Different machine learning language models for cardiovascular disease risk prediction: a systematic review

Abstract

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, prompting the urgent need for accurate and efficient predictive tools. This systematic review evaluates the efficacy of various machine learning algorithms in predicting cardiovascular disease risk by analyzing multiple studies that employed diverse techniques, including support vector machines, decision trees, and neural networks. The results consistently demonstrate that machine learning algorithms outperform traditional risk assessment models in predicting critical outcomes such as myocardial infarction, heart failure, and stroke, with advanced methods like gradient boosting and deep learning models showing superior accuracy. The review highlights the potential of these technologies to enhance clinical decision-making and improve patient outcomes, while also recognizing challenges such as implementation barriers and the need for validation across broader populations. Furthermore, the review underscores the transformative potential of machine learning in cardiovascular risk assessment, emphasizing the necessity for continued validation and adaptation to diverse patient groups. These findings affirm the growing role of artificial intelligence in revolutionizing cardiovascular care through early diagnosis and precise risk stratification, while also addressing the strengths and limitations of AI-based tools.

Ähnliche Arbeiten