Neuroscience meets behavior: A systematic literature review on magnetic resonance imaging of the brain combined with real-world digital phenotyping.

A primary goal of neuroscience is to understand the relationship between the brain and behavior. While magnetic resonance imaging (MRI) examines brain structure and function under controlled conditions, digital phenotyping via portable automatic devices (PAD) quantifies behavior in real-world settings. Combining these two technologies may bridge the gap between brain imaging, physiology, and real-time behavior, enhancing the generalizability of laboratory and clinical findings. However, the use of MRI and data from PADs outside the MRI scanner remains underexplored. Herein, we present a Preferred Reporting Items for Systematic Reviews and Meta-Analysis systematic literature review that identifies and analyzes the current state of research on the integration of brain MRI and PADs. PubMed and Scopus were automatically searched using keywords covering various MRI techniques and PADs. Abstracts were screened to only include articles that collected MRI brain data and PAD data outside the laboratory environment. Full-text screening was then conducted to ensure included articles combined quantitative data from MRI with data from PADs, yielding 94 selected papers for a total of N = 14,778 subjects. Results were reported as cross-frequency tables between brain imaging and behavior sampling methods and patterns were identified through network analysis. Furthermore, brain maps reported in the studies were synthesized according to the measurement modalities that were used. Results demonstrate the feasibility of integrating MRI and PADs across various study designs, patient and control populations, and age groups. The majority of published literature combines functional, T1-weighted, and diffusion weighted MRI with physical activity sensors, ecological momentary assessment via PADs, and sleep. The literature further highlights specific brain regions frequently correlated with distinct MRI-PAD combinations. These combinations enable in-depth studies on how physiology, brain function and behavior influence each other. Our review highlights the potential for constructing brain-behavior models that extend beyond the scanner and into real-world contexts.

Validation of smartwatch electrocardiogram intervals in children compared to standard 12 lead electrocardiograms.

Lay people are now able to obtain one-lead electrocardiograms (ECG) using smartwatches, which facilitates documentation of arrhythmias. The accuracy of smartwatch derived ECG intervals has not been validated in children though. Home-based monitoring of ECG intervals using a smartwatch could improve monitoring of children, e.g. when taking QTc prolonging medications. The aim of this study was to validate the ECG intervals measured by smartwatch in comparison to standard 12-lead ECGs in children and adolescents. Prospective study of children (age 5-17 years) at the outpatient clinic of a national pediatric heart center. Patients underwent a smartwatch ECG (ScanWatch, Withings) and a simultaneous standard 12-lead ECG. ECG intervals were measured both automatically and manually from the smartwatch ECG and the 12-lead ECG. Intraclass correlation coefficients and Bland-Altman plots were performed. 100 patients (54% male, median age 12.9 (IQR 8.7-15.6) were enrolled. The ICC calculated from the automated smartwatch and automated 12-lead ECG were excellent for heart rate (ICC 0.97, p < 0.001), good for the PR and QT intervals (ICC 0.86 and 0.8, p < 0.001), and moderate for the QRS duration and QTc interval (ICC 0.7 and 0.53, p < 0.001). When using manual measurements for the smartwatch ECG, validity was improved for the PR interval (ICC 0.93, p < 0.001), QRS duration (ICC 0.92, p < 0.001), QT (ICC 0.95, p < 0.001) and QTc interval (ICC 0.84, p < 0.001). CONCLUSION: Automated smartwatch intervals are most reliable measuring the heart rate. The automated smartwatch QTc intervals are less reliable, but this may be improved by manual measurements. WHAT IS KNOWN: In adults, smartwatch derived ECG intervals measured manually have previously been shown to be accurate, though agreement for automated QTc may be fair. WHAT IS NEW: In children, automated smartwatch QTc intervals are less reliable than RR, PR, QRS and uncorrected QT interval. Accuracy of the QTc can be improved by peroforming manual measurements.

Validity of a smartwatch for detecting atrial fibrillation in patients after heart valve surgery: a prospective observational study.

OBJECTIVES: Atrial fibrillation (AF) is a common early arrhythmia after heart valve surgery that limits physical activity. We aimed to evaluate the criterion validity of the Apple Watch Series 5 single-lead electrocardiogram (ECG) for detecting AF in patients after heart valve surgery. DESIGN: We enrolled 105 patients from the University Hospital of North Norway, of whom 93 completed the study. All patients underwent single-lead ECG using the smartwatch three times or more daily on the second to third or third to fourth postoperative day. These results were compared with continuous 2-4 days ECG telemetry monitoring and a 12-lead ECG on the third postoperative day. RESULTS: On comparing the Apple Watch ECGs with the ECG monitoring, the sensitivity and specificity to detect AF were 91% (75, 100) and 96% (91, 99), respectively. The accuracy was 95% (91, 99). On comparing Apple Watch ECG with a 12-lead ECG, the sensitivity was 71% (62, 100) and the specificity was 92% (92, 100). CONCLUSION: The Apple smartwatch single-lead ECG has high sensitivity and specificity, and might be a useful tool for detecting AF in patients after heart valve surgery.

Barriers and facilitators to smartwatch-based prehabilitation participation among frail surgery patients: a qualitative study.

BACKGROUND: For older, frail adults, exercise before surgery through prehabilitation (prehab) may hasten return recovery and reduce postoperative complications. We developed a smartwatch-based prehab program (BeFitMe) for older adults that encourages and tracks at-home exercise. The objective of this study was to assess patient perceptions about facilitators and barriers to prehab generally and to using a smartwatch prehab program among older adult thoracic surgery patients to optimize future program implementation. METHODS: We recruited patients, aged ≥50 years who had or were having surgery and were screened for frailty (Fried's Frailty Phenotype) at a thoracic surgery clinic at a single academic institution. Semi-structured interviews were conducted by telephone after obtaining informed consent. Participants were given a description of the BeFitMe program. The interview questions were informed by The Five "Rights" of Clinical Decision-Making framework (Information, Person, Time, Channel, and Format) and sought to identify the factors perceived to influence smartwatch prehab program participation. Interview transcripts were transcribed and independently coded to identify themes in for each of the Five "Rights" domains. RESULTS: A total of 29 interviews were conducted. Participants were 52% men (n = 15), 48% Black (n = 14), and 59% pre-frail (n = 11) or frail (n = 6) with a mean age of 68 ± 9 years. Eleven total themes emerged. Facilitator themes included the importance of providers (right person) clearly explaining the significance of prehab (right information) during the preoperative visit (right time); providing written instructions and exercise prescriptions; and providing a preprogrammed and set-up (right format) Apple Watch (right channel). Barrier themes included pre-existing conditions and disinterest in exercise and/or technology. Participants provided suggestions to overcome the technology barrier, which included individualized training and support on usage and responsibilities. CONCLUSIONS: This study reports the perceived facilitators and barriers to a smartwatch-based prehab program for pre-frail and frail thoracic surgery patients. The future BeFitMe implementation protocol must ensure surgical providers emphasize the beneficial impact of participating in prehab before surgery and provide a written prehab prescription; must include a thorough guide on smartwatch use along with the preprogrammed device to be successful. The findings are relevant to other smartwatch-based interventions for older adults.

Diagnostic accuracy of apple watch ECG outputs in identifying dysrhythmias: A comparison with 12-Lead ECG in emergency department.

BACKGROUND: Wearable devices, particularly smartwatches like the Apple Watch (AW), can record important cardiac information, such as single­lead electrocardiograms (ECGs). Although they are increasingly used to detect conditions such as atrial fibrillation (AF), research on their effectiveness in detecting a wider range of dysrhythmias and abnormal ECG findings remains limited. The primary objective of this study is to evaluate the accuracy of the AW in detecting various cardiac rhythms by comparing it with standard ECG's lead-I. METHODS: This single-center prospective observational study was conducted in a tertiary care emergency department (ED) between 1.10.2023 and 31.10.2023. The study population consisted of all patients assessed in the critical care areas of the ED, all of whom underwent standard 12­lead ECGs for various clinical reasons. Participants in the study were included consecutively. An AW was attached to patients' wrists and an ECG lead-I printout was obtained. Heart rate, rhythm and abnormal findings were evaluated and compared with the lead-I of standard ECG. Two emergency medicine specialists performed the ECG evaluations. Rhythms were categorized as normal sinus rhythm and abnormal rhythms, while ECG findings were categorized as the presence or absence of abnormal findings. AW and 12­lead ECG outputs were compared using the McNemar test. Predictive performance analyses were also performed for subgroups. Bland-Altman analysis using absolute mean differences and concordance correlation coefficients was used to assess the level of heart rate agreement between devices. RESULTS: The study was carried out on 721 patients. When analyzing ECG rhythms and abnormal findings in lead-I, the effectiveness of AW in distinguishing between normal and abnormal rhythms was similar to standard ECGs (p = 0.52). However, there was a significant difference between AW and standard ECGs in identifying abnormal findings in lead-I (p < 0.05). Using Bland-Altman analysis for heart rate assessment, the absolute mean difference for heart rate was 0.81 ± 6.12 bpm (r = 0.94). There was strong agreement in 658 out of 700 (94%) heart rate measurements. CONCLUSION: Our study indicates that the AW has the potential to detect cardiac rhythms beyond AF. ECG tracings obtained from the AW may help evaluate cardiac rhythms prior to the patient's arrival in the ED. However, further research with a larger patient cohort is essential, especially for specific diagnoses.

A smartwatch sphygmomanometer-based model for predicting short-term new-onset hypertension in individuals with high-normal blood pressure: a cohort study.

OBJECTIVES: The objective was to utilize a smartwatch sphygmomanometer to predict new-onset hypertension within a short-term follow-up among individuals with high-normal blood pressure (HNBP). METHODS: This study consisted of 3180 participants in the training set and 1000 participants in the validation set. Participants underwent both ambulatory blood pressure monitoring (ABPM) and home blood pressure monitoring (HBPM) using a smartwatch sphygmomanometer. Multivariable Cox regressions were used to analyze cumulative events. A nomogram was constructed to predict new-onset hypertension. Discrimination and calibration were assessed using the C-index and calibration curve, respectively. RESULTS: Among the 3180 individuals with HNBP in the training set, 693 (21.8%) developed new-onset hypertension within a 6-month period. The nomogram for predicting new-onset hypertension had a C-index of 0.854 (95% CI, 0.843-0.867). The calibration curve demonstrated good agreement between the nomogram's predicted probabilities and actual observations for short-term new-onset hypertension. In the validate dataset, during the 6-month follow-up, the nomogram had a good C-index of 0.917 (95% CI, 0.904-0.930) and a good calibration curve. As the score increased, the risk of new-onset hypertension significantly increased, with an HR of 8.415 (95% CI: 5.153-13.744, p = .000) for the middle-score vs. low-score groups and 86.824 (95% CI: 55.071-136.885, p = .000) for the high-score vs. low-score group. CONCLUSIONS: This study provides evidence for the use of smartwatch sphygmomanometer to monitor blood pressure in individuals at high risk of developing new-onset hypertension in the near future. TRIAL REGISTRATION: ChiCTR2200057354.

Association of Smartwatch-Based Heart Rate and Physical Activity With Cardiorespiratory Fitness Measures in the Community: Cohort Study.

BACKGROUND: Resting heart rate (HR) and routine physical activity are associated with cardiorespiratory fitness levels. Commercial smartwatches permit remote HR monitoring and step count recording in real-world settings over long periods of time, but the relationship between smartwatch-measured HR and daily steps to cardiorespiratory fitness remains incompletely characterized in the community. OBJECTIVE: This study aimed to examine the association of nonactive HR and daily steps measured by a smartwatch with a multidimensional fitness assessment via cardiopulmonary exercise testing (CPET) among participants in the electronic Framingham Heart Study. METHODS: Electronic Framingham Heart Study participants were enrolled in a research examination (2016-2019) and provided with a study smartwatch that collected longitudinal HR and physical activity data for up to 3 years. At the same examination, the participants underwent CPET on a cycle ergometer. Multivariable linear models were used to test the association of CPET indices with nonactive HR and daily steps from the smartwatch. RESULTS: We included 662 participants (mean age 53, SD 9 years; n=391, 59% women, n=599, 91% White; mean nonactive HR 73, SD 6 beats per minute) with a median of 1836 (IQR 889-3559) HR records and a median of 128 (IQR 65-227) watch-wearing days for each individual. In multivariable-adjusted models, lower nonactive HR and higher daily steps were associated with higher peak oxygen uptake (VO2), % predicted peak VO2, and VO2 at the ventilatory anaerobic threshold, with false discovery rate (FDR)-adjusted P values <.001 for all. Reductions of 2.4 beats per minute in nonactive HR, or increases of nearly 1000 daily steps, corresponded to a 1.3 mL/kg/min higher peak VO2. In addition, ventilatory efficiency (VE/VCO2; FDR-adjusted P=.009), % predicted maximum HR (FDR-adjusted P<.001), and systolic blood pressure-to-workload slope (FDR-adjusted P=.01) were associated with nonactive HR but not associated with daily steps. CONCLUSIONS: Our findings suggest that smartwatch-based assessments are associated with a broad array of cardiorespiratory fitness responses in the community, including measures of global fitness (peak VO2), ventilatory efficiency, and blood pressure response to exercise. Metrics captured by wearable devices offer a valuable opportunity to use extensive data on health factors and behaviors to provide a window into individual cardiovascular fitness levels.

Smartwatch-Detected Arrhythmias in Patients After Transcatheter Aortic Valve Replacement (TAVR): Analysis of the SMART TAVR Trial.

BACKGROUND: There are limited data available on the development of arrhythmias in patients at risk of high-degree atrioventricular block (HAVB) or complete heart block (CHB) following transcatheter aortic valve replacement (TAVR). OBJECTIVE: This study aimed to explore the incidence and evolution of arrhythmias by monitoring patients at risk of HAVB or CHB after TAVR using smartwatches. METHODS: We analyzed 188 consecutive patients in the prospective SMART TAVR (smartwatch-facilitated early discharge in patients undergoing TAVR) trial. Patients were divided into 2 groups according to the risk of HAVB or CHB. Patients were required to trigger a single-lead electrocardiogram (ECG) recording and send it to the Heart Health App via their smartphone. Physicians in the central ECG core lab would then analyze the ECG. The incidence and timing of arrhythmias and pacemaker implantation within a 30-day follow-up were compared. All arrhythmic events were adjudicated in a central ECG core lab. RESULTS: The mean age of the patients was 73.1 (SD 7.3) years, of whom 105 (55.9%) were men. The mean discharge day after TAVR was 2.0 (SD 1.8) days. There were no statistically significant changes in the evolution of atrial fibrillation or atrial flutter, Mobitz I, Mobitz II, and third-degree atrial ventricular block over time in the first month after TAVR. The incidence of the left bundle branch block (LBBB) increased in the first week and decreased in the subsequent 3 weeks significantly (P<.001). Patients at higher risk of HAVB or CHB received more pacemaker implantation after discharge (n=8, 9.6% vs n=2, 1.9%; P=.04). The incidence of LBBB was higher in the group with higher HAVB or CHB risk (n=47, 56.6% vs n=34, 32.4%; P=.001). The independent predictors for pacemaker implantation were age, baseline atrial fibrillation, baseline right bundle branch block, Mobitz II, and third-degree atrioventricular block detected by the smartwatch. CONCLUSIONS: Except for LBBB, no change in arrhythmias was observed over time in the first month after TAVR. A higher incidence of pacemaker implantation after discharge was observed in patients at risk of HAVB or CHB. However, Mobitz II and third-degree atrioventricular block detected by the smartwatch during follow-ups were more valuable indicators to predict pacemaker implantation after discharge from the index TAVR. TRIAL REGISTRATION: ClinicalTrials.gov NCT04454177; https://clinicaltrials.gov/study/NCT04454177.

Feasibility of a wearable self-management application for patients with COPD at home: a pilot study.

BACKGROUND: Among people with COPD, smartphone and wearable technology may provide an effective method to improve care at home by supporting, encouraging, and sustaining self-management. The current study was conducted to determine if patients with COPD will use a dedicated smartphone and smartwatch app to help manage their COPD and to determine the effects on their self-management. METHODS: We developed a COPD self-management application for smartphones and smartwatches. Participants were provided with the app on a smartphone and a smartwatch, as well as a cellular data plan and followed for 6 months. We measured usage of the different smartphone app functions. For the primary outcome, we examined the change in self-management from baseline to the end of follow up. Secondary outcomes include changes in self-efficacy, quality of life, and COPD disease control. RESULTS: Thirty-four patients were enrolled and followed. Mean age was 69.8 years, and half of the participants were women. The most used functions were recording steps through the smartwatch, entering a daily symptom questionnaire, checking oxygen saturation, and performing breathing exercises. There was no significant difference in the primary outcome of change in self-management after use of the app or in overall total scores of health-related quality of life, disease control or self-efficacy. CONCLUSION: We found older patients with COPD would engage with a COPD smartphone and smartwatch application, but this did not result in improved self-management. More research is needed to determine if a smartphone and smartwatch application can improve self-management in people with COPD. TRIAL REGISTRATION: ClinicalTrials.Gov NCT03857061, First Posted February 27, 2019.

The Use of Electrocardiogram Smartwatches in Patients with Cardiac Implantable Electrical Devices.

Unlimited access to ECGs using an over-the-counter smartwatch constitutes a real revolution for our discipline, and the application is rapidly expanding to include patients with cardiac implantable electronic devices (CIEDs) such as pacemakers (PMs) and implantable cardioverter defibrillators (ICDs). CIEDs require periodic evaluation and adjustment by healthcare professionals. In addition, implanted patients often present with symptoms that may be related to their PMs or ICDs. An ECG smartwatch could reveal information about device functioning, confirm normal device function, or aid in the case of device troubleshooting. In this review, we delve into the available evidence surrounding smartwatches with ECG registration and their integration into the care of patients with implanted pacemakers and ICDs. We explore safety considerations and the benefits and limitations associated with these wearables, drawing on relevant studies and case series from our own experience. By analyzing the current landscape of this emerging technology, we aim to provide a comprehensive overview that facilitates informed decision-making for both healthcare professionals and patients.

Simplified Indoor Localization Using Bluetooth Beacons and Received Signal Strength Fingerprinting with Smartwatch.

Variations in Global Positioning Systems (GPSs) have been used for tracking users' locations. However, when location tracking is needed for an indoor space, such as a house or building, then an alternative means of precise position tracking may be required because GPS signals can be severely attenuated or completely blocked. In our approach to indoor positioning, we developed an indoor localization system that minimizes the amount of effort and cost needed by the end user to put the system to use. This indoor localization system detects the user's room-level location within a house or indoor space in which the system has been installed. We combine the use of Bluetooth Low Energy beacons and a smartwatch Bluetooth scanner to determine which room the user is located in. Our system has been developed specifically to create a low-complexity localization system using the Nearest Neighbor algorithm and a moving average filter to improve results. We evaluated our system across a household under two different operating conditions: first, using three rooms in the house, and then using five rooms. The system was able to achieve an overall accuracy of 85.9% when testing in three rooms and 92.106% across five rooms. Accuracy also varied by region, with most of the regions performing above 96% accuracy, and most false-positive incidents occurring within transitory areas between regions. By reducing the amount of processing used by our approach, the end-user is able to use other applications and services on the smartwatch concurrently.

Development of a Smartwatch with Gas and Environmental Sensors for Air Quality Monitoring.

In recent years, there has been a growing interest in developing portable and personal devices for measuring air quality and surrounding pollutants, partly due to the need for ventilation in the aftermath of COVID-19 situation. Moreover, the monitoring of hazardous chemical agents is a focus for ensuring compliance with safety standards and is an indispensable component in safeguarding human welfare. Air quality measurement is conducted by public institutions with high precision but costly equipment, which requires constant calibration and maintenance by highly qualified personnel for its proper operation. Such devices, used as reference stations, have a low spatial resolution since, due to their high cost, they are usually located in a few fixed places in the city or region to be studied. However, they also have a low temporal resolution, providing few samples per hour. To overcome these drawbacks and to provide people with personalized and up-to-date air quality information, a personal device (smartwatch) based on MEMS gas sensors has been developed. The methodology followed to validate the performance of the prototype was as follows: firstly, the detection capability was tested by measuring carbon dioxide and methane at different concentrations, resulting in low detection limits; secondly, several experiments were performed to test the discrimination capability against gases such as toluene, xylene, and ethylbenzene. principal component analysis of the data showed good separation and discrimination between the gases measured.

Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition.

Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person's ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.

Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection.

Smartwatch health sensor data are increasingly utilized in smart health applications and patient monitoring, including stress detection. However, such medical data often comprise sensitive personal information and are resource-intensive to acquire for research purposes. In response to this challenge, we introduce the privacy-aware synthetization of multi-sensor smartwatch health readings related to moments of stress, employing Generative Adversarial Networks (GANs) and Differential Privacy (DP) safeguards. Our method not only protects patient information but also enhances data availability for research. To ensure its usefulness, we test synthetic data from multiple GANs and employ different data enhancement strategies on an actual stress detection task. Our GAN-based augmentation methods demonstrate significant improvements in model performance, with private DP training scenarios observing an 11.90-15.48% increase in F1-score, while non-private training scenarios still see a 0.45% boost. These results underline the potential of differentially private synthetic data in optimizing utility-privacy trade-offs, especially with the limited availability of real training samples. Through rigorous quality assessments, we confirm the integrity and plausibility of our synthetic data, which, however, are significantly impacted when increasing privacy requirements.

Combining Different Wearable Devices to Assess Gait Speed in Real-World Settings.

Assessing mobility in daily life can provide significant insights into several clinical conditions, such as Chronic Obstructive Pulmonary Disease (COPD). In this paper, we present a comprehensive analysis of wearable devices' performance in gait speed estimation and explore optimal device combinations for everyday use. Using data collected from smartphones, smartwatches, and smart shoes, we evaluated the individual capabilities of each device and explored their synergistic effects when combined, thereby accommodating the preferences and possibilities of individuals for wearing different types of devices. Our study involved 20 healthy subjects performing a modified Six-Minute Walking Test (6MWT) under various conditions. The results revealed only little performance differences among devices, with the combination of smartwatches and smart shoes exhibiting superior estimation accuracy. Particularly, smartwatches captured additional health-related information and demonstrated enhanced accuracy when paired with other devices. Surprisingly, wearing all devices concurrently did not yield optimal results, suggesting a potential redundancy in feature extraction. Feature importance analysis highlighted key variables contributing to gait speed estimation, providing valuable insights for model refinement.

[Wearables in rheumatology]. / Wearables in der Rheumatologie.

As a result of digitalization in medicine wearable computing devices (wearables) are becoming increasingly more important. Wearables are small portable electronic devices with which the user can record data relevant to health, such as number of steps, activity profile, electrocardiogram (ECG), heart and breathing frequency or oxygen saturation. Initial studies on the use of wearables in patients with rheumatological diseases show the opening up of new possibilities for prevention, disease monitoring and treatment. This study provides the current data situation and the implementation of wearables in the discipline of rheumatology. Additionally, future potential fields of application as well as challenges and limits of the implementation of wearables are illustrated.

Development and validation of a deep learning model to diagnose COVID-19 using time-series heart rate values before the onset of symptoms.

One of the effective ways to minimize the spread of COVID-19 infection is to diagnose it as early as possible before the onset of symptoms. In addition, if the infection can be simply diagnosed using a smartwatch, the effectiveness of preventing the spread will be greatly increased. In this study, we aimed to develop a deep learning model to diagnose COVID-19 before the onset of symptoms using heart rate (HR) data obtained from a smartwatch. In the deep learning model for the diagnosis, we proposed a transformer model that learns HR variability patterns in presymptom by tracking relationships in sequential HR data. In the cross-validation (CV) results from the COVID-19 unvaccinated patients, our proposed deep learning model exhibited high accuracy metrics: sensitivity of 84.38%, specificity of 85.25%, accuracy of 84.85%, balanced accuracy of 84.81%, and area under the receiver operating characteristics (AUROC) of 0.8778. Furthermore, we validated our model using external multiple datasets including healthy subjects, COVID-19 patients, as well as vaccinated patients. In the external healthy subject group, our model also achieved high specificity of 77.80%. In the external COVID-19 unvaccinated patient group, our model also provided similar accuracy metrics to those from the CV: balanced accuracy of 87.23% and AUROC of 0.8897. In the COVID-19 vaccinated patients, the balanced accuracy and AUROC dropped by 66.67% and 0.8072, respectively. The first finding in this study is that our proposed deep learning model can simply and accurately diagnose COVID-19 patients using HRs obtained from a smartwatch before the onset of symptoms. The second finding is that the model trained from unvaccinated patients may provide less accurate diagnosis performance compared with the vaccinated patients. The last finding is that the model trained in a certain period of time may provide degraded diagnosis performances as the virus continues to mutate.

Accuracy of the Apple watch for detection of AF: A multicenter experience.

INTRODUCTION: The Apple watch (AW) irregular rhythm notification (IRN) feature uses photoplethysmography to identify prolonged episodes of irregular rhythm suggestive of atrial fibrillation (AF). IRN is FDA cleared for those with no previous history of AF, however, these devices are increasingly being used for AF management.  The objective of the present study was to determine the accuracy of the IRN in subjects with a previous diagnosis of nonpermanent AF. METHODS: Subjects with a history of nonpermanent AF and either an insertable cardiac monitor (ICM) or cardiac implanted electronic device (CIED) with <5% ventricular pacing were fitted with an AW Series 5 for 6 months. AF episodes were compared between the ICM/CIED and IRN. The primary endpoints were sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the IRN by subject for AF ≥1 h. Secondary endpoints were sensitivity and PPV by AF episode ≥1 h. Analysis was limited to a maximum of 10 ICM/CIED episodes per subject and included only those AF episodes occurring during active AW use confirmed by activity data. RESULTS: Thirty participants were enrolled. Mean age was 65.4 ± 12.2 years and 40% were female. There were 10 ICMs and 20 CIEDs. Eleven subjects had AF on ICM/CIED while the AW was worn, of whom 8 were detected by IRN. There were no false positive IRN detections by subject ("by subject" 72% sensitivity, 100% specificity, 100% PPV, and 90% NPV). Five subjects had AF only when the AW was not worn. There were a total of 70 AF episodes on ICM/CIED, 35 of which occurred while the AW was being worn. Of these, 21 were detected by IRN with 1 false positive ("by episode" sensitivity = 60.0%, PPV = 95.5%). CONCLUSION: In a population with known AF, the AW IRN had a low rate of false positive detections and high specificity. Sensitivity for detection by subject and by AF episode was lower. The current IRN algorithm appears accurate for AF screening as currently cleared, but increased sensitivity and wear times would be necessary for disease management.

Ambulatory Smartwatch ECG Monitoring among Patients Undergoing Transcatheter Aortic Valve Replacement Early after Discharge: An Observational Study.

Background: As an emerging arrhythmia monitor, ambulatory smartwatch electrocardiogram (ECG) provides an option for home-based monitoring of delayed new-onset arrhythmic events after transcatheter aortic valve replacement (TAVR). We aimed to validate the diagnostic efficacy of a consumer smartwatch ECG in TAVR recipients, while further explore the occurrence rate of both tachy- and brady-arrhythmia for 30 days after discharge to support risk management. Methods: Consecutive TAVR recipients from February 26th, 2021 to December 13th, 2021 were enrolled prospectively, receiving simultaneous 24-hour Holter and 12-lead ECG compared with smartwatch ECG during hospitalization and daily smartwatch ECG collection for 30 days after discharge. Results: Among 110 patients, the efficacy of smartwatch ECG presented sensitivity and specificity in diagnosing atrial fibrillation (AF) as 1.00 and 0.97, left bundle branch block (LBBB) as 0.61 and 0.88, and right bundle branch block (RBBB) as 0.60 and 0.97, respectively, compared with 24-hour Holter; presented sensitivity and specificity in diagnosing AF as 0.88 and 1.00, LBBB as 0.90 and 0.96, and RBBB as 0.83 and 0.94, respectively, compared with 12-lead ECG. At 30-day follow-up, new-onset arrhythmia included new-onset severe conduction disturbance (SCD) (23.6%), new-onset AF (21.8%), new-onset permanent LBBB (14.5%) and new-onset permanent RBBB (0.9%); 69.2% (36/52) of early new-onset LBBB recovered at 30-day follow-up. Conclusions: The diagnostic efficacy of consumer smartwatch ECG in arrhythmic events among TAVR population was acceptable, which provided a recommendable option for home-based management. Clinical Trial Registration: "Continuously ambulatory rhythm monitoring and predictors of electrocardio-related adverse events in 30 days after transcatheter aortic valve replacement"; Identifier: ChiCTR2000041244; http://www.chictr.org.cn/showproj.aspx?proj=66324.

Wrist-worn smartwatch and predictive models for seizures.

OBJECTIVE: This study was undertaken to describe extracerebral biosignal characteristics of overall and various seizure types as compared with baseline physical activities using multimodal devices (Empatica E4); develop predictive models for overall and each seizure type; and assess diagnostic performance of each model. METHODS: We prospectively recruited patients with focal epilepsy who were admitted to the epilepsy monitoring unit for presurgical evaluation during January to December 2020. All study participants were simultaneously applied gold standard long-term video-electroencephalographic (EEG) monitoring and an index test, E4. Two certified epileptologists independently determined whether captured events were seizures and then indicated ictal semiology and EEG information. Both were blind to multimodal biosignal findings detected by E4. Biosignals during 5-min epochs of both seizure events and baseline were collected and compared. Predictive models for occurrence overall and of each seizure type were developed using a generalized estimating equation. Diagnostic performance of each model was then assessed. RESULTS: Thirty patients had events recorded and were recruited for analysis. One hundred eight seizure events and 120 baseline epochs were collected. Heart rate (HR), acceleration (ACC), and electrodermal activity (EDA) but not temperature were significantly elevated during seizures. Cluster analysis showed trends of greatest elevation of HR and ACC in bilateral tonic-clonic seizures (BTCs), as compared with non-BTCs and isolated auras. HR and ACC were independent predictors for overall seizure types, BTCs, and non-BTCs, whereas only HR was a predictor for isolated aura. Diagnostic performance including sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve of the predictive model for overall seizures were 77.78%, 60%, and .696 (95% confidence interval = .628-.764), respectively. SIGNIFICANCE: Multimodal extracerebral biosignals (HR, ACC, EDA) detected by a wrist-worn smartwatch can help differentiate between epileptic seizures and normal physical activities. It would be worthwhile to implement our predictive algorithms in commercial seizure detection devices. However, larger studies to externally validate our predictive models are required.