In recent decades, spiralling costs, an ageing population, and the rise of chronic diseases have propelled public healthcare systems into crisis. For many policy makers and health professionals, the solution resides in a move from a ‘one-size-fits-all’ model, to healthcare that is preventive, participatory, and tailored to the specific characteristics of individuals. 1
Two essential aspects of personalized healthcare – its data-centeredness and its participatory form – are brought together in self-tracking devices, wearable sensors, and mobile applications that allow users to collect, measure, and display data concerning virtually any form of bodily function and behavioral activity. 1
Over the past decade, several new smartphone applications and wearable mobile sensors that allow users to monitor sleep, food intake, exercise, blood sugar, mood, and a host of other physiological states and behaviours has permeated the consumer health landscape, bearing the promise of more cost effective, more optimal, and more efficient healthcare. 1
Wearable devices include wristbands, smartwatches, wearable mobile sensors, and other mobile hub medical devices that collect a large body of diverse data ranging from blood glucose parameters and exercise routines to sleep and mood. Wearable electronics exhibit unique characteristics in that they are flexible and/or stretchable, they are able to conform in shape to enable the development of novel wearable formulations including skin patches or even clothing.2 The technology used in wearable devices are sensor-based health-monitoring systems that include different flexible sensors. These sensors have the capability to measure physiological signs such as heart rate, electrocardiogram, body temperature, blood pressure, arterial oxygen saturation, and respiration rate. 3
Patient data can be collected through an active process by facilitating consumer reporting or passively through sensors in apps that communicate with devices through application programming interfaces (APIs); these data are then shared through data aggregators such as Apple’s HealthKit that pools data from multiple health apps. 4
Self-tracking devices facilitate individuals to be more involved in the process of managing their own health and can generate data that will benefit clinical decision making and research. Self-tracking device data has attracted the attention of medical and public health professionals as a key influencer in the move toward participatory and personalized healthcare. 1
Clinical Impact of Wearable Devices: Monitoring: At hospital. At Home. Acute or Chronic
With the adoption of digital health technologies, stakeholders are discovering the enabling effect of wearable device technology on patient-centric measurement of health markers. Frequent and continuous monitoring moving from the healthcare setting to the home setting can offer more precise and accurate assessments than traditional observational models. 5
Medical wearable devices are able to quantitatively assess patient’s health by tracking their status while they are away from the hospital or in a hospital-at-home environment. 3 Remote monitoring allows for timely intervention if conditions change, allowing for effective management of patients with acute medical conditions. 6 Moreover, the value of smart wearables monitoring should not be underestimated in an in-patient setting, where ambulatory patients in general wards are able to be more closely monitored, thereby minimizing the risk of missed deterioration, while at the same time reducing the burden on the nursing staff to continually monitor patients. Moving beyond this, the data collected from these monitoring devices can be analysed to create actionable insights.
In the post discharge setting, smartphones and connected devices may also be able to diagnose and characterize postoperative complications occurring after hospital discharge and facilitate remote care and trigger the need for intervention should complications arise. 7
Wearable devices also have the potential to help patients and providers manage chronic conditions including diabetes, Crohn’s disease, asthma, heart conditions, and chronic pain. 1 In cardiovascular disease specifically, wearable devices have been shown to reduce the chances of re-admission to hospital as well as lowering the mortality of patients with the help of implanted cardiac rhythm devices. 3
Financial impact of wearable devices
By allowing for earlier intervention, remote monitoring through medical wearable devices could improve clinical outcomes, lower resource utilization and improve quality of life. 6
The positive return-on-investment (ROI) for remote monitoring may be evidenced in a reduction of ED visits and/or hospitalizations. For example, RM could reduce the overall length of stay (LOS) and associated costs by admitting the patient only when it becomes necessary. 6
The improved overall health that personalized and mobile healthcare promise to deliver comprises more precisely calibrated health interventions, diagnoses and treatments, fewer side effects, extended life expectancy, the reduction of unnecessary consultations, improved quality of life and patient comfort, better planning, better prepared professionals, and increased treatment rates. 1
Additionally in the hospital setting, wearable monitoring assisted by AI-decision tools may result in timely interventions to prevent patient clinical deterioration, thus potentially reducing length of hospitalization, scale up of care and reducing costs.
The question is how do we leverage all the data that is collected, decide what is relevant and clinically meaningful and how do we translate this into clinical insights that are predictive and actionable?
Fusing artificial intelligence (AI) with functional electronic sensing
The next-generation of wearable electronic and photonic devices are advancing rapidly toward the era of artificial intelligence (AI) and internet of things (IoT), to achieve a higher level of comfort, convenience, connection, and intelligence. 3Recently, the technology fusion of emerging artificial intelligence (AI) with functional electronics has prompted the development of novel intelligent systems that can detect, analyze, and facilitate decisions about patient care or intervention with the assistance of pre-programmed machine learning assisted algorithms. In addition, benefitting from the 5G network, the acquisition rate of sensing data is able to satisfy the requirements of big data analysis and higher forms of AI. 2, 9, 10
Smart Monitoring and impact of AI to contextualize and focus data for the clinician
The advent of digital wearable technologies has enabled a plethora of physiological parameters to be monitored. Appropriately designed interconnected systems that incorporate wearable technology, wireless sensor and actuator networks (WSANs) and software applications have the potential to provide a good overview of the of the patient’s health status for a specific environmental condition, as well as being able to provide the appropriate healthcare services or intervention. 2 However, considering the multiple parameters that can be measured, it is essential to personalize the type of data collected for each patient, based on their underlying medical condition and willingness to be monitored, and ensure a level of integration between the various monitoring parameters to create a coherent clinical picture.
The rapid advance in AI and data processing, now present us with the capability of utilizing the power of AI to integrate and contextualize this data and focus the clinician’s attention on the most important areas requiring intervention and management.
CLEWMED solutions for patients deliver customizable high integration and real-time clinical optimization, actionable predictive clinical analytics and patient risk stratification. CLEW’s unique technology helps focus attention to where it is needed most, staying ahead of impending problems The platform utilizes the full range of available patient data to provide continuous predictions based on sophisticated machine learning algorithms and models. The CLEW platform offers high end integration of data collected from wearables and is able to contextualize this large data monitoring set into predictive and actionable insights. The solution enables early identification and intervention and patient context prioritization. The CLEW system interfaces with existing EMR systems and sensory wearable medical devices and can be deployed in the cloud.
- Sharon, T. Self-Tracking for Health and the Quantified Self: Re-Articulating Autonomy, Solidarity, and Authenticity in an Age of Personalized Healthcare. Technol. 2017; 30:93–121. https://doi.org/10.1007/s13347-016-0215-5
- Shi Q, Dong B, He T, Sun Z, Zhu J, Zang Z, et al. Progress in wearable electronics/photonics—Moving toward the era of artificial intelligence and internet of things. InfoMat. 2020 ;2:1131–1162. https://doi.org/10.1002/inf2.12122
- El Khatib M, Ahmed G.Management of Artificial Intelligence Enabled Smart Wearable Devices for Early Diagnosis and Continuous Monitoring of CVDS. International Journal of Innovative Technology and Exploring Engineering. 2019; 9:1211-1215. https://doi.org/10.35940/ijitee.L3108.119119
- Grundy Q, Held FP, Bero LA. Tracing the Potential Flow of Consumer Data: A Network Analysis of Prominent Health and Fitness Apps. J Med Internet Res. 2017;19(6):e233. https://doi.org/10.2196/jmir.7347
- Brooks K. Advancing Digital Endpoints in Clinical Trials. Contract Pharma. 14 December 2020. Available from https://www.contractpharma.com/contents/view_online-exclusives/2020-12-14/advancing-digital-endpoints-in-clinical-trials/ [Accessed 2 August 2021]
- Cummings J. TechFlash: At-home remote monitoring of COVID-19 patients. June 2020. Available from https://www.vizientinc.com/-/media/documents/sitecorepublishingdocuments/secured/collaboratives/techflash_remote_monitoring_jun_2020.pdf [Accessed 9 June 2021]
- Michard F. Smartphones and e-tablets in perioperative medicine. Korean J Anesthesiol. 2017 Oct;70(5):493-499. https://doi.org/10.4097/kjae.2017.70.5.493
- Rodrigues MJ, Postolache O, Cercas F. Physiological and Behavior Monitoring Systems for Smart Healthcare Environments: A Review. Sensors 2020; 20:2186; doi:10.3390/s20082186 https://www.mdpi.com/1424-8220/20/8/2186/pdf
- Li J-a, Ma Z, Wang H-t, Gao X-x, Zhou Z, Tao R-w, et al. Skin-Inspired Electronics and Its Applications in Advanced Intelligent Systems. Intell. Syst. 2019;1:1900063. https://doi.org/10.1002/aisy.201900063
- Wang C, Dong L, Peng D, Pan C. Tactile Sensors for Advanced Intelligent Systems. Intell. Syst. 2019;1:1900090. https://doi.org/10.1002/aisy.201900090