This research study focuses on advancing healthcare applications through machine learning by specifically targeting the classification and prediction of diabetes. The primary objective is to develop and evaluate machine learning models for accurately identifying and predicting the presence of diabetes based on various patient parameters. The research utilizes a dataset that includes measurements such as blood pressure, weight, height, BMI, and glucose levels collected through sensors. The data is transferred from the sensors to a local computer and then to the cloud, where healthcare professionals and patients can access it through a mobile application. The machine learning approach involves the development and training of two models: linear regression and Artificial Neural Network (ANN). These models utilize the input parameters to predict the health condition of patients. Additionally, the research employs statistical analyses and performance evaluations to assess the accuracy and reliability of the models. The results demonstrate that the ANN model achieves an impressive accuracy rate of 100%, while the linear regression model achieves 98.3%. These findings highlight the potential of machine learning in accurately predicting patient health conditions and assisting healthcare professionals in making informed decisions. The study contributes to the growing body of knowledge in healthcare applications of machine learning and emphasizes the importance of leveraging advanced technologies for improved patient care and management