Abstract
Despite significant advancements in diagnosis and disease management, cardiovascular (CV) disorders remain the No. 1 killer both in the United States and across the world, and innovative and transformative technologies such as artificial intelligence (AI) are increasingly employed in CV medicine. In this chapter, the authors introduce different AI and machine learning (ML) tools including support vector machine (SVM), gradient boosting machine (GBM), and deep learning models (DL), and their applicability to advance CV diagnosis and disease classification, and risk prediction and patient management. The applications include, but are not limited to, electrocardiogram, imaging, genomics, and drug research in different CV pathologies such as myocardial infarction (heart attack), heart failure, congenital heart disease, arrhythmias, valvular abnormalities, etc.
TopIntroduction
Cardiovascular (CV) diseases claim the greatest number of deaths both worldwide and across the United States (Virani et al., 2021). The CV healthcare costs are enormous despite several advancements in diagnostic and therapeutic products. The CV system can be negatively impacted at various clinical levels. These broadly include heart valve abnormalities such as stenosis (narrowing) or regurgitation (backflow), myocardial infarction (heart attack), heart failure, congenital heart disease (birth defects) and arrhythmias (electrical defects). Thus, novel technologies such as those offered by artificial intelligence (AI) has potential to enhance further progress in the field and may offer significant improvements in health outcomes along with reductions in costs.
As one of the fastest emerging technologies, AI plays major roles in practically every sector of our daily lives. For example, virtual assistants such as Alexa, Siri or Google Assistant can help customers perform searches, order products online, answer questions, set reminders, adjust local environment, etc. Many e-commerce websites improve customers’ online shopping experience with personalized recommendations and more streamlined buying processes. Voice verification, facial recognition, and biometric systems have been widely used to enhance security and surveillance.
AI also plays an increasingly important role in healthcare. AI and Machine Learning (ML) techniques have been widely used to improve both patient care and administrative processing. ML and Deep Learning (DL) techniques have been successfully applied to diagnose, analyze, and predict the course of various types of diseases, and in monitoring patient health conditions as well. Natural Language Processing (NLP) techniques can be used to understand and classify unstructured clinical documentations and assist in structuring patient and medication information. AI systems and robotics are also helping with day-to-day administrative and routine functions of health facilities, thus reducing physical workload of medical personnel, minimizing human errors and maximizing efficiency.
AI and ML techniques have been applied to improve CV research and health (Figure 1). This chapter is aimed to provide an overview of AI advancements in diverse areas within the CV field, however, it is not meant be a complete resource of all developments. For a comprehensive collection, the readers are suggested to explore several published review articles (Antoniades, Asselbergs, & Vardas, 2021; Benjamins, Hendriks, Knuuti, Juarez-Orozco, & van der Harst, 2019; C. Krittanawong et al., 2019; Mathur, Srivastava, Xu, & Mehta, 2020; Quer, Arnaout, Henne, & Arnaout, 2021). AI will also be discussed in the context of aforesaid disorders along with imaging, basic and biomedical sciences, precision medicine, drug discovery and development and robotics. The Coronavirus Disease 2019 (COVID-19) pandemic has significantly affected the CV health as well, (Abu Mouch et al., 2021; Chung et al., 2021; Farshidfar, Koleini, & Ardehali, 2021; Gedefaw et al., 2021; Nishiga, Wang, Han, Lewis, & Wu, 2020; Patil, Singh, Henderson, & Krishnamurthy, 2021; Rosner et al., 2021; Wenger & Lewis, 2021; Yiangou, Davis, & Mummery, 2021), however, this chapter will not delve into the topic, as a separate chapter is dedicated for COVID-19 in this volume. Before we dive into the clinical and biomedical aspects, we shall first introduce state-of-the-art AI and ML techniques, and subsequently discuss how those techniques are applied and are beneficial in diverse CV applications.
Figure 1. Schematic of areas where Artificial Intelligence and Machine Learning impact Cardiovascular sciences and medicine.
Key Terms in this Chapter
Genome: Complete set of genetic instructions needed to build and sustain an organism. This may include interactions of genes with one another and the environment (epigenome).
Artificial Intelligence: Artificial intelligence is the ability of computer systems to perform tasks that normally require human intelligence.
Myocardial Infarction: Sometimes referred as heart attack, myocardial infarction occurs when blood flow to the heart tissues is interrupted secondary to obstruction from buildup of fat and other substances within blood vessels called coronary arteries.
Machine Learning: A study of computer algorithms that can access data and use the data to learn by themselves.
Arrhythmia: Arrhythmias are heart rhythm abnormalities that occur when electrical impulses that coordinate heartbeats are anomalous and can lead to impaired heart contraction or relaxation or both.
Deep Learning: A class of machine learning based on artificial neural networks that include multiple hidden layers to progressively extract higher level features from the raw data.
Heart Failure: Heart failure occurs when heart muscle does not pump sufficient blood to meet the demands of the body secondary to several conditions including heart attack, hypertension, heart valve disease, congenital (birth) heart defects, etc.