An Aquila-optimized SVM classifier for Diabetes prediction

In the medical industry, earlier prediction of diseases is essential. The dietary habits of humans in modern lifestyles are often high in sugar and fat, raising the risk of Diabetes. According to current research, Diabetes can be managed if it is detected early. Understanding the disease's symptoms is critical for making predictions about it. This means that a prediction method that uses a computer and analyses data from the affected person to find any potential contamination can be a valuable tool for helping both doctors and patients. One difficulty with this technique is that the detection accuracy must be good for the system to be dependable. Machine learning (ML) techniques are helpful right now for identifying diseases. However, unstructured healthcare data contain inappropriate information that can degrade classifiers' prediction accuracy. Therefore, an efficient optimization method must be utilized to eliminate irrelevant data and improve prediction accuracy. An accurate dataset of symptoms that can be used for a more precise diabetes diagnosis can be produced using optimization approaches. This work demonstrates applying a new hybrid optimization technique called Aquila Optimized (AO) Support Vector Machine (AO-SVM) to improve diabetes prediction accuracy. Here SVM is used for the classification, and the Aquila algorithm is used for optimizing SVM. The results show that the proposed method achieved a maximum accuracy rate of 96%, an execution time of 0.42s, the precision of 92.5 %, a recall rate of 92.1 %, and an F1-Score value of 0. 91. The suggested AO-SVM model outperformed all other existing classification models regarding classification accuracy and other parameters.