Abstract

Depressive and anxiety disorders stem from an unhealthy lifestyle perpetuated by the hectic lives of the modern world. In an effort to manage these symptoms, there is a tendency to turn to drug usage, smoking, and binge drinking. All of these things are the main causes of cardiovascular disease, tumors, and other major ailments. The World Health Organization, which is part of the UN has established that cardiovascular disease (CVD) is the primary cause of death worldwide. They have proliferated throughout time and are currently overtaxing national healthcare systems. Clinical evaluation of the illness severity that is prompt, precise, and accurate is essential at this point. This article presented an efficient deep learning-based approach for CVD prediction to improve making choices and logistical preparation in healthcare systems. Cytokines are regarded as a crucial component for the forecast. This work acknowledges the urgency and suggests a remedy: using deep learning to quickly and correctly forecast the severity of CVD. The work shows the efficacy of a Long Short Term Memory (LSTM) classification in CVD prediction by evaluating publically accessible information from the MIMIC-II database. Findings show a significant increase in prediction accuracy, providing crucial assistance for medical decision-making and logistics scheduling. To summarize, this study shows the critical need to address cardiovascular disease (CVD) and provides a viable approach using sophisticated prediction methods, with the ultimate goal to decrease the strain on health care systems while improving patient outcomes.