HD-MVCNN: High-density ECG signal based diabetic prediction and classification using multi-view convolutional neural network

Diabetes mellitus, also known as diabetes, is a medical condition marked by high blood sugar levels and impacts a large population worldwide. Treating diabetes is not feasible. It can be managed. Hence, it is crucial to promptly identify a diagnosis of diabetes. This study explores the effects of diabetes on the heart, focusing on heart rate variability (HRV) signals, which can offer valuable information about the existence and seriousness of diabetes through the evaluation of diabetes-related heart problems. Extracting crucial data from the irregular and nonlinear HRV signal can be quite challenging. Studying cardiac diagnostics involves a thorough analysis of electrocardiogram (ECG) signals. Traditional electrocardiogram recordings utilize twelve channels, each capturing a complex combination of activities originating from different regions of the heart. Examining ECG signals recorded on the body’s surface may not be an effective method for studying and diagnosing diabetic issues. The study introduces a research proposal utilizing a high-density resolution electrocardiogram (ECG) system with a minimum of 64 channels and multi-view convolutional neural network classification (HD-MVCNN) to address the mentioned challenges. This framework may help identify the hypoglycaemia effects on brain regions, leading to decreased complexity and increased theta and delta power during scalp electrocardiogram procedures. The convolutional architectural model primarily contributes to enhancement and optimization through its Stochastic Gradient Descent (SGD) along with convolutional layers and according to results, the HD-MVCNN demonstrated better stability and accuracy in comparison to traditional classification models. Thus, HD-MVCNN shows promise as a powerful method for classifying features in diabetes clinical data.