We conducted a systematic review of the literature for assessing the value of home monitoring for heart failure (HF) patients. The abstracts of 383 articles were read. We excluded those in which either no home monitoring was done or only the technical aspects of the telemedicine application were described. Forty-two studies met the selection criteria. We classified the results into feasibility (technical and institutional) and impact (on the clinical process, on patient health, on accessibility and acceptability of the health system, and on the economy). Evaluating the articles showed that home monitoring in HF patients is viable, given that: (1) it appears to be technically effective for following the patient remotely; (2) it appears to be easy to use, and it is widely accepted by patients and health professionals; and (3) it appears to be economically viable. Furthermore, home monitoring of HF patients has been shown to have a positive impact on: (1) the clinical process, supported by a significant improvement of patient follow-up by adjustment of treatment, diet or behaviour, as well as hospital readmissions and emergency visits reduction; (2) the patient's health, supported by a relevant improvement in quality of life, a reduction of days in hospital, and a decrease in mortality; and (3) costs resulting from the use of health resources.

No abstract

This paper deals with the application of the Support Vector Method (SVM) methodology to the Auto Regressive and Moving Average (ARMA) linear-system identification problem. The SVM-ARMA algorithm for a single-input single-output transfer function is formulated. The relationship between the SVM coefficients and the residuals, together with the embedded estimation of the autocorrelation function, are presented. Also, the effect of the numerical regularization is used to highlight the robust cost character of this approach. A clinical example is presented for qualitative comparison with the classical Least Squares (LS) methods.

No abstract