Classification Model Analysis for the Prediction of Leptospirosis Cases.

Leptospirosis is a disease that affects mainly low-income populations, with an incidence of 500,000 cases per year worldwide[1]. The disease has symptoms often confused with other febrile syndromes, such as dengue, influenza and viral hepatitis. Improved diagnosis of patients with leptospirosis is very important for health professionals, epidemiological surveillance and primarily for rapid evaluation and appropriate treatment of patients. In this work, an analysis of the data mining techniques classification was performed, evaluating algorithms of the methods of Decision Tree, Classification Rules and Bayesian Classification. Of these, JRip was the model with the best performance, yielding 85% sensitivity and 81% specificity. The algorithms successfully predicted the disease and may represent a new tool to assist health professionals in the daily hospital routine, especially in endemic areas for leptospirosis, accelerating targeted treatment, and minimizing disease exacerbation and mortality. [ABSTRACT FROM AUTHOR]