Artificial intelligence in personalized cardiovascular medicine and cardiovascular imaging

Abstract

The collection of large, heterogeneous electronic datasets and imaging from patients with cardiovascular disease (CVD) has lent itself to the use of sophisticated analysis using artificial intelligence (AI). AI techniques such as machine learning (ML) are able to identify relationships between data points by linking input to output variables using a combination of different functions, such as neural networks. In cardiovascular medicine, this is especially pertinent for classification, diagnosis, risk prediction and treatment guidance. Common cardiovascular data sources from patients include genomic data, cardiovascular imaging, wearable sensors and electronic health records (EHR). Leveraging AI in analysing such data points: (I) for clinicians: more accurate and streamlined image interpretation and diagnosis; (II) for health systems: improved workflow and reductions in medical errors; (III) for patients: promoting health with further education and promoting primary and secondary cardiovascular health prevention. This review addresses the need for AI in cardiovascular medicine by reviewing recent literature in different cardiovascular imaging modalities: electrocardiography, echocardiography, cardiac computed tomography, cardiac nuclear imaging, and cardiac magnetic resonance (CMR) imaging as well as the role of EHR. This review aims to conceptulise these studies in relation to their clinical applications, potential limitations and future opportunities and directions.

Keywords: Precision medicine; artificial intelligence (AI); cardiovascular imaging; deep learning (DL); machine learning (ML).

Figure 1

Schematic overview demonstrating the information flow and inter-links between various data sources.

Figure 2

Schematic representation of the relationships between general AI, narrow AI, ML and DL.

Figure 3

Schematic outlining the steps involved in generating risk prediction and probability scores with a deep convolutional neural network with (N) hidden layers.