Early detection of decompensation conditions in heart failure patients by knowledge discovery: The HEARTFAID approaches

Abstract

For the clinical management of chronic heart failure (CHF) patient, a crucial mid-long term goal is the early detection of new acute decompensation events, for improving quality of outcomes while reducing costs on the healthcare system. Within the relevant clinical protocols and guidelines, a general consensus has not been reached about the prediction of further decompensations, even though many different evidence- based indications are known. Under this respect we adopted Knowledge Discovery (KD) approaches as a practical and effective solution to extract new potentially useful facts from repositories of pertinent clinical data. In fact, we present the KD task which has been implemented into the EU FP6 Project HEARTFAID (www.heartfaid.org), aiming at developing an innovative knowledge based platform of services for more effective and efficient clinical management of heart failure within elderly population. 49 CHF patients were recurrently visited by cardiologist, measuring clinical parameters taken from clinical guidelines and evidence- based knowledge. Also general information about each patient was taken into account for the analysis. Several KD algorithms were applied on collected data, obtaining different binary classifiers performing the early detection of new acute decompensation events. Some of these models are easy-to-understand and their consistency was directly evaluated by the cardiologists. Moreover, high percentage of correct classifications (above 87%) was obtained by using suitable validation approaches.