AI and ML in the Treatment of Cardiovascular Diseases

Abstract

Computer intelligence, also known as artificial intelligence (AI), aims to imitate human intelligence in machines. AI discoveries have significantly benefited many scientific, technological, and medical disciplines. Among several diseases, one of the important causes of death is cardiovascular disease, a significant threat to human fitness. Initial applications of Al and Machine Learning include remote follow-ups, prescription reminders, disease counseling, and early symptom alerts. Activities utilizing machines are far less unpredictable since there is little chance of human error. Large-scale statistical analysis using AI and ML can help clinicians generate more accurate forecasts using historical data. The goal of this evaluation is to make available doctors with clinical research practices and describe the cutting-edge state of AI and ML applied to cardiovascular medicinal medication. Applications based on AI and ML are widely used in various scientific, technological, and medical domains. Since the 1960s, it has been investigated how advanced computational capabilities of machines could be used in the clinical diagnosis of various diseases and medicine. Recently, there has been a resurgence of interest in their application in clinical practice because of developments in various computing fields, machine learning algorithms, and advanced neural networks that behave similarly to the human brain. Various applications in cardiovascular risk assessment, imaging, and emerging therapeutic targets in cardiovascular therapy are based on AI. This chapter aims to discuss various AI applications, such as ML and DL, and how they are used in cardiovascular care. AI-based solutions have improved knowledge of various heart failure and congenital heart disease phenotypes. These applications have produced newer approaches to cardiovascular drug therapy, newer treatment techniques for various types of cardiovascular illnesses, and post-marketing analyses of pharmaceuticals. Data privacy, poorly chosen/outdated data, selection bias, and inadvertent perpetuation of historical biases/stereotypes in the data are some of the difficulties in the clinical application of AI-based applications and the interpretation of the results, which might result in incorrect conclusions. However, AI is a revolutionary technology with enormous potential for the healthcare industry.

Ähnliche Arbeiten