EUCARDIA: a web-based platform for the CVD prediction using ML techniques in the Greek population

Statistical models used to estimate cardiovascular disease (CVD) risk often present methodological constraints, leading to overestimation or underestimation of the total CVD risk. The aim of this study was to develop and implement a web-based machine learning (ML) platform to predict personalized 10-year CVD risk for the Greek population.

The retrospective study included clinical and demographic data from 3290 participants without CVD. The CVD risk prediction model was based on two classifiers. The first was a binary classifier to estimate the occurrence of CVD, and the second was a multiclass classifier designed to replicate SCORE2 risk stratification categories. The selection of appropriate algorithms for integration into the platform was based on the receiver operating characteristic area under the curve (ROC-AUC) evaluation metric. To support clinicians, the platform was integrated with scientific libraries to retrieve the most relevant literature based on the features that most influence the model's decision-making.

The Voting Ensemble algorithm was selected for the binary classifier, achieving an area under the receiver operating characteristic curve (AUC-ROC) of 0.78. For the multiclass classifier, the selection algorithm was Stacking Ensemble, which yielded an AUC-ROC of 0.97. The comparison between the ML and the statistical model HellenicSCORE showed that the binary classifier performed better in all metrics except accuracy, for which HellenicSCORE had a higher value. The CVD risk prediction model and the integration with scientific libraries were successfully developed and deployed as a web-based platform.

The pilot run of the platform showed that it could be used as a reliable tool for CVD risk assessment, outperforming traditional statistical models.