Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective

•Clinicians seek a reliable one-time diagnostic system for diabetes diagnosis without several blood sugar tests.•We framed working data pre-processing steps for feature selection and missing value imputation.•We developed a deep neural network model for accurately predicting diabetes mellitus and determining the disease severity during diagnosis.•A train and test prediction accuracies of 99.01% and 97.25% are achieved with the PIMA Indian dataset, while 99.57% and 97.33% accuracies are achieved with the LMCH dataset.•A performance difference that ranges from 8.68% to 21.99% is achieved in comparison to state-of-the-art.•This work can be reproduced with the publicly available source code.