Applying Artificial Intelligence to Wearable Sensor Data to Diagnose and Predict Cardiovascular Disease: A Review

Abstract

Cardiovascular disease (CVD) is the world's leading cause of mortality. There is significant interest in using Artificial Intelligence (AI) to analyse data from novel sensors such as wearables to provide an earlier and more accurate prediction and diagnosis of heart disease. Digital health technologies that fuse AI and sensing devices may help disease prevention and reduce the substantial morbidity and mortality caused by CVD worldwide. In this review, we identify and describe recent developments in the application of digital health for CVD, focusing on AI approaches for CVD detection, diagnosis, and prediction through AI models driven by data collected from wearables. We summarise the literature on the use of wearables and AI in cardiovascular disease diagnosis, followed by a detailed description of the dominant AI approaches applied for modelling and prediction using data acquired from sensors such as wearables. We discuss the AI algorithms and models and clinical applications and find that AI and machine-learning-based approaches are superior to traditional or conventional statistical methods for predicting cardiovascular events. However, further studies evaluating the applicability of such algorithms in the real world are needed. In addition, improvements in wearable device data accuracy and better management of their application are required. Lastly, we discuss the challenges that the introduction of such technologies into routine healthcare may face.

Keywords: artificial intelligence (AI); cardiovascular disease; deep learning (DL); machine learning (ML); wearable sensor devices.

Figure 1

Deep learning-based methods that could extract features automatically, while classical machine learning needs human experts to extract features from the raw data, identify cardiac structural or functional abnormalities or make proactive predictions.

Figure 2

Illustration of types and methods of extracting features.

Figure 3

An example of ECG signals.

Figure 4

Classification of classical machine learning methods.

Figure 5

Supervised Machine Learning methods [20,28,38].

Figure 6

Classification of Deep learning methods.

Figure 7

The numbers of types of disease in the 79 studies between January 2018 and April 2022 that are related to detection/prediction from the identified studies.

Figure 8

The number of studies applying each type of AI models for detection of AF (there are 14 papers related to ML, 12 related to DL in the identified papers between January 2018 and April 2022).