Data Mining based Prediction of Diabetes using Firefly Optimized Neural Network

Diabetes is an increasingly frequent disease. It is currently considered the disease of the century given the number of diabetics that continues to grow. In patients with cardiovascular disease, it is associated with a worse prognosis and greater comorbidity. Its early diagnosis makes it possible to initiate secondary prevention measures that have been shown to reduce the risk of ischemic events. Learning is the ability to improve with experience, to remember previous decisions and results in order to make better choices in the future in similar situations. Machine learning is a discipline of artificial intelligence. One of the most important motivations for the construction of machine learning systems lies in the fact that in many fields the experience is insufficient and the codification of the knowledge that describes it is limited, fragmented and therefore incomplete. Artificial Intelligence has generated significant advances in areas such as education, agriculture and medical care, in which it helps to detect and treat diseases such as cancer and diabetes much earlier than with the conventional methods. A Firefly algorithm Optimized Neural Network classifier is implemented to predict the diagnosis of diabetes mellitus based on the factors mentioned in patients from Pima Indians Diabetes dataset. Results are recorded on the basis of precision, recall and accuracy.