PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Colantonio S., Salvetti O. Temporal analysis of remotely sensed data for the assessment of COPD patients' health status. In: International Joint Conference CISIS’12-ICEUTE´12-SOCO´12 Special Sessions (Ostrava, Czech Republic, 5-7 Settembre 2012). Proceedings, pp. 457 - 466. Álvaro Herrero, Václav Snášel, Ajith Abraham, Ivan Zelinka, Bruno Baruque, Héctor Quintián, José Luis Calvo, Javier Sedano, Emilio Corchado. (Advances in Intelligent Systems and Computing, vol. 189). Springer-Verlag, 2013.
 
 
Abstract
(English)
In the last years, ICT-based Remote Patients' Monitoring (RPM) programmes are being developed to address the continuously increasing socioeconomic impact of Chronic Obstructive Pulmonary Disease (COPD). ICTbased RPM assures the automatic, regular collection of multivariate time series of patient's data. These can be profitably used to assess patient's health status and detect the onset of disease's exacerbations. This paper presents an approach to suitably represent and analyze the temporal data acquired during COPD patients' tele-monitoring so as to extend usual methods based on e-diary cards. The approach relies on Temporal Abstractions (TA) to extract significant information about disease's trends and progression. In particular, the paper describes the application of TA to identify relevant patterns and episodes that are, then, used to obtain a global picture of patient's conditions. The global picture mainly consists of TA-based qualitative and quantitative features that express: (i) a characterization of disease's course in the most recent period; (ii) a summarization of the global disease evolution based on the most frequent pattern; and (ii) a profiling of the patient, based on anamnesis data combined with a summary of disease progression. The paper focuses on the description of the extracted features and discusses their significance and relevance to the problem at hand. Further work will focus on the development of intelligent applications able to recognize and classify the extracted information.
URL: http://www.springerlink.com/content/k7v13152827243k3/
DOI: 10.1007/978-3-642-33018-6_47
Subject Temporal Analysis
Patients' Monitoring
Temporal Abstractions
I.2.4 Knowledge Representation Formalisms and Methods
I.2.1 Applications and Expert Systems


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional