Advances in wearable device applications towards personalized cardiovascular health solutions: A machine learning perspective

Abstract

The integration of wearable electronic devices (WEDs) with artificial intelligence and machine learning (AI/ML) is transforming cardiovascular healthcare by enabling continuous, non-invasive, and personalized monitoring beyond conventional clinical environments. Recent advances in wearable sensing technologies, smart materials, and wireless communication have expanded the ability to capture rich multimodal cardiovascular data, including ECG, PPG, blood pressure surrogates, and activity-related biomarkers; and thus increased their adoption. Nevertheless, issues such data volume, privacy and security and inefficient utilization persist. ML/AI integration promises critical improvement in the use of wearable devices for healthcare monitoring and personalized care. This review presents the innovative approaches of different machine learning techniques adopted in healthcare wearable devices. It highlights the advances in wearable device technologies and the challenges of machine learning integrated applications. Major application areas reviewed include hypertension risk stratification, atrial fibrillation and arrhythmia detection, myocardial infarction identification, congestive heart failure monitoring, and remote cardiovascular surveillance. Finding suggests that ML-enabled wearable electronics hold great promise in the personalized care paradigm, howbeit, addressing privacy, data security, and ethical challenges will assist to further drive its adoption and real-world implementation.