People from all around the world are afflicted by the fatal condition known as diabetes mellitus (DM). A timely diagnosis of DM is particularly advantageous because it may be managed before the beginning of the condition. In this work, different pre-processing methods for the diagnosis of DM are discussed and contrasted. Additionally, the accuracy of several methods for data mining has been evaluated depending on missing scores, with a particular emphasis on artificial neural networks (ANN) to handle missing data utilizing z-value and Min-Max procedures. IoT (Internet of Things) devices are used in this research to track the patients’ situations. Statistics are sent from IoT gadgets to smartphones for surveillance, and subsequently from smartphones to the web, where categorization is done. Employing a Python instrument, the simulation is carried out on the data sets that were obtained. The simulation findings demonstrate that the suggested strategy outperforms current state-of-the-art ensemble approaches in terms of accuracy pace, recall, precision, and f-value.