Deep Neural Network to Predict Diabetes A Data Science Approach

Diabetes has become a famous and lethal disease among the low medium-income countries. People could not overcome this deadly abnormal condition due to current lifestyle, food habit genetic transmittance. Medical practitioners provide advice prevent diabetic medications control as does have permanent cure. However, detection of is being tidy process deployment machine learning predictive models conduct smart diagnosis/detection vital in healthcare domain nowadays. Though several were built regard, deploying Deep Neural Network seems less focused. Therefore, model was with support complete preprocessing, class balancing, normalization, feature selection hyper-parameter tuning using cross-validated searching technique. The achieved 88% accuracy 0.88 ROC score standing out promising diagnosing/detecting diabetes.