Journal Article

Wearable Devices in Healthcare Beyond the One-Size-Fits All Paradigm

Marconi, Francesco, Bignami, Elena Giovanna, Fornaciari, Anna, Bellini, Valentina, Fedele, Sara, Madeo, Mattia, Cerdelli, Erika, Panizzi, Matteo

2025

Overview

Wearable devices (WDs) are increasingly integrated into clinical workflows to enable continuous, non-invasive vital signs monitoring. Combined with Artificial Intelligence (AI), these systems can shift clinical monitoring from being reactive to predictive, allowing for earlier detection of deterioration and more personalized interventions. The value of these technologies lies not in absolute measurements, but in detecting physiological parameters trends relative to each patient’s baseline. Such a trend-based approach enables real-time prediction of deterioration, enhancing patient safety and continuity of care. However, despite their shared multiparametric capabilities, WDs are not interchangeable. This narrative review analyzes nine clinically validated devices, Radius VSM® (Masimo Corporation, Irvine, CA, USA), BioButton® (BioIntelliSense Inc., Redwood City, CA, USA. Distributed by Medtronic), Portrait Mobile® (GE HealthCare, Chicago, IL, USA), VitalPatch® (VitalConnect Inc., San Jose, CA, USA), CardioWatch 287-2® (Corsano Health B.V., The Hague, The Netherlands. Distributed by Medtronic), Cosinuss C-Med Alpha® (Cosinuss Gmb, Munich, Germany), SensiumVitals® (Sensium Healthcare Limited, Abingdon, Oxfordshire, UK), Isansys Lifetouch® (Isansys Lifecare Ltd., Abingdon, Oxfordshire, UK), and CheckPoint Cardio® (CheckPoint R&D LTD., Kazanlak, Bulgaria), highlighting how differences in sensor configurations, battery life, connectivity, and validation contexts influence their suitability across various clinical environments. Rather than establishing a hierarchy of technical superiority, this review emphasizes the importance of context-driven selection, considering care setting, patient profile, infrastructure requirements, and interoperability. Each device demonstrates strengths and limitations depending on patient population and operational demands, ranging from perioperative, post-operative, emergency, or post-Intensive Care Unit (ICU) settings. The findings support a tailored approach to WD implementation, where matching device capabilities to clinical needs is key to maximizing utility, safety, and efficiency.

• Publisher: MDPI AG
• Subject: Accountability / Accuracy / Algorithms / Artificial Intelligence / Batteries / Clinical deterioration / clinical monitoring / Clinical outcomes / context-driven selection / continuous monitoring / Decision making / Deep learning / Delivery of Health Care / ethical implications / Ethics / Heart rate / Hospitals / Humans / Hypoxemia / Length of stay / Machine learning / Medical personnel / Middleware / Monitoring, Physiologic - instrumentation / Monitoring, Physiologic - methods / multiparametric wearable devices / Oxygen saturation / Patient safety / perioperative care / Physiology / Privacy / Privacy, Right of / Sensors / Sepsis / Surveillance / Transparency / Vital Signs - physiology / Wearable computers / Wearable Electronic Devices