Lélis VM, et al. – This study was designed to describe the development of statistical classifiers to help diagnose meningococcal meningitis, i.e. the most severe, infectious and deadliest type of this disease. Researchers aimed at finding a mechanism able to determine whether a patient had this type of meningitis from a set of symptoms that could be directly observed in the earliest stages of this pathology. Results indicated the utility of the developed model in leading to a non–invasive and early diagnosis of this pathology. This seemed especially useful in less developed areas, where the epidemiologic risk is usually high and medical expenses, sometimes, unaffordable.

• In Brazil, immediate hospitalization and the beginning of a treatment with invasive tests and medicines were observed in all suspected cases.
• In less developed regions, this expensive procedure seemed unaffordable.
• For this purpose, a dataset of 22,602 records of suspected meningitis cases was gathered together from the Brazilian state of Bahia.
• Researchers applied seven classification techniques from input data of nine symptoms and other information about the patient such as age, sex and the area they live in, and performed a 10 cross–fold validation.
• For diagnosing the meningococcal meningitis, the techniques applied proved suitable.
• They computed several indexes, such as precision, recall or ROC area, to indicate the accuracy of the models.
• All of them seemed to provide good results, but the best corresponds to the J48 classifier with a precision of 0.942 and a ROC area over 0.95.