usually presents complications and it is not always possible. Although emergency situations may occur without prior warning, still in the majority of emergency cases, there are “signals” that precede their appearance. By capitalizing on technology developments that are changing the way how healthcare services are provided, we propose a multi-parameter and multi-level data analysis approach in order to detect possible alarms which can then trigger proper preventive medical interventions. The main contribution of the presented approach is a methodology that combines selected health parameters that can be measured in a home environment using ambient assisted living technologies, with clinical history, in order to design a risk detection system for a chronic disease based on a Bayesian reasoning network. The added value of the proposed approach is that the system not only collects, processes and transmits vital measurements to the healthcare experts but also detects risks within the collected data. The system developed is discussed in detail as well as the validation process performed both on a technical and a medical level.
CITATION STYLE
Goumopoulos, C., & Lappa, A. (2018). Home-based multi-parameter analysis for early risk detection and management of a chronic disease. In Communications in Computer and Information Science (Vol. 869, pp. 46–68). Springer Verlag. https://doi.org/10.1007/978-3-319-93644-4_3
Mendeley helps you to discover research relevant for your work.