Abstract:
In the medical field, it is essential to predict diseases early to prevent them. Diabetes is one of the world's largest ongoing chronic metabolic disorders. In modern lifestyles, sugar and fat are typically present in our dietary habits, which have increased the risk of diabetes. To predict the disease, it is extremely important to understand its symptoms. Currently, machine-learning (ML) algorithms are valuable for disease detection.
ML algorithms are currently useful for the detection of diseases, but the previous research models are less accurate because they usually focused on pre-processing techniques, data balancing, and various types of supervised and semi supervised learning models. Therefore, it is required to find new technique with decision level fusion which would be able to integrate the accuracy of multiple machine learning algorithms with high disease detection accuracy. For this purpose, a fused ML model is proposed which uses two supervised machine-learning approaches including ANN and SVM followed by weight-based decision level fusion.
In the Machine Learning Fusion stage, Weight-based fusion is applied to the actual output of SVM and ANN results for final prediction. The fused trained model is then stored in the local storage for future use. Based on the user input, the fused model predicts whether the patient is diabetic or not. Through this diagnosis model, we can save several lives. Moreover, the death ratio of diabetes can be controlled if the disease is diagnosed, and preventative measures are taken in early stage.
