Random Forest-Based Prediction Models for Assessing Cardiovascular Disease Risk: Integrating Clinical and Genetic Factors

Abstract

This research investigates the adequacy of Irregular Forest-based expectation models in evaluating cardiovascular disease (CVD) hazards by joining clinical and hereditary variables. Leveraging a dataset comprising comprehensive clinical profiles and hereditary data, we prepared and assessed Arbitrary Woodland models near other machine learning calculations. Ours comes about illustrates that the Random Forest show outperformed Logistic Relapse, Support Vector Machine, and Slope Boosting in precision (85%), affectability (82%), specificity (88%), and zone beneath the recipient working characteristic bend (AUC-ROC) (0.92). Furthermore, the consideration of hereditary highlights altogether progressed the prescient execution, with the show accomplishing a precision of 88%, affectability of 86%, specificity of 90%, and AUC-ROC of 0.94. This study highlights the significance of coordination hereditary data for personalized hazard evaluation in CVD. The comparison with related works underscores the progressions made in leveraging machine learning for cardiovascular hazard forecast and conclusion. Our discoveries recommend that Irregular Forest-based models offer a promising approach for upgrading quiet results through precise chance evaluation, early location, and focused on preventive intercessions. Moving forward, encourage inquiry about is justified to illustrate fundamental pathophysiological components and direct accuracy medication approaches in cardiovascular wellbeing.