Proposta e avaliação de um modelo para predição da morbidade e mortalidade em pacientes diagnosticados com taquicardia ventricular

Abstract

According to the World Health Organization, cardiovascular diseases are the leading cause of death in the world. Thousands of people die every year due to complications caused by this type of disease. In this sense, cardiologists seek early diagnosis, preventing the disease from reaching the pathological phase (i.e. the stages where limitations arise and become increasingly greater for its bearers). In the context of tachycardia-type arrhythmias, patients need to adopt the continuous use of medication and change habits to reduce the impact caused by this type of disease, thus providing a healthier life. Therefore, this study proposes and evaluates a morbidity and mortality prognostic model for patients diagnosed with ventricular tachycardia. The proposed model considers the scenario where the patient diagnosed with ventricular tachycardia will develop heart failure (HF) and ventricular fibrillation (VF). In this scenario, we used the CHA2DS2-VASc score to predict the risk of stroke, TIA and Systemic Embolism for the VF scenario. In addition to a combination of the CHA2DS2-VASc with the score generated from the patient’s habits, to be able to categorize the patient within NYHA classes, which in turn generates a morbidity and mortality level for each category. Computational techniques such as the use of SVM,KNN, Neural Networks, Random Trees and Naïve Bayes were used to validate the system. The model achieved its best results by validation with Support Vector Machines (SVM), with an accuracy of 0.997, F1, precision and recall of 0.976. From these classifications and predictions, it is possible to provide the cardiologist with a higher level of information, optimizing decision making, impacting on the adopted treatment, interventions, and patient follow-up.