Abstract: Millions of individuals worldwide are impacted by the serious public health problem of diabetes. Early detection and treatment are critical to prevent complications and improve outcomes. In this research, we provide a deep learning method for diabetes prediction utilizing big data analytics. We use a large dataset of electronic health records (EHRs) from a hospital system to train and test our model. The dataset contains demographic, clinical, and laboratory data for thousands of patients. We preprocess the data to handle missing values and standardize the features. We then use a deep neural network with multiple layers to learn the underlying patterns in the data and predict the likelihood of diabetes. Our findings demonstrate that our model beats numerous benchmark models in terms of precision, recall, and accuracy. To determine the features that are most essential for predicting diabetes, we also conduct a feature importance analysis. Our strategy can be applied to other chronic diseases and has the potential to enhance diabetes screening and diagnosis.
Keywords: Diabetes Prediction, Deep Learning
|
DOI:
10.17148/IJARCCE.2023.125276
