摘要
The COVID-19 pandemic has profoundly impacted global health, with far-reaching consequences beyond respiratory complications. Increasing evidence highlights the link between COVID-19 and cardiovascular diseases (CVD), raising concerns about long-term health risks for those recovering from the virus. This study rigorously investigates the influence of COVID-19 on cardiovascular disease risk, focusing on conditions such as heart failure and myocardial infarction. Using a dataset of 52,683 individuals aged 30 to 80, including both COVID-19 survivors and those unaffected, the study employs machine learning models—logistic regression, decision trees, and random forests—to predict cardiovascular outcomes. The multifaceted approach allowed for a comprehensive evaluation of the model’s predictive capabilities, with logistic regression yielding the highest Binary F1 score of 0.94, effectively identifying cardiovascular risks in both the COVID-19 and non-COVID-19 groups. The correlation matrix revealed significant associations between COVID-19 and key symptoms of heart disease, emphasizing the need for early cardiovascular risk assessment. These findings underscore the importance of machine learning in enhancing early diagnosis and developing preventive strategies for COVID-19-related heart complications. Ultimately, this research contributes to a broader understanding of the pandemic’s lasting health effects, highlighting the critical role of cardiovascular care in post-COVID-19 recovery.
The COVID-19 pandemic has profoundly impacted global health, with far-reaching consequences beyond respiratory complications. Increasing evidence highlights the link between COVID-19 and cardiovascular diseases (CVD), raising concerns about long-term health risks for those recovering from the virus. This study rigorously investigates the influence of COVID-19 on cardiovascular disease risk, focusing on conditions such as heart failure and myocardial infarction. Using a dataset of 52,683 individuals aged 30 to 80, including both COVID-19 survivors and those unaffected, the study employs machine learning models—logistic regression, decision trees, and random forests—to predict cardiovascular outcomes. The multifaceted approach allowed for a comprehensive evaluation of the model’s predictive capabilities, with logistic regression yielding the highest Binary F1 score of 0.94, effectively identifying cardiovascular risks in both the COVID-19 and non-COVID-19 groups. The correlation matrix revealed significant associations between COVID-19 and key symptoms of heart disease, emphasizing the need for early cardiovascular risk assessment. These findings underscore the importance of machine learning in enhancing early diagnosis and developing preventive strategies for COVID-19-related heart complications. Ultimately, this research contributes to a broader understanding of the pandemic’s lasting health effects, highlighting the critical role of cardiovascular care in post-COVID-19 recovery.
