Hybrid Convolutional Neural Networks for PIMA Indians Diabetes Prediction

This paper explores developing and validating a hybrid classification model for assessing the risk of diabetes among the PIMA Indian population, a community known for its higher susceptibility to diabetes. Leveraging a comprehensive dataset that includes demographic information, genetic markers, lifestyle factors, and historical health records, our proposed hybrid convolutional neural networks (CNNs) employ advanced machine learning algorithms to classify the likelihood of diabetes onset. The proposed hybrid CNN models utilize unique features of machine learning models and a CNN architecture. The research aims to contribute to early detection and prevention strategies, ultimately improving health outcomes within the PIMA Indian community. Our analysis explores traditional machine learning models such as logistic regression, k-nearest neighbors (kNN), Gaussian Naive Bayes (GNB), support vector machine (SVM), decision tree (DT), random forest (RF), AdaBoost, LightGBM, XGBoost, CatBoost, and hybrid CNN models applied to the PIMA Indians Diabetes Database, focusing on classifying diabetes onset. The study provides insights into model performance, classification accuracy, and relevant evaluation metrics, allowing for a comprehensive assessment of the dataset's utility in diabetes prediction tasks. The outcomes of this study are anticipated to contribute significantly to the field of diabetes prediction, specifically tailored to the distinct characteristics of the PIMA Indian population. The developed hybrid CNN models promise to inform targeted interventions, preventive strategies, and personalized healthcare approaches, aiming to mitigate the burden of diabetes within the PIMA Indian community. As we delve into machine learning for health prediction, this research seeks to refine predictive capabilities and empower communities to manage health risks proactively.