ECNN-MmIC: an Enhanced Convolutional Neural Network model with hybrid optimization strategy techniques for diabetes and cardiovascular disease comorbidity

Abstract

The increasing prevalence and clinical interrelationship of diabetes mellitus and cardiovascular disease (CVD) present substantial challenges to healthcare systems, creating a need for efficient and robust diagnostic approaches to support early intervention and continuous patient monitoring. This study presents ECNN-MmIC, an intelligent cloud-oriented Internet of Medical Things (IoMT) framework that integrates an Enhanced Convolutional Neural Network (ECNN), Bayesian Optimization (BO), and the Salp Swarm Algorithm (SSA) for joint diabetes and CVD prediction, hyperparameter optimization, and feature selection. The experimental analysis was conducted using the publicly available Diabetes in Bangladesh (DiaBD) medical dataset comprising 5,288 patient records collected from communities across 63 unions in Bangladesh, representing urban, semi-urban, and rural populations aged 21–80 years. The dataset incorporates 14 demographic, physiological, anthropometric, and clinical predictors, including age, gender, glucose level, pulse rate, systolic and diastolic blood pressure, BMI, hypertension, family histories of diabetes and hypertension, CVD, and stroke, thereby providing clinically relevant information for investigating diabetes–CVD comorbidity. The ECNN-MmIC framework was evaluated against Logistic Regression, SVM, Random Forest, DNN, conventional CNN, LSTM, and CNN-LSTM. Experimental results showed that ECNN-MmIC achieved 98.73% accuracy, 98.41% precision, 98.12% recall, 98.26% F1-score, 99.05% specificity, and 99.31% AUC for diabetes detection, while achieving 98.21% accuracy and 99.04% AUC for CVD prediction. The proposed hybrid optimization strategy also reduced training time from 412 s to 341 s and produced lower prediction errors compared with the evaluated optimization approaches. Statistical validation using stratified 10-fold cross-validation, confidence interval analysis, paired t-tests, Cohen’s Kappa, Matthews Correlation Coefficient, and error analysis demonstrated stable predictive performance. These findings indicate the potential of ECNN-MmIC as a data-driven clinical decision-support framework for diabetes–CVD comorbidity prediction, although external and prospective clinical validation remains necessary before real-world deployment.