Medical Wearables Research Articles

DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors

Modern advances in machine learning (ML) and wearable medical sensors (WMSs) in edge devices have enabled ML-driven disease detection for smart healthcare. Conventional ML-driven methods for disease detection rely on customizing individual models for each disease and its corresponding WMS data. However, such methods lack adaptability to distribution shifts and new task classification classes. In addition, they need to be rearchitected and retrained from scratch for each new disease. Moreover, installing multiple ML models in an edge device consumes excessive memory, drains the battery faster, and complicates the detection process. To address these challenges, we propose DOCTOR, a multi-disease detection continual learning (CL) framework based on WMSs. It employs a multi-headed deep neural network (DNN) and a replay-style CL algorithm. The CL algorithm enables the framework to continually learn new missions in which different data distributions, classification classes, and disease detection tasks are introduced sequentially. It counteracts catastrophic forgetting with either a data preservation (DP) method or a synthetic data generation (SDG) module. The DP method preserves the most informative subset of real training data from previous missions for exemplar replay. The SDG module models the probability distribution of the real training data and generates synthetic data for generative replay while retaining data privacy. The multi-headed DNN enables DOCTOR to detect multiple diseases simultaneously based on user WMS data. We demonstrate DOCTOR’s efficacy in maintaining high disease classification accuracy with a single DNN model in various CL experiments. In complex scenarios, DOCTOR achieves 1.43× better average test accuracy, 1.25× better F1-score, and 0.41 higher backward transfer than the naïve fine-tuning framework, with a small model size of less than 350 KB.

User Engagement with the User Manuals of Smart Medical Wearable Technologies and Relevant Questions of User Behavior.

In this paper, engagement with smart medical wearables and with their user manuals, as well as related user behavior are studied. A research questionnaire containing 15 single-choice questions was completed by 1381 test participants to address relevant topics of the investigated area, including trust in measured medical data, device calibration, technical terminologies and function discovery in the documentation, information sources beyond the documentation, and wearing such devices to bed. The questionnaire particularly focused on device functionalities and characteristics that initially led to the purchase of the smart medical wearable.

The datafied hand in our health

AbstractThis article looks at a smart ring as a window into how contemporary datafication in fitness and medical wearables is informed by the longer history of notions of fitness and the datafication of health within the practice of medicine. After introducing some of the concerns arising from the history of eugenics, specifically out of disability studies critiques, and the more recent organizing of health through data‐driven algorithmic medicine, as well as discussing the difference between non‐optional wearables and their use as part of transhumanism, I briefly consider how wearables could be a site of intervention, to seize rather than relinquish power over our datafied bodies.

Consumer Perception Towards Wearable Medical Devices in India

This study investigates consumer perception and adoption of wearable medical devices (WMDs) in India, exploring factors influencing awareness, purchase, and usage. A survey of 186 respondents reveals varying levels of awareness across different fields, with sports/fitness and medical/wellness showing the highest awareness. Online platforms are the primary source of purchase. Males exhibit greater familiarity with WMDs than females. Pearson's correlation analysis shows a weak association between perception towards WMDs and healthy lifestyle habits, indicating that attitude towards WMDs does not significantly impact healthy lifestyle choices. The findings provide insights for manufacturers, marketers, and healthcare providers to develop targeted strategies for increasing adoption and usage of WMDs in India.

Hot Embossing to Fabricate Parylene-Based Microstructures and Its Impact on the Material Properties.

This study aims to establish and optimize a process for the fabrication of 3D microstructures of the biocompatible polymer Parylene C using hot embossing techniques. The different process parameters such as embossing temperature, embossing force, demolding temperature and speed, and the usage of a release agent were optimized, utilizing adhesive micropillars as a use case. To enhance compatibility with conventional semiconductor fabrication techniques, hot embossing of Parylene C was adapted from conventional stainless steel substrates to silicon chip platforms. Furthermore, this adaptation included an investigation of the effects of the hot embossing process on metal layers embedded in the Parylene C, ensuring compatibility with the ultra-thin Parylene printed circuit board (PCB) demonstrated previously. To evaluate the produced microstructures, a combination of characterization methods was employed, including light microscopy (LM) and scanning electron microscopy (SEM), X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS), and Fourier-transform infrared spectroscopy (FTIR). These methods provided comprehensive insights into the morphological, chemical, and structural properties of the embossed Parylene C. Considering the improved results compared to existing patterning techniques for Parylene C like plasma etching or laser ablation, the developed hot embossing approach yields a superior structural integrity, characterized by increased feature resolution and enhanced sidewall smoothness. These advancements render the method particularly suitable for diverse applications, including but not limited to, sensor optical components, adhesive interfaces for medical wearables, and microfluidic systems.

24-h continuous non-invasive multiparameter home monitoring of vitals in patients with Rett syndrome by an innovative wearable technology: evidence of an overlooked chronic fatigue status.

Sleep is disturbed in Rett syndrome (RTT), a rare and progressive neurodevelopmental disorder primarily affecting female patients (prevalence 7.1/100,000 female patients) linked to pathogenic variations in the X-linked methyl-CpG-binding protein 2 (MECP2) gene. Autonomic nervous system dysfunction with a predominance of the sympathetic nervous system (SNS) over the parasympathetic nervous system (PSNS) is reported in RTT, along with exercise fatigue and increased sudden death risk. The aim of the present study was to test the feasibility of a continuous 24 h non-invasive home monitoring of the biological vitals (biovitals) by an innovative wearable sensor device in pediatric and adolescent/adult RTT patients. A total of 10 female patients (mean age 18.3 ± 9.4 years, range 4.7-35.5 years) with typical RTT and MECP2 pathogenic variations were enrolled. Clinical severity was assessed by validated scales. Heart rate (HR), respiratory rate (RR), and skin temperature (SkT) were monitored by the YouCare Wearable Medical Device (Accyourate Group SpA, L'Aquila, Italy). The average percentage of maximum HR (HRmax%) was calculated. Heart rate variability (HRV) was expressed by consolidated time-domain and frequency-domain parameters. The HR/LF (low frequency) ratio, indicating SNS activation under dynamic exercise, was calculated. Simultaneous continuous measurement of indoor air quality variables was performed and the patients' contributions to the surrounding water vapor partial pressure [PH2O (pt)] and carbon dioxide [PCO2 (pt)] were indirectly estimated. Of the 6,559.79 h of biovital recordings, 5051.03 h (77%) were valid for data interpretation. Sleep and wake hours were 9.0 ± 1.1 h and 14.9 ± 1.1 h, respectively. HRmax % [median: 71.86% (interquartile range 61.03-82%)] and HR/LF [median: 3.75 (interquartile range 3.19-5.05)] were elevated, independent from the wake-sleep cycle. The majority of HRV time- and frequency-domain parameters were significantly higher in the pediatric patients (p ≤ 0.031). The HRV HR/LF ratio was associated with phenotype severity, disease progression, clinical sleep disorder, subclinical hypoxia, and electroencephalographic observations of multifocal epileptic activity and general background slowing. Our findings indicate the feasibility of a continuous 24-h non-invasive home monitoring of biovital parameters in RTT. Moreover, for the first time, HRmax% and the HR/LF ratio were identified as potential objective markers of fatigue, illness severity, and disease progression.

A Guide to Measuring Heart and Respiratory Rates Based on Off-the-Shelf Photoplethysmographic Hardware and Open-Source Software.

The remote monitoring of vital signs via wearable devices holds significant potential for alleviating the strain on hospital resources and elder-care facilities. Among the various techniques available, photoplethysmography stands out as particularly promising for assessing vital signs such as heart rate, respiratory rate, oxygen saturation, and blood pressure. Despite the efficacy of this method, many commercially available wearables, bearing Conformité Européenne marks and the approval of the Food and Drug Administration, are often integrated within proprietary, closed data ecosystems and are very expensive. In an effort to democratize access to affordable wearable devices, our research endeavored to develop an open-source photoplethysmographic sensor utilizing off-the-shelf hardware and open-source software components. The primary aim of this investigation was to ascertain whether the combination of off-the-shelf hardware components and open-source software yielded vital-sign measurements (specifically heart rate and respiratory rate) comparable to those obtained from more expensive, commercially endorsed medical devices. Conducted as a prospective, single-center study, the research involved the assessment of fifteen participants for three minutes in four distinct positions, supine, seated, standing, and walking in place. The sensor consisted of four PulseSensors measuring photoplethysmographic signals with green light in reflection mode. Subsequent signal processing utilized various open-source Python packages. The heart rate assessment involved the comparison of three distinct methodologies, while the respiratory rate analysis entailed the evaluation of fifteen different algorithmic combinations. For one-minute average heart rates' determination, the Neurokit process pipeline achieved the best results in a seated position with a Spearman's coefficient of 0.9 and a mean difference of 0.59 BPM. For the respiratory rate, the combined utilization of Neurokit and Charlton algorithms yielded the most favorable outcomes with a Spearman's coefficient of 0.82 and a mean difference of 1.90 BrPM. This research found that off-the-shelf components are able to produce comparable results for heart and respiratory rates to those of commercial and approved medical wearables.

3D printed PEDOT:PSS-based conducting and patternable eutectogel electrodes for machine learning on textiles

The proliferation of medical wearables necessitates the development of novel electrodes for cutaneous electrophysiology. In this work, poly(3,4-ethylenedioxythiophene) polystyrene sulfonate (PEDOT:PSS) is combined with a deep eutectic solvent (DES) and polyethylene glycol diacrylate (PEGDA) to develop printable and biocompatible electrodes for long-term cutaneous electrophysiology recordings. The impact of printing parameters on the conducting properties, morphological characteristics, mechanical stability and biocompatibility of the material were investigated. The optimised eutectogel formulations were fabricated in four different patterns —flat, pyramidal, striped and wavy— to explore the influence of electrode geometry on skin conformability and mechanical contact. These electrodes were employed for impedance and forearm EMG measurements. Furthermore, arrays of twenty electrodes were embedded into a textile and used to generate body surface potential maps (BSPMs) of the forearm, where different finger movements were recorded and analysed. Finally, BSPMs for three different letters (B, I, O) in sign-language were recorded and used to train a logistic regressor classifier able to reliably identify each letter. This novel cutaneous electrode fabrication approach offers new opportunities for long-term electrophysiological recordings, online sign-language translation and brain-machine interfaces.

Digital Transformation in Healthcare Challenges and Prospects

The following are presented, by the global community, as the main fields of Digital Transformation (DT) in Healthcare: Telemedicine Telemedicine is the remote delivery of healthcare services through Information and Communication Technologies (ICTs). It could be particularly beneficial in a range of services such as medical consultation, diagnosis remote monitoring of patients’ status and educational purposes. Patients could con- nect with healthcare providers at a distance using video calls, messaging platforms, or other communication tools. Telemedicine enhances accessibility to healthcare by overcoming geographical barriers while at the same time provides a transformative approach to healthcare services. Big Data Big data represents vast and diverse health information sets collected from several sources like Electronic Health Records (EHRs), wearable devices and social media. Big data can extract valuable insights and patterns, assisting clinical decision-making, public health management, personalised medicine and disease forecasting. Internet of Things (IoT) The Internet of Things (IoT) in healthcare refers to the interconnected network of medical devices, sensors and sys- tems that collect and exchange health data through the Inter- net. These devices offer real-time exchange of various data monitoring like patient's vital signs, and remote patient’s care, which could eventually result in the improvement of operational efficiency within healthcare systems, and patients' monitoring and care delivery. Virtual Reality (VR) in Health Virtual Reality (VR) employs immersive computer-generated environments into realistic experiences to transform medical training and education, rehabilitation, surgical planning and pain management. Employing VR tools such as headsets, users engage with three-dimensional simulation scenarios for training and skill practice in a safe environment without risking personal and patient safety. In addition, VR offers opportunities to improve outcomes, provide safer experiences to patients, while promoting the evolution of healthcare systems and care delivery. Artificial Intelligence (AI) in Health AI in healthcare is an umbrella term for the applications of Machine Learning (ML) algorithms used in medical contexts. AI algorithms analyse medical data, aiding in diagnostics, drug discovery, personalised medicine, and patient management. Virtual (personal) Assistants in Health Virtual Health Assistants (VHAs) are tools designed to engage patients, provide personalised health information and assist in various aspects of health services administration. Using Natural language Processing (NLP) and ML algorithms, VHAs offer support to remote communication between patients and healthcare providers, understand patients’ inquiries and healthcare-related issues. Also, VHAs could facil- itate appointment scheduling, symptom assessment, medication management, and health coaching, resulting at the enhancement of accessibility in healthcare and the empower- ment of the patient. Blockchain in Health Blockchain is an emerging technology, which utilises decentralised systems to record and manage healthcare information and patient data. By linking data blocks, blockchain can enhance security, interoperability and traceability, and address significant challenges such as data breaches, interoperability issues, and inefficiencies in data sharing, thus providing a stan- dardised and secure platform for data exchange across health- care systems and stakeholders. Medical Wearables Wearables emerge positive outcomes on continuing monitoring, tracking and early detecting of health issues. Wearables are devices wore on the body or putted on clothing allowing constant monitoring of health data and behaviour. They enable individuals to engage a proactive approach to their health and well-being, by empowering them to take control of their health. In addition, wearables have the potential to enhance telemedicine and population health management, while reducing healthcare costs.

A review of wearable technology in healthcare: Monitoring patient health and enhancing outcomes

Wearable technology has emerged as a transformative force in the healthcare landscape, reshaping the way patient health is monitored and healthcare outcomes are enhanced. The paper delves into various types of wearables, including fitness trackers, smartwatches, and medical wearables, elucidating their functionalities and applications in the healthcare domain. The review emphasizes the profound influence of wearable technology on patient monitoring, encompassing continuous health tracking, remote patient monitoring, and chronic disease management. Through real-time data collection and analysis, wearables enable early detection of health abnormalities and empower healthcare providers to offer timely interventions, thereby reducing hospital readmissions. The role of wearables in chronic disease management is examined, showcasing their potential in tailoring personalized treatment plans and facilitating proactive health management. Furthermore, the paper explores the broader implications of wearable technology in enhancing healthcare outcomes. Wearables contribute to improved patient engagement by providing individuals with access to their health data, fostering a sense of empowerment and accountability. The review underscores the shift towards personalized healthcare, where wearables play a pivotal role in tailoring treatment plans based on individual health data and leveraging predictive analytics for disease prevention. Despite the promising advancements, challenges such as data security, privacy concerns, and integration with existing healthcare systems are discussed. Strategies to address these challenges and enhance user adoption and adherence to wearable technology are explored, recognizing the importance of a holistic approach in realizing the full potential of wearables in healthcare. This review serves as a comprehensive guide for researchers, healthcare providers, and policymakers, offering insights into the evolving landscape of wearable technology and its profound impact on monitoring patient health and improving healthcare outcomes.

Multisensor Integrated Platform Based on MEMS Charge Variation Sensing Technology for Biopotential Acquisition.

We propose a new methodology for long-term biopotential recording based on an MEMS multisensor integrated platform featuring a commercial electrostatic charge-transfer sensor. This family of sensors was originally intended for presence tracking in the automotive industry, so the existing setup was engineered for the acquisition of electrocardiograms, electroencephalograms, electrooculograms, and electromyography, designing a dedicated front-end and writing proper firmware for the specific application. Systematic tests on controls and nocturnal acquisitions from patients in a domestic environment will be discussed in detail. The excellent results indicate that this technology can provide a low-power, unexplored solution to biopotential acquisition. The technological breakthrough is in that it enables adding this type of functionality to existing MEMS boards at near-zero additional power consumption. For these reasons, it opens up additional possibilities for wearable sensors and strengthens the role of MEMS technology in medical wearables for the long-term synchronous acquisition of a wide range of signals.

Effect of skin color on optical properties and the implications for medical optical technologies: a review.

Skin color affects light penetration leading to differences in its absorption and scattering properties. COVID-19 highlighted the importance of understanding of the interaction of light with different skin types, e.g., pulse oximetry (PO) unreliably determined oxygen saturation levels in people from Black and ethnic minority backgrounds. Furthermore, with increased use of other medical wearables using light to provide disease information and photodynamic therapies to treat skin cancers, a thorough understanding of the effect skin color has on light is important for reducing healthcare disparities. The aim of this work is to perform a thorough review on the effect of skin color on optical properties and the implication of variation on optical medical technologies. Published in vivo optical coefficients associated with different skin colors were collated and their effects on optical penetration depth and transport mean free path (TMFP) assessed. Variation among reported values is significant. We show that absorption coefficients for dark skin are to 74% greater than for light skin in the 400 to 1000nm spectrum. Beyond 600nm, the TMFP for light skin is greater than for dark skin. Maximum transmission for all skin types was beyond 940nm in this spectrum. There are significant losses of light with increasing skin depth; in this spectrum, depending upon Fitzpatrick skin type (FST), on average 14% to 18% of light is lost by a depth of 0.1mm compared with 90% to 97% of the remaining light being lost by a depth of 1.93mm. Current published data suggest that at wavelengths beyond 940nm light transmission is greatest for all FSTs. Data beyond 1000nm are minimal and further study is required. It is possible that the amount of light transmitted through skin for all skin colors will converge with increasing wavelength enabling optical medical technologies to become independent of skin color.

Validation of a Wearable Medical Device for Automatic Diagnosis of OSA against Standard PSG.

The objective of this study was to assess the accuracy of automatic diagnosis of obstructive sleep apnea (OSA) with a new, small, acoustic-based, wearable technology (AcuPebble SA100), by comparing it with standard type 1 polysomnography (PSG) diagnosis. This observational, prospective study was carried out in a Spanish hospital sleep apnea center. Consecutive subjects who had been referred to the hospital following primary care suspicion of OSA were recruited and underwent in-laboratory attended PSG, together with the AcuPebble SA100 device simultaneously overnight from January to December 2022. A total of 80 patients were recruited for the trial. The patients had a median Epworth scoring of 10, a mean of 10.4, and a range of 0-24. The mean AHI obtained with PSG plus sleep clinician marking was 23.2, median 14.3 and range 0-108. The study demonstrated a diagnostic accuracy (based on AHI) of 95.24%, sensitivity of 92.86%, specificity of 97.14%, positive predictive value of 96.30%, negative predictive value of 94.44%, positive likelihood ratio of 32.50 and negative likelihood ratio of 0.07. The AcuPebble SA100 (EU) device has demonstrated an accurate automated diagnosis of OSA in patients undergoing in-clinic sleep testing when compared against the gold-standard reference of in-clinic PSG.

Blockchain-Based Data Access Security Solutions for Medical Wearables.

Digital healthcare services have become an integral part of our lives. There is an increasing number of healthcare professionals and patients using medical wearables for diagnosis and treatment, which simplifies and improves the diagnostic and therapeutic process. However, inappropriate use of medical data may result in the disclosure of private patient information. For protecting patients' privacy when using medical wearables, we propose a new blockchain-based data access security scheme. Specifically, the elliptic curve encryption algorithm and zero-knowledge authentication method are used to authenticate the identity of patients and doctors in the blockchain network. Furthermore, we develop a smart recommendation method based on deep reinforcement learning to recommend appropriate doctors for patients. Next, patients allow recommended doctors to access their medical data, and smart contracts specifically designed for secure data access to medical wearables will regulate subsequent data access. The security analysis and experimental results demonstrate that the proposed scheme can effectively protect patients' privacy during treatment through secure authentication and data access for medical wearables.

An Enhanced Autoencoder-based Anomaly Detection Model for time series Data from Wearable Medical Devices.

In today's era of rapidly advancing technologies, such as sensors and the Internet of Things (IoT), and the increasing focus on promoting healthy lifestyles, smart wearable devices play a crucial role in real-time detection and diagnosis of physical health conditions. Through analyzing the multi-featured time series data captured by these devices with multiple sensors, we can uncover hidden diseases and provide timely treatment. Therefore, it is imperative to study an anomaly detection model with robust feature learning and anomaly diagnosis capabilities. To address this need, this paper proposes an enhanced autoencoder-based anomaly detection model for time series data obtained from wearable medical devices. Initially, the model utilizes a convolutional neural network to learn the correlations between multiple features. Subsequently, a long and short-term memory network is employed to capture the sequence correlations, and an multi-head attention mechanism is used to mitigate the performance degradation caused by increasing the sequence length. The residual loss is also used to effectively mitigate the vanishing gradient problem. Finally, the model is evaluated using two widely recognized public datasets: the HeartDisease dataset, which contains information on patients with heart conditions, and the MIMIC dataset, a comprehensive database of de-identified health data related to critical care. The experimental results demonstrate that our model can achieve an accuracy of 95.37% and 95.56% on the two datasets, respectively. Compared to the best performing baseline methods, our model improves 8.6% and 12.3% on the two datasets, respectively. Overall, our model enables efficient analysis of sequential data, effectively captures long-term dependencies, and significantly improves the success rate of early health diagnosis for individuals.

FA-SMW: Fog-Driven Anonymous Lightweight Access Control for Smart Medical Wearables

FA-SMW: Fog-Driven Anonymous Lightweight Access Control for Smart Medical Wearables

Biointerface Fiber Technology from Electrospinning to Inflight Printing.

Building two-dimensional (2D) and three-dimensional (3D) micro- and nanofibril structures with designable patterns and functionalities will offer exciting prospects for numerous applications spanning from permeable bioelectronics to tissue engineering scaffolds. This Spotlight on Applications highlights recent technological advances in fiber printing and patterning with functional materials for biointerfacing applications. We first introduce the current state of development of micro- and nanofibers with applications in biology and medical wearables. We then describe our contributions in developing a series of fiber printing techniques that enable the patterning of functional fiber architectures in three dimensions. These fiber printing techniques expand the material library and device designs, which underpin technological capabilities from enabling fundamental studies in cell migration to customizable and ecofriendly fabrication of sensors. Finally, we provide an outlook on the strategic pathways for developing the next-generation bioelectronics and "Fiber-of-Things" (FoT) using nano/micro-fibers as architectural building blocks.

Abstract 12454: Weak Supervision Enables Scalable Post-Market Surveillance on Medical Wearables

Introduction: With the advent of consumer-facing devices that can render atrial fibrillation (AF) pre-diagnosis, medical wearables now have the potential to affect diagnosis rates and medical care. Post-market surveillance is necessary to understand the impact of wearables on patient outcomes and health care utilization, but is hindered by the lack of codified terms in EHR that capture wearable use. Research Questions: Constructing a post-market surveillance system therefore requires a classifier that identifies mentions of AF pre-diagnosis in unstructured EHR data. However, fine-tuning classifiers require large, hand-labeled training sets that can be costly to generate. It is unclear whether a scalable surveillance system could be built for wearables. Methods: Two weakly-supervised approaches were evaluated to reduce clinical note labeling overhead: one using programmatic codes, and the other using prompts to large language models (LLMs). Probabilistically labeled notes were then used to fine-tune a classifier, which identified patients with AF pre-diagnosis mentions. A retrospective cohort study was conducted, where the characteristics and care patterns of patients identified by the classifier were compared against those who did not receive pre-diagnosis. Results: Label model derived from prompt-based labeling heuristics using LLMs (precision = 0.67, recall = 0.83, F1 = 0.74) nearly achieved the performance of code-based heuristics (precision = 0.84, recall = 0.72, F1 = 0.77), while cutting down the cost to create a labeled training set. The classifier learned on the labeled notes accurately identified patients with AF pre-diagnosis (precision = 0.85, recall = 0.81, F1 = 0.83). Those patients who received pre-diagnosis exhibited different demographic and comorbidity characteristics, and were enriched for anticoagulation and eventual diagnosis of AF. At the index diagnosis, existence of pre-diagnosis did not stratify patients on clinical characteristics, but did correlate with anticoagulant prescription. Conclusion: Our work establishes the feasibility of an EHR-based surveillance system for wearable devices that render AF pre-diagnosis. Weakly-supervised approaches can be effective in reducing test set labeling costs.

Abstract 14168: A Randomised Open-Label Controlled Trial of a Remote Cardiac Rehabilitation System With Wearable Medical Devices - An Interim Report of the TELE-REHA Trial

Introduction: Outpatient cardiac rehabilitation (CR) prevents recurrence after cardiac surgery or cardiac catheterisation, but participation rate of outpatient CR is low. Although attempts at remote CR have been investigated with advances in equipment, they have not yet reached the stage of social implementation, and it is not clear whether remote CR can be an alternative to outpatient CR. Objective: The aim of this study was to confirm the safety and efficacy of remote CR management using wearable devices feasible in Japan, and to implement the device early in society. Primary outcome: All-cause death, cardiovascular events, EFs, e/e', BNPs, CRPs, PeakVO2, VE-VCO2 slop, muscle mass; secondary outcome: EQ5D. Subjects: Patients discharged home after hospitalization for cardiovascular diseases. Study design: A single-centre, randomised, open-label, parallel-group study was conducted to evaluate the efficacy and safety of wearable device (Apple Watch)-based Remote-CR versus Outpatient-CR. In Remote-CR group, ECG and SpO2 are measured by Apple Watch before and after exercise. Biweekly health information, weight, blood pressure, heart rate, electrocardiogram (ECG) and EQ5D are automatically transmitted by the app. Tele-nursing was provided by trained nurses on a bi-weekly basis, based on the health information provided by the app. For both groups, the intervention period was 90 days, and blood sampling, ECG, cardiopulmonary exercise testing (CPX), and body composition testing were performed at the end of the study. Results: A total of 110 cardiovascular patients were randomly divided into Remote-CR group and Outpatient-CR group. The background of the two groups was similar. Though the PeakVO2 and EQ5D scores after the CR program were not significantly improved in Outpatient-CR group, those were significantly improved in Remote-CR group (P=0.02). The dropout rate from CR program was lower in Remote-CR group than Outpatient-CR group. No significant incident occurred in both group. Conclusions: Remote-CR is expected to be as effective as Outpatient-CR and safe for patients after cardiac treatment, and can provide a relapse prevention programme for those who are difficult to attend.

Correction to: Precise Dosing for Medical Wearables

Correction to: Precise Dosing for Medical Wearables