Prediction of Diseases in the Elderly in Manabí Through Big Data Technologies

Abstract

In the last decade, data collection and analysis have increased considerably in many fields of society. Big Data analysis has begun to play a fundamental role in the advancement of practices and research, as well as in the area of health. In this sense, data mining is a tool that allows you to find useful behavior patterns for decision-making in medicine or clinics, as well as predicting diseases. CVDs are one of the main causes of death in older adults and in the province of Manabí there are no studies reported on the analysis of risk factors for this disease in the elderly population. This research compares the performance of 13 learning algorithms to predict the risk of cardiovascular diseases (CVD) in the population of Manabí, the dataset used is composed of 604 participants, from a study by the National Institute of Statistics and Census (INEC) on health, the well-being of the elderly. The performance of the model was measured by the area under the curve (AUC), obtaining that the model with the best performance is the Random Forest, from which the prediction was made and the value of the variables could be obtained through the Shapley index or more significant risk factors in CVD. In Manabi, these are: if you have shortness of breath, the value of stature_altura if you have taken medication and may or may not have persistent dizziness.