Consumer Wearables Research Articles

Impact of Consumer Wearables Data on Pediatric Surgery Clinicians' Management: Multi-Institutional Scenario-Based Usability Study.

At present, parents lack objective methods to evaluate their child's postoperative recovery following discharge from the hospital. As a result, clinicians are dependent upon a parent's subjective assessment of the child's health status and the child's ability to communicate their symptoms. This subjective nature of home monitoring contributes to unnecessary emergency department (ED) use as well as delays in treatment. However, the integration of data remotely collected using a consumer wearable device has the potential to provide clinicians with objective metrics for postoperative patients to facilitate informed longitudinal, remote assessment. This multi-institutional study aimed to evaluate the impact of adding actual and simulated objective recovery data that were collected remotely using a consumer wearable device to simulated postoperative telephone encounters on clinicians' management. In total, 3 simulated telephone scenarios of patients after an appendectomy were presented to clinicians at 5 children's hospitals. Each scenario was then supplemented with wearable data concerning or reassuring against a postoperative complication. Clinicians rated their likelihood of ED referral before and after the addition of wearable data to evaluate if it changed their recommendation. Clinicians reported confidence in their decision-making. In total, 34 clinicians participated. Compared with the scenario alone, the addition of reassuring wearable data resulted in a decreased likelihood of ED referral for all 3 scenarios (P<.01). When presented with concerning wearable data, there was an increased likelihood of ED referral for 1 of 3 scenarios (P=.72, P=.17, and P<.001). At the institutional level, there was no difference between the 5 institutions in how the wearable data changed the likelihood of ED referral for all 3 scenarios. With the addition of wearable data, 76% (19/25) to 88% (21/24 and 22/25) of clinicians reported increased confidence in their recommendations. The addition of wearable data to simulated telephone scenarios for postdischarge patients who underwent pediatric surgery impacted clinicians' remote patient management at 5 pediatric institutions and increased clinician confidence. Wearable devices are capable of providing real-time measures of recovery, which can be used as a postoperative monitoring tool to reduce delays in care and avoidable health care use.

Detecting cardiac states with wearable photoplethysmograms and implications for out-of-hospital cardiac arrest detection.

Out-of-hospital cardiac arrest (OHCA) is a global health problem affecting approximately 4.4million individuals yearly. OHCA has a poor survival rate, specifically when unwitnessed (accounting for up to 75% of cases). Rapid recognition can significantly improve OHCA survival, and consumer wearables with continuous cardiopulmonary monitoring capabilities hold potential to "witness" cardiac arrest and activate emergency services. In this study, we used an arterial occlusion model to simulate cardiac arrest and investigated the ability of infrared photoplethysmogram (PPG) sensors, often utilized in consumer wearable devices, to differentiate normal cardiac pulsation, pulseless cardiac (i.e., resembling a cardiac arrest), and non-physiologic (i.e., off-body) states. Across the classification models trained and evaluated on three anatomical locations, higher classification performances were observed on the finger (macro average F1-score of 0.964 on the fingertip and 0.954 on the finger base) compared to the wrist (macro average F1-score of 0.837). The wrist-based classification model, which was trained and evaluated using all PPG measurements, including both high- and low-quality recordings, achieved a macro average precision and recall of 0.922 and 0.800, respectively. This wrist-based model, which represents the most common form factor in consumer wearables, could only capture about 43.8% of pulseless events. However, models trained and tested exclusively on high-quality recordings achieved higher classification outcomes (macro average F1-score of 0.975 on the fingertip, 0.973 on the finger base, and 0.934 on the wrist). The fingertip model had the highest performance to differentiate arterial occlusion pulselessness from normal cardiac pulsation and off-body measurements with macro average precision and recall of 0.978 and 0.972, respectively. This model was able to identify 93.7% of pulseless states (i.e., resembling a cardiac arrest event), with a 0.4% false positive rate. All classification models relied on a combination of time-, power spectral density (PSD)-, and frequency-domain features to differentiate normal cardiac pulsation, pulseless cardiac, and off-body PPG recordings. However, our best model represented an idealized detection condition, relying on ensuring high-quality PPG data for training and evaluation of machine learning algorithms. While 90.7% of our PPG recordings from the fingertip were considered of high quality, only 53.2% of the measurements from the wrist passed the quality criteria. Our findings have implications for adapting consumer wearables to provide OHCA detection, involving advancements in hardware and software to ensure high-quality measurements in real-world settings, as well as development of wearables with form factors that enable high-quality PPG data acquisition more consistently. Given these improvements, we demonstrate that OHCA detection can feasibly be made available to anyone using PPG-based consumer wearables.

Machine Learning Models For Predicting Laboratory-based Physical Activity Type From Consumer Wearables In Children

Machine Learning Models For Predicting Laboratory-based Physical Activity Type From Consumer Wearables In Children

The Validity of Apple Watch Series 9 and Ultra 2 for Serial Measurements of Heart Rate Variability and Resting Heart Rate.

The widespread use of wearable devices has enabled continuous monitoring of biometric data, including heart rate variability (HRV) and resting heart rate (RHR). However, the validity of these measurements, particularly from consumer devices like Apple Watch, remains underexplored. This study aimed to validate HRV measurements obtained from Apple Watch Series 9 and Ultra 2 against the Polar H10 chest strap paired with the Kubios HRV software, which together served as the reference standard. A prospective cohort of 39 healthy adults provided 316 HRV measurements over a 14-day period. Generalized Estimating Equations were used to assess the difference in HRV between devices, accounting for repeated measures. Apple Watch tended to underestimate HRV by an average of 8.31 ms compared to the Polar H10 (p = 0.025), with a mean absolute percentage error (MAPE) of 28.88% and a mean absolute error (MAE) of 20.46 ms. The study found no significant impact of RHR discrepancies on HRV differences (p = 0.156), with RHR showing a mean difference of -0.08 bpm, an MAPE of 5.91%, and an MAE of 3.73 bpm. Equivalence testing indicated that the HRV measurements from Apple Watch did not fall within the pre-specified equivalence margin of ±10 ms. Despite accurate RHR measurements, these findings underscore the need for improved HRV algorithms in consumer wearables and caution in interpreting HRV data for clinical or performance monitoring.

Banning biometric mind reading: the case for criminalising mind probing

ABSTRACT Several emerging technologies afford a specific type of interference with privacy which has not yet been conceptualised: inferring information about mental properties of persons on the basis of physiological or biometric signals, in short: mind probing. This paper conceptualises it, analyses several forms and proposes concrete norms that ban and criminalise it. Facial emotion recognition, neuroimaging, or wearable consumer devices such as smartwatches process biometric data to draw inferences about minds; the prevalence and sophistication of such mind probes will soon increase through AI data analysis. This paper explores how human rights law, the EU General Data Protection Regulation and the EU AI Act address mind probes and shows why the current level of protection appears insufficient. This motivates novel norms banning and criminalising non-consensual biometric-based forms of mind reading, ensuring that at least some parts of the mind remain in principle free from non-consensual mind probing.

(Invited) Electrodermal Activity Sensing at Scale

Electrodes have emerged as powerful tools for sensing various physiological signals, paving the way for a new era of wearable consumer devices that offer in situ measurement and analysis. Electrodermal activity (EDA) sensors are used for evaluating autonomic nervous system activity, wherein changes in EDA are associated with physiological excitation reflecting stress, arousal, and emotional changes. The Fitbit Sense 2 and Pixel Watch 2 are two wearable commercial devices that passively measure EDA using wrist-facing electrodes powering a stress management feature. Descriptive findings of the Fitbit Sense 2 across 10 million hours of continuous EDA data collected from over 16,000 people are herein reported, including real-time population response to Thanksgiving 2022 and the 2023 Super Bowl.

Keeping Pace with Wearables: A Living Umbrella Review of Systematic Reviews Evaluating the Accuracy of Consumer Wearable Technologies in Health Measurement.

Consumer wearable technologies have become ubiquitous, with clinical and non-clinical populations leveraging a variety of devices to quantify various aspects of health and wellness. However, the accuracy with which these devices measure biometric outcomes such as heart rate, sleep and physical activity remains unclear. To conduct a 'living' (i.e. ongoing) evaluation of the accuracy of consumer wearable technologies in measuring various physiological outcomes. A systematic search of the literature was conducted in the following scientific databases: MEDLINE via PubMed, Embase, Cinahl and SPORTDiscus via EBSCO. The inclusion criteria required systematic reviews or meta-analyses that evaluated the validation of consumer wearable devices against accepted reference standards. In addition to publication details, review protocol, device specifics and a summary of the authors' results, we extracted data on mean absolute percentage error (MAPE), pooled absolute bias, intraclass correlation coefficients (ICCs) and mean absolute differences. Of 904 identified studies through the initial search, 24 systematic reviews met our inclusion criteria; these systematic reviews included 249 non-duplicate validation studies of consumer wearable devices involving 430,465 participants (43% female). Of the commercially available wearable devices released to date, approximately 11% have been validated for at least one biometric outcome. However, because a typical device can measure a multitude of biometric outcomes, the number of validation studies conducted represents just 3.5% of the total needed for a comprehensive evaluation of these devices. For heart rate, wearables showed a mean bias of ± 3%. In arrhythmia detection, wearables exhibited a pooled sensitivity and specificity of 100% and 95%, respectively. For aerobic capacity, wearables significantly overestimated VO2max by ± 15.24% during resting tests and ± 9.83% during exercise tests. Physical activity intensity measurements had a mean absolute error ranging from 29 to 80%, depending on the intensity of the activity being undertaken. Wearables mostly underestimated step counts (mean absolute percentage errors ranging from - 9 to 12%) and energy expenditure (mean bias = - 3kcal per minute, or - 3%, with error ranging from - 21.27 to 14.76%). For blood oxygen saturation, wearables showed a mean absolute difference of up to 2.0%. Sleep measurement showed a tendency to overestimate total sleep time (mean absolute percentage error typically > 10%). While consumer wearables show promise in health monitoring, a conclusive assessment of their accuracy is impeded by pervasive heterogeneity in research outcomes and methodologies. There is a need for standardised validation protocols and collaborative industry partnerships to enhance the reliability and practical applicability of wearable technology assessments. CRD42023402703.

Detection of Common Respiratory Infections, Including COVID-19, Using Consumer Wearable Devices in Health Care Workers: Prospective Model Validation Study.

The early detection of respiratory infections could improve responses against outbreaks. Wearable devices can provide insights into health and well-being using longitudinal physiological signals. The purpose of this study was to prospectively evaluate the performance of a consumer wearable physiology-based respiratory infection detection algorithm in health care workers. In this study, we evaluated the performance of a previously developed system to predict the presence of COVID-19 or other upper respiratory infections. The system generates real-time alerts using physiological signals recorded from a smartwatch. Resting heart rate, respiratory rate, and heart rate variability measured during the sleeping period were used for prediction. After baseline recordings, when participants received a notification from the system, they were required to undergo testing at a Northwell Health System site. Participants were asked to self-report any positive tests during the study. The accuracy of model prediction was evaluated using respiratory infection results (laboratory results or self-reports), and postnotification surveys were used to evaluate potential confounding factors. A total of 577 participants from Northwell Health in New York were enrolled in the study between January 6, 2022, and July 20, 2022. Of these, 470 successfully completed the study, 89 did not provide sufficient physiological data to receive any prediction from the model, and 18 dropped out. Out of the 470 participants who completed the study and wore the smartwatch as required for the 16-week study duration, the algorithm generated 665 positive alerts, of which 153 (23.0%) were not acted upon to undergo testing for respiratory viruses. Across the 512 instances of positive alerts that involved a respiratory viral panel test, 63 had confirmed respiratory infection results (ie, COVID-19 or other respiratory infections detected using a polymerase chain reaction or home test) and the remaining 449 had negative upper respiratory infection test results. Across all cases, the estimated false-positive rate based on predictions per day was 2%, and the positive-predictive value ranged from 4% to 10% in this specific population, with an observed incidence rate of 198 cases per week per 100,000. Detailed examination of questionnaires filled out after receiving a positive alert revealed that physical or emotional stress events, such as intense exercise, poor sleep, stress, and excessive alcohol consumption, could cause a false-positive result. The real-time alerting system provides advance warning on respiratory viral infections as well as other physical or emotional stress events that could lead to physiological signal changes. This study showed the potential of wearables with embedded alerting systems to provide information on wellness measures.

Magnetotransport properties of ternary tetradymite films with high mobility

(Bi,Sb)2(Te,Se)3 tetradymite materials are among the most efficient for thermoelectric energy conversion, and most robust for topological insulator spintronic technologies, but should possess rather disparate doping properties to be useful for either technology. In this work, we report results on the molecular beam epitaxy growth of p-type (Bi0.43Sb0.57)2Te3 and n-type Bi2(Te0.95Se0.05)3 that can contribute to both technology bases, but are especially useful for topological insulators where low bulk doping is critical for devices to leverage the Dirac-like topological surface states. Comprehensive temperature, field and angular dependent magnetotransport measurements have attested to the superior quality of these ternary tetradymite films, displaying low carrier density on the order of 1018 cm−3 and a record high mobility exceeding 104 cm2 V−1 s−1 at 2 K. The remarkable manifestation of strong Shubnikov–de Haas (SdH) quantum oscillation under 9 T at liquid helium temperatures, as well as the analyses therein, has allowed direct experimental investigation of the tetradymite electronic structure with optimized ternary alloying ratio. Our effort substantiates tetradymites as a critical platform for miniaturized thermoelectric cooling and power generation in wearable consumer electronics, as well as for futuristic topological spintronics with unprecedented magnetoelectric functionalities.

Finger pulse plethysmography predicts gestational hypertension, preeclampsia and gestational diabetes.

Pregnancy complications related to hypertension can affect both mother and newborn. Pulse wave attenuation (PWA) captured through fingertip photoplethysmography (PPG) provide valuable insights into maternal acute hemodynamic and autonomic vascular function. Here, we quantify the nocturnal dynamics of PWA during early pregnancy and assess their association with the development of gestational hypertension, preeclampsia and gestational diabetes. PWA dynamics were assessed on overnight polysomnography-derived PPG signals from a cohort of 2714 pregnant women (mean age: 26.8 ± 5.5 years) enrolled in the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b). We determined the average duration (PWA duration ) and depth (PWA depth ) of PWA events in all women. Odds ratio (OR) analysis-adjusted common confounders indicates that an average PWA duration greater than 8.74 s was associated with the increased risk of gestational hypertension [OR = 1.75 (1.27-2.39), P < 0.001]. Similarly, average PWA depth greater than 1.19 was associated with an increased risk of preeclampsia [OR = 1.53 (1.01-2.33), P = 0.045] and gestational diabetes [OR = 1.66 (1.01-2.73), P = 0.044]. PWA attenuation dynamics during early pregnancy predict the risk of developing gestational hypertension and diabetes condition for women in their later trimesters. Potentially obtainable from smart wearable consumer devices, PWA analysis offers a low-cost, accessible and scalable marker that can enhance the management of pregnancy-induced cardiometabolic issues.

Deciphering the Link: Correlating REM Sleep Patterns with Depressive Symptoms via Consumer Wearable Technology.

This study investigates the correlation between REM sleep patterns, as measured by the Apple Watch, and depressive symptoms in an undiagnosed population. Employing the Apple Watch for data collection, REM sleep duration and frequency were monitored over a specified period. Concurrently, participants' depressive symptoms were evaluated using standardized questionnaires. The analysis, primarily using Spearman's correlation, revealed noteworthy findings. A significant correlation was observed between an increased REM sleep proportion and higher depressive symptom scores, with a correlation coefficient of 0.702, suggesting a robust relationship. These results highlight the potential of using wearable technology, such as the Apple Watch, in early detection and intervention for depressive symptoms, suggesting that alterations in REM sleep could serve as preliminary indicators of depressive tendencies. This approach offers a non-invasive and accessible means to monitor and potentially preempt the progression of depressive disorders. This study's implications extend to the broader context of mental health, emphasizing the importance of sleep assessment in routine health evaluations, particularly for individuals exhibiting early signs of depressive symptoms.

A Comparison of Personalized and Generalized Approaches to Emotion Recognition Using Consumer Wearable Devices: Machine Learning Study.

There are a wide range of potential adverse health effects, ranging from headaches to cardiovascular disease, associated with long-term negative emotions and chronic stress. Because many indicators of stress are imperceptible to observers, the early detection of stress remains a pressing medical need, as it can enable early intervention. Physiological signals offer a noninvasive method for monitoring affective states and are recorded by a growing number of commercially available wearables. We aim to study the differences between personalized and generalized machine learning models for 3-class emotion classification (neutral, stress, and amusement) using wearable biosignal data. We developed a neural network for the 3-class emotion classification problem using data from the Wearable Stress and Affect Detection (WESAD) data set, a multimodal data set with physiological signals from 15 participants. We compared the results between a participant-exclusive generalized, a participant-inclusive generalized, and a personalized deep learning model. For the 3-class classification problem, our personalized model achieved an average accuracy of 95.06% and an F1-score of 91.71%; our participant-inclusive generalized model achieved an average accuracy of 66.95% and an F1-score of 42.50%; and our participant-exclusive generalized model achieved an average accuracy of 67.65% and an F1-score of 43.05%. Our results emphasize the need for increased research in personalized emotion recognition models given that they outperform generalized models in certain contexts. We also demonstrate that personalized machine learning models for emotion classification are viable and can achieve high performance.

Harnessing Consumer Wearable Digital Biomarkers for Individualized Recognition of Postpartum Depression Using the All of Us Research Program Data Set: Cross-Sectional Study.

Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. The main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. Using the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the κ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. Patient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; κ=0.80) models outperforming generalized linear models (mAUC=0.82; κ=0.74), support vector machine (mAUC=0.75; κ=0.72), and k-nearest neighbor (mAUC=0.74; κ=0.62). Model performance decreased in women without PPD, illustrating the method's specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. This research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies.

Consumer wearables and personal devices for tracking the fertile window

The market for technology that tracks ovulation to promote conception is rapidly expanding in the United States, targeting the growing audience of technologically proficient, reproductive-age female consumers. In this narrative review, twenty-three different, non-prescription wearables and devices designed to help women track their fertile window were identified as currently, commercially available in the United States. The majority of these utilize measurements of basal body temperature or combinations of various urinary hormones. This clinical opinion characterizes the scant available research validating the accuracy of these technologies. It further examines research oversight, discusses the utility of these wearables and devices to consumers, and considers these technologies through an equity lens. The discussion concludes with a call for innovation, describing promising new technologies that not only harness unique physiologic parameters to predict ovulation, but also focus on cost-effectiveness with the hope of increasing access to these currently costly devices and wearables.

Exploring Regular Exercisers' Experiences with Readiness/Recovery Scores Produced by Wearable Devices: A Descriptive Qualitative Study.

Meta-session autoregulation, a person-adaptive exercise programming approach, is characterized by individuals' matching exercise demands specifically to their current readiness states. Some consumer wearables provide 'recovery' or 'readiness' scores, computed primarily based on heart rate variability. Despite the growing popularity of consumer wearables and interest in person-adaptive programming, limited research exists on how exercisers interact, interpret and use these scores. This study explores individuals' experiences with wearable devices and their associated readiness or recovery scores. Seventeen regular exercisers who owned and used a Whoop™ band or Oura™ ring for at least 3 months participated in a one-on-one virtual semi-structured interview. Interviews were analyzed using reflexive thematic analysis, with themes supported by 'in-vivo' quotes. This paper focuses on three key themes for a comprehensive demonstration. Theme 1, 'It's more about how I can make adjustments to optimize my programming,' (MPR) highlights users' intended use of wearables for guiding training decisions. Theme 2, 'So many things outside of training modifications have changed,' (Misty) reveals that users also modify non-exercise behaviors to manage and optimize their scores. Theme 3, 'You can't really capture the complexities of a human on a device' (Letty) underscores users' recognition of the limitations and errors associated with these devices emphasizing self-reliance to further direct behavioral adjustments. While wearable devices provide a numeric approach to measuring readiness and recovery, users prioritize self-awareness, flexibility, and personal judgment for exercise decisions. Understanding these experiences, in addition to exploring the psycho-behavioral aspects of user interactions, can contribute to refining meta-session autoregulation.

0333 Sleep Patterns Throughout Mountain Warfare Training in U.S. Marines Measured Using a Consumer Wearable

0333 Sleep Patterns Throughout Mountain Warfare Training in U.S. Marines Measured Using a Consumer Wearable

Predicting stress in first-year college students using sleep data from wearable devices.

Consumer wearables have been successful at measuring sleep and may be useful in predicting changes in mental health measures such as stress. A key challenge remains in quantifying the relationship between sleep measures associated with physiologic stress and a user's experience of stress. Students from a public university enrolled in the Lived Experiences Measured Using Rings Study (LEMURS) provided continuous biometric data and answered weekly surveys during their first semester of college between October-December 2022. We analyzed weekly associations between estimated sleep measures and perceived stress for participants (N = 525). Through mixed-effects regression models, we identified consistent associations between perceived stress scores and average nightly total sleep time (TST), resting heart rate (RHR), heart rate variability (HRV), and respiratory rate (ARR). These effects persisted after controlling for gender and week of the semester. Specifically, for every additional hour of TST, the odds of experiencing moderate-to-high stress decreased by 0.617 or by 38.3% (p<0.01). For each 1 beat per minute increase in RHR, the odds of experiencing moderate-to-high stress increased by 1.036 or by 3.6% (p<0.01). For each 1 millisecond increase in HRV, the odds of experiencing moderate-to-high stress decreased by 0.988 or by 1.2% (p<0.05). For each additional breath per minute increase in ARR, the odds of experiencing moderate-to-high stress increased by 1.230 or by 23.0% (p<0.01). Consistent with previous research, participants who did not identify as male (i.e., female, nonbinary, and transgender participants) had significantly higher self-reported stress throughout the study. The week of the semester was also a significant predictor of stress. Sleep data from wearable devices may help us understand and to better predict stress, a strong signal of the ongoing mental health epidemic among college students.

Scalable Approach to Consumer Wearable Postmarket Surveillance: Development and Validation Study.

With the capability to render prediagnoses, consumer wearables have the potential to affect subsequent diagnoses and the level of care in the health care delivery setting. Despite this, postmarket surveillance of consumer wearables has been hindered by the lack of codified terms in electronic health records (EHRs) to capture wearable use. We sought to develop a weak supervision-based approach to demonstrate the feasibility and efficacy of EHR-based postmarket surveillance on consumer wearables that render atrial fibrillation (AF) prediagnoses. We applied data programming, where labeling heuristics are expressed as code-based labeling functions, to detect incidents of AF prediagnoses. A labeler model was then derived from the predictions of the labeling functions using the Snorkel framework. The labeler model was applied to clinical notes to probabilistically label them, and the labeled notes were then used as a training set to fine-tune a classifier called Clinical-Longformer. The resulting classifier identified patients with an AF prediagnosis. A retrospective cohort study was conducted, where the baseline characteristics and subsequent care patterns of patients identified by the classifier were compared against those who did not receive a prediagnosis. The labeler model derived from the labeling functions showed high accuracy (0.92; F1-score=0.77) on the training set. The classifier trained on the probabilistically labeled notes accurately identified patients with an AF prediagnosis (0.95; F1-score=0.83). The cohort study conducted using the constructed system carried enough statistical power to verify the key findings of the Apple Heart Study, which enrolled a much larger number of participants, where patients who received a prediagnosis tended to be older, male, and White with higher CHA2DS2-VASc (congestive heart failure, hypertension, age ≥75 years, diabetes, stroke, vascular disease, age 65-74 years, sex category) scores (P<.001). We also made a novel discovery that patients with a prediagnosis were more likely to use anticoagulants (525/1037, 50.63% vs 5936/16,560, 35.85%) and have an eventual AF diagnosis (305/1037, 29.41% vs 262/16,560, 1.58%). At the index diagnosis, the existence of a prediagnosis did not distinguish patients based on clinical characteristics, but did correlate with anticoagulant prescription (P=.004 for apixaban and P=.01 for rivaroxaban). Our work establishes the feasibility and efficacy of an EHR-based surveillance system for consumer wearables that render AF prediagnoses. Further work is necessary to generalize these findings for patient populations at other sites.

Comparison of raw accelerometry data from ActiGraph, Apple Watch, Garmin, and Fitbit using a mechanical shaker table.

The purpose of this study was to evaluate the reliability and validity of the raw accelerometry output from research-grade and consumer wearable devices compared to accelerations produced by a mechanical shaker table. Raw accelerometry data from a total of 40 devices (i.e., n = 10 ActiGraph wGT3X-BT, n = 10 Apple Watch Series 7, n = 10 Garmin Vivoactive 4S, and n = 10 Fitbit Sense) were compared to reference accelerations produced by an orbital shaker table at speeds ranging from 0.6 Hz (4.4 milligravity-mg) to 3.2 Hz (124.7mg). Two-way random effects absolute intraclass correlation coefficients (ICC) tested inter-device reliability. Pearson product moment, Lin's concordance correlation coefficient (CCC), absolute error, mean bias, and equivalence testing were calculated to assess the validity between the raw estimates from the devices and the reference metric. Estimates from Apple, ActiGraph, Garmin, and Fitbit were reliable, with ICCs = 0.99, 0.97, 0.88, and 0.88, respectively. Estimates from ActiGraph, Apple, and Fitbit devices exhibited excellent concordance with the reference CCCs = 0.88, 0.83, and 0.85, respectively, while estimates from Garmin exhibited moderate concordance CCC = 0.59 based on the mean aggregation method. ActiGraph, Apple, and Fitbit produced similar absolute errors = 16.9mg, 21.6mg, and 22.0mg, respectively, while Garmin produced higher absolute error = 32.5mg compared to the reference. ActiGraph produced the lowest mean bias 0.0mg (95%CI = -40.0, 41.0). Equivalence testing revealed raw accelerometry data from all devices were not statistically significantly within the equivalence bounds of the shaker speed. Findings from this study provide evidence that raw accelerometry data from Apple, Garmin, and Fitbit devices can be used to reliably estimate movement; however, no estimates were statistically significantly equivalent to the reference. Future studies could explore device-agnostic and harmonization methods for estimating physical activity using the raw accelerometry signals from the consumer wearables studied herein.

Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation

The high prevalence of cardiovascular diseases (CVDs) calls for accessible and cost-effective continuous cardiac monitoring tools. Despite Electrocardiography (ECG) being the gold standard, continuous monitoring remains a challenge, leading to the exploration of Photoplethysmography (PPG), a promising but more basic alternative available in consumer wearables. This notion has recently spurred interest in translating PPG to ECG signals. In this work, we introduce Region-Disentangled Diffusion Model (RDDM), a novel diffusion model designed to capture the complex temporal dynamics of ECG. Traditional Diffusion models like Denoising Diffusion Probabilistic Models (DDPM) face challenges in capturing such nuances due to the indiscriminate noise addition process across the entire signal. Our proposed RDDM overcomes such limitations by incorporating a novel forward process that selectively adds noise to specific regions of interest (ROI) such as QRS complex in ECG signals, and a reverse process that disentangles the denoising of ROI and non-ROI regions. Quantitative experiments demonstrate that RDDM can generate high-fidelity ECG from PPG in as few as 10 diffusion steps, making it highly effective and computationally efficient. Additionally, to rigorously validate the usefulness of the generated ECG signals, we introduce CardioBench, a comprehensive evaluation benchmark for a variety of cardiac-related tasks including heart rate and blood pressure estimation, stress classification, and the detection of atrial fibrillation and diabetes. Our thorough experiments show that RDDM achieves state-of-the-art performance on CardioBench. To the best of our knowledge, RDDM is the first diffusion model for cross-modal signal-to-signal translation in the bio-signal domain.