Design and Development of an Intelligent Decision Support System Applied to the Diagnosis of Patients Susceptible to Heart Failure

Heart failure (HF) is a cardiovascular disease characterized by the inability of the heart to pump the necessary amount of blood. According to the World Health Organization, cardiovascular pathologies are the leading cause of death worldwide, so their importance and the relevance of their study are unquestionable. In this sense, achieving an early diagnosis is a very convenient, but also complex and challenging, task due to the lack of protocols and guidelines that standardize the diagnostic process. Given this background, this work addresses the design and development of an intelligent decision support tool applied to the diagnosis of patients susceptible to HF. To this end, based on clinical and demographic data (presence of comorbid conditions and results of clinical tests) of the patients, and implementing a Machine Learning classification algorithm focused on their management, it is possible to obtain a risk metric value related to the hazard of suffering from severe HF. Initial testing of the system on the test dataset yields promising results, supported by AUC values close to 0.90.