Consumer Wearables Research Articles

Smart Consumer Wearables as Digital Diagnostic Tools: A Review.

The increasing usage of smart wearable devices has made an impact not only on the lifestyle of the users, but also on biological research and personalized healthcare services. These devices, which carry different types of sensors, have emerged as personalized digital diagnostic tools. Data from such devices have enabled the prediction and detection of various physiological as well as psychological conditions and diseases. In this review, we have focused on the diagnostic applications of wrist-worn wearables to detect multiple diseases such as cardiovascular diseases, neurological disorders, fatty liver diseases, and metabolic disorders, including diabetes, sleep quality, and psychological illnesses. The fruitful usage of wearables requires fast and insightful data analysis, which is feasible through machine learning. In this review, we have also discussed various machine-learning applications and outcomes for wearable data analyses. Finally, we have discussed the current challenges with wearable usage and data, and the future perspectives of wearable devices as diagnostic tools for research and personalized healthcare domains.

Agreement of Sleep Measures-A Comparison between a Sleep Diary and Three Consumer Wearable Devices.

Nowadays, self-tracking and optimization are widely spread. As sleep is essential for well-being, health, and peak performance, the number of available consumer technologies to assess individual sleep behavior is increasing rapidly. However, little is known about the consumer wearables’ usability and reliability for sleep tracking. Therefore, the aim of the present study was to compare the sleep measures of wearable devices with a standardized sleep diary in young healthy adults in free-living conditions. We tracked night sleep from 30 participants (19 females, 11 males; 24.3 ± 4.2 years old). Each wore three wearables and simultaneously assessed individual sleep patterns for four consecutive nights. Wearables and diaries correlated substantially regarding time in bed (Range CCCLin: 0.74–0.84) and total sleep time (Range CCCLin: 0.76–0.85). There was no sufficient agreement regarding the measures of sleep efficiency (Range CCCLin: 0.05–0.34) and sleep interruptions (Range CCCLin: −0.02–0.10). Finally, these results show wearables to be an easy-to-handle, time- and cost-efficient alternative to tracking sleep in healthy populations. Future research should develop and empirically test the usability of such consumer sleep technologies.

Medical Research Charities and Biopharmaceutical Companies as Partners in Patient-Centred R&D.

Life science research and development (R&D) companies are all too aware of the importance of patient perspectives but also of the barriers to engaging directly with patients, not least compliance, complex technical and regulatory issues, and the need to meet multifaceted expectations. Medical research charities (MRCs), highly technical and professional organisations, work directly with patients; they represent an expert resource for the science of their field, for disease-related patient advocacy issues and to advise and assist R&D companies in devising meaningful trials. The Pistoia Alliance, a non-profit organisation facilitating life sciences R&D, gathered a number of UK MRCs focused on complex lifelong conditions. The group used workshops and an opinion questionnaire for a snapshot of how the charities believe their knowledge and patient experiences could contribute insights and efficiencies to commercial R&D. MRCs argued that for chronic conditions, the patient perspective is vital in facilitating and de-risking trials, promoting patient motivation, compliance and study viability. MRCs and the patients they represent want to see successful trials, and it is in everyone’s interest that well considered studies can proceed. Today, with remote assessments, consumer wearables and digital health technologies, MRCs and patients are already collating substantial data sets that are relevant to quality-of-life benefits, regulatory and value assessments, all of great interest to biopharmaceutical companies. In turn, MRCs would benefit from the experience of biopharma in generating clinical data and implementing novel technologies.

High-Resolution Digital Phenotypes From Consumer Wearables and Their Applications in Machine Learning of Cardiometabolic Risk Markers: Cohort Study.

BackgroundConsumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized.ObjectiveWe aimed to derive high-resolution digital phenotypes from observational wearable recordings and to examine their associations with modifiable and inherent markers of cardiometabolic disease risk.MethodsWe introduced a principled framework to extract interpretable high-resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes the handling of data irregularities; encodes contextual information regarding the underlying physiological state at any given time; and generates a set of 66 minimally redundant features across active, sedentary, and sleep states. We applied our approach to a multimodal data set, from the SingHEART study (NCT02791152), which comprises heart rate and step count time series from wearables, clinical screening profiles, and whole genome sequences from 692 healthy volunteers. We used machine learning to model nonlinear relationships between the high-resolution phenotypes on the one hand and clinical or genomic risk markers for blood pressure, lipid, weight and sugar abnormalities on the other. For each risk type, we performed model comparisons based on Brier scores to assess the predictive value of high-resolution features over and beyond typical baselines. We also qualitatively characterized the wearable phenotypes for participants who had actualized clinical events.ResultsWe found that the high-resolution features have higher predictive value than typical baselines for clinical markers of cardiometabolic disease risk: the best models based on high-resolution features had 17.9% and 7.36% improvement in Brier score over baselines based on age and gender and resting heart rate, respectively (P<.001 in each case). Furthermore, heart rate dynamics from different activity states contain distinct information (maximum absolute correlation coefficient of 0.15). Heart rate dynamics in sedentary states are most predictive of lipid abnormalities and obesity, whereas patterns in active states are most predictive of blood pressure abnormalities (P<.001). Moreover, in comparison with standard measures, higher resolution patterns in wearable heart rate recordings are better able to represent subtle physiological dynamics related to genomic risk for cardiometabolic disease (improvement of 11.9%-22.0% in Brier scores; P<.001). Finally, illustrative case studies reveal connections between these high-resolution phenotypes and actualized clinical events, even for borderline profiles lacking apparent cardiometabolic risk markers.ConclusionsHigh-resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance the prediction of cardiometabolic disease risk and could enable more proactive and personalized health management.

Wearable In-Ear PPG: Detailed Respiratory Variations Enable Classification of COPD.

An ability to extract detailed spirometry-like breathing waveforms from wearable sensors promises to greatly improve respiratory health monitoring. Photoplethysmography (PPG) has been researched in depth for estimation of respiration rate, given that it varies with respiration through overall intensity, pulse amplitude and pulse interval. We compare and contrast the extraction of these three respiratory modes from both the ear canal and finger and show a marked improvement in the respiratory power for respiration induced intensity variations and pulse amplitude variations when recording from the ear canal. We next employ a data driven multi-scale method, noise assisted multivariate empirical mode decomposition (NA-MEMD), which allows for simultaneous analysis of all three respiratory modes to extract detailed respiratory waveforms from in-ear PPG. For rigour, we considered in-ear PPG recordings from healthy subjects, both older and young, patients with chronic obstructive pulmonary disease (COPD) and idiopathic pulmonary fibrosis (IPF) and healthy subjects with artificially obstructed breathing. Specific in-ear PPG waveform changes are observed for COPD, such as a decreased inspiratory duty cycle and an increased inspiratory magnitude, when compared with expiratory magnitude. These differences are used to classify COPD from healthy and IPF waveforms with a sensitivity of 87% and an overall accuracy of 92%. Our findings indicate the promise of in-ear PPG for COPD screening and unobtrusive respiratory monitoring in ambulatory scenarios and in consumer wearables.

Evaluation of a wearable consumer noise measurement device in a laboratory setting.

Exposure to noise occurs throughout daily life and, depending on the intensity, duration, and context, can lead to hearing loss, disturbed sleep, decreased academic achievement, and other negative health outcomes. Recently, smartwatches that use the device's onboard microphone to measure noise levels were released. This study evaluated the accuracy of these smartwatches in a controlled laboratory setting. For broadband pink noise, a total of 11 441 measurements were collected. The results showed that, on average, the smartwatch reported 3.4 dBA lower than the reference system on average. For the octave-band, a total of 18 449 measurements were collected. The smartwatch measured lower than the reference microphone from the 125 Hz to 1000 Hz octave bands, were somewhat in agreement at 2000 Hz, measured higher sound pressure levels than the reference microphone at 4000 Hz, and then lower at 8000 Hz. Despite not meeting the ANSI criteria for sound level meters, in some cases, these smartwatches still provide a reasonable degree of accuracy and have the potential for use in studies that require the measurement of personal noise exposure over an extended period.

Using Consumer-Wearable Activity Trackers for Risk Prediction of Life-Threatening Heart Arrhythmia in Patients with an Implantable Cardioverter-Defibrillator: An Exploratory Observational Study.

Ventricular arrhythmia (VA) is a leading cause of sudden death and health deterioration. Recent advances in predictive analytics and wearable technology for behavior assessment show promise but require further investigation. Yet, previous studies have only assessed other health outcomes and monitored patients for short durations (7–14 days). This study explores how behaviors reported by a consumer wearable can assist VA risk prediction. An exploratory observational study was conducted with participants who had an implantable cardioverter-defibrillator (ICD) and wore a Fitbit Alta HR consumer wearable. Fitbit reported behavioral markers for physical activity (light, fair, vigorous), sleep, and heart rate. A case-crossover analysis using conditional logistic regression assessed the effects of time-adjusted behaviors over 1–8 weeks on VA incidence. Twenty-seven patients (25 males, median age 59 years) were included. Among the participants, ICDs recorded 262 VA events during 8093 days monitored by Fitbit (median follow-up period 960 days). Longer light to fair activity durations and a higher heart rate increased the odds of a VA event (p < 0.001). In contrast, lengthier fair to vigorous activity and sleep durations decreased the odds of a VA event (p < 0.001). Future studies using consumer wearables in a larger population should prioritize these outcomes to further assess VA risk.

Detecting Driver Sleepiness Using Consumer Wearable Devices in Manual and Partial Automated Real-Road Driving

Detecting Driver Sleepiness Using Consumer Wearable Devices in Manual and Partial Automated Real-Road Driving

Technical, Regulatory, Economic, and Trust Issues Preventing Successful Integration of Sensors into the Mainstream Consumer Wearables Market.

Sensors that track physiological biomarkers of health must be successfully incorporated into a fieldable, wearable device if they are to revolutionize the management of remote patient care and preventative medicine. This perspective article discusses logistical considerations that may impede the process of adapting a body-worn laboratory sensor into a commercial-integrated health monitoring system with a focus on examples from sleep tracking technology.

Direct-to-consumer detection of atrial fibrillation in a smartwatch electrocardiogram: Medical overuse, medicalisation and the experience of consumers

The Apple Watch Electrocardiogram (ECG) is a digital feature that detects signs of atrial fibrillation (AFib), a heart arrhythmia that can lead to stroke. Unlike AFib detection offered in a clinical setting to patients or those at higher risk, the Apple Watch ECG is a direct-to-consumer (DTC) product marketed to the healthy as a self-performed medical test. The feature is incorporated in the design as one of many applications in a multifunctional smartwatch. The Apple Watch ECG signals the movement of consumer wearables into the domain of medical devices, and the highly contested practice of AFib screening. This article examines how this technology produces new avenues for medical overuse among people who are unlikely to gain clinical benefit, and who as active consumers become medicalised via taking part in disease-specific monitoring. Interviews with Apple Watch ECG consumers suggest their strongly trust in the Apple brand is amplified by the promissory quality of screening and technical innovation. What would otherwise be a costly clinical procedure is condensed into an accessible function in a wearable device. Consequently, AFib screening loses its clinical purpose, and is instead refashioned into a component of healthy lifestyle behaviour. Repeat self-screening becomes ‘bundled’ with similar health monitoring practices routinised in consumer wearables. Active uptake supports a market for the product and adds to the reputation of the Apple brand such that consumers become complicit in legitimising a medical practice that has limited clinical justification.

Considerations for the Use of Consumer-Grade Wearables and Smartphones in Population Surveillance of Physical Activity

As smartphone and wearable device ownership increase, interest in their utility to monitor physical activity has risen concurrently. Numerous examples of the application of wearables in clinical and epidemiological research settings already exist. However, whether these devices are all suitable for physical activity surveillance is open for debate. In this commentary, we respond to a commentary by Mair et al. (2021) and discuss four key issues specifically relevant to surveillance that we believe need to be tackled before consumer wearables can be considered for this measurement purpose: representative sampling, representative wear time, validity and reliability, and compatibility between devices. A recurring theme is how to deal with systematic biases by demographic groups. We suggest some potential solutions to the issues of concern such as providing individuals with standardized devices, considering summary metrics of physical activity less prone to wear time biases, and the development of a framework to harmonize estimates between device types and their inbuilt algorithms. We encourage collaborative efforts from researchers and consumer wearable manufacturers in this area. In the meantime, we caution against the use of consumer wearable device data for inference of population-level activity without the consideration of these issues.

Plataformização da pele? Tatuagens biométricas, dataísmo e a datificação do consumidor

Abstract This theoretical essay starts from the possibility of the platformization of the skin through the use of biometric tattoos to analyze the imminent risks posed by consumer wearables and their biopolitical marketing in the context of communicative capitalism. The theme is approached through a critical perspective that goes beyond the marketing rhetoric that focuses on individual improvement and self-care through consumer datification. The aim is to overcome the opacity of technological systems associated with communication and information technologies. The work discusses the consequences of biopolitical marketing associated with the consumption of wearables; for example, the formation of profiles informed by governmentality based on a belief in dataism, which fosters objective truth markets based on the capture and analysis of big data. The essay concludes that the consumption of wearables associated with the platform economy, datification, and dataism poses risks to privacy and democracy, especially in contexts such as the pandemic, in which dependence on communication and information technologies is evident.

A Digital Therapeutic Intervention Delivering Biofeedback for Panic Attacks (PanicMechanic): Feasibility and Usability Study.

BackgroundPanic attacks (PAs) are an impairing mental health problem that affects >11% of adults every year. PAs are episodic, and it is difficult to predict when or where they may occur; thus, they are challenging to study and treat.ObjectiveThe aim of this study is to present PanicMechanic, a novel mobile health app that captures heart rate–based data and delivers biofeedback during PAs.MethodsIn our first analysis, we leveraged this tool to capture profiles of real-world PAs in the largest sample to date (148 attacks from 50 users). In our second analysis, we present the results from a pilot study to assess the usefulness of PanicMechanic as a PA intervention (N=18).ResultsThe results demonstrate that heart rate fluctuates by about 15 beats per minute during a PA and takes approximately 30 seconds to return to baseline from peak, cycling approximately 4 times during each attack despite the consistently decreasing anxiety ratings. Thoughts about health were the most common trigger and potential lifestyle contributors include slightly worse stress, sleep, and eating habits and slightly less exercise and drug or alcohol consumption than typical.ConclusionsThe pilot study revealed that PanicMechanic is largely feasible to use but would be made more so with modifications to the app and the integration of consumer wearables. Similarly, participants found PanicMechanic useful, with 94% (15/16) indicating that they would recommend PanicMechanic to others who have PAs. These results highlight the need for future development and a controlled trial to establish the effectiveness of this digital therapeutic for preventing PAs.

On the Security of Bluetooth Low Energy in Two Consumer Wearable Heart Rate Monitors/Sensing Devices.

Since its inception in 2013, Bluetooth Low Energy (BLE) has become the standard for short-distance wireless communication in many consumer devices, as well as special-purpose devices. In this study, we analyze the security features available in Bluetooth LE standards and evaluate the features implemented in two BLE wearable devices (a Fitbit heart rate wristband and a Polar heart rate chest wearable) and a BLE keyboard to explore which security features in the BLE standards are implemented in the devices. In this study, we used the ComProbe Bluetooth Protocol Analyzer, along with the ComProbe software to capture the BLE traffic of these three devices. We found that even though the standards provide security mechanisms, because the Bluetooth Special Interest Group does not require that manufacturers fully comply with the standards, some manufacturers fail to implement proper security mechanisms. The circumvention of security in Bluetooth devices could leak private data that could be exploited by rogue actors/hackers, thus creating security, privacy, and, possibly, safety issues for consumers and the public. We propose the design of a Bluetooth Security Facts Label (BSFL) to be included on a Bluetooth/BLE enabled device’s commercial packaging and conclude that there should be better mechanisms for informing users about the security and privacy provisions of the devices they acquire and use and to educate the public on protection of their privacy when buying a connected device.

Enabling Research and Clinical Use of Patient-Generated Health Data (the mindLAMP Platform): Digital Phenotyping Study.

BackgroundThere is a growing need for the integration of patient-generated health data (PGHD) into research and clinical care to enable personalized, preventive, and interactive care, but technical and organizational challenges, such as the lack of standards and easy-to-use tools, preclude the effective use of PGHD generated from consumer devices, such as smartphones and wearables.ObjectiveThis study outlines how we used mobile apps and semantic web standards such as HTTP 2.0, Representational State Transfer, JSON (JavaScript Object Notation), JSON Schema, Transport Layer Security (version 1.3), Advanced Encryption Standard-256, OpenAPI, HTML5, and Vega, in conjunction with patient and provider feedback to completely update a previous version of mindLAMP.MethodsThe Learn, Assess, Manage, and Prevent (LAMP) platform addresses the abovementioned challenges in enhancing clinical insight by supporting research, data analysis, and implementation efforts around PGHD as an open-source solution with freely accessible and shared code.ResultsWith a simplified programming interface and novel data representation that captures additional metadata, the LAMP platform enables interoperability with existing Fast Healthcare Interoperability Resources–based health care systems as well as consumer wearables and services such as Apple HealthKit and Google Fit. The companion Cortex data analysis and machine learning toolkit offer robust support for artificial intelligence, behavioral feature extraction, interactive visualizations, and high-performance data processing through parallelization and vectorization techniques.ConclusionsThe LAMP platform incorporates feedback from patients and clinicians alongside a standards-based approach to address these needs and functions across a wide range of use cases through its customizable and flexible components. These range from simple survey-based research to international consortiums capturing multimodal data to simple delivery of mindfulness exercises through personalized, just-in-time adaptive interventions.

Effect of U-Flex-to-Install and Dynamic U-Flexing on Li-Ion Battery State of Health Degradation Subjected to Varying Fold Orientations, Folding Speeds, Depths of Charge, C-Rates, and Temperatures

Abstract The demand for wearable consumer electronics, fitness accessories, and biomedical equipment has led to the growth research and development of thin flexible batteries. Wearable equipment and other asset monitoring applications require conformal installation of power sources on nonplanar surfaces. For power sources in wearable electronics, durability to sustain repetitive mechanical stresses induced by human body motion is paramount along with the usual desirable power source characteristics. Previous research documenting the reliability of statically and dynamically folded power sources is scarce and does not follow standardized test protocols. Particularly, the use of manual stressing for mechanical folding of the power sources instead of a mechanical test setup is a key shortcoming in existing literature. Data are lacking on battery life cycling and in situ mechanical stress-testing of the power sources including their impact of performance and reliability. This study aims to overcome these deficiencies by testing a commercial Li-ion power source under static as well as dynamic folding. Furthermore, the fold orientation and its fold speed are varied to evaluate the effect of different mechanical stress topologies on the power source. Finally, a regression model was developed to capture the effect of these use parameters on battery capacity degradation.

Validity of a Global Positioning System-Based Algorithm and Consumer Wearables for Classifying Active Trips in Children and Adults.

To investigate the convergent validity of a global positioning system (GPS)-based and two consumer-based measures with trip logs for classifying pedestrian, cycling, and vehicle trips in children and adults. Participants (N = 34) wore a Qstarz GPS tracker, Fitbit Alta, and Garmin vivosmart 3 on multiple days and logged their outdoor pedestrian, cycling, and vehicle trips. Logged trips were compared with device-measured trips using the Personal Activity Location Measurement System (PALMS) GPS-based algorithms, Fitbit's SmartTrack, and Garmin's Move IQ. Trip- and day-level agreement were tested. The PALMS identified and correctly classified the mode of 75.6%, 94.5%, and 96.9% of pedestrian, cycling, and vehicle trips (84.5% of active trips, F1 = 0.84 and 0.87) as compared with the log. Fitbit and Garmin identified and correctly classified the mode of 26.8% and 17.8% (22.6% of active trips, F1 = 0.40 and 0.30) and 46.3% and 43.8% (45.2% of active trips, F1 = 0.58 and 0.59) of pedestrian and cycling trips. Garmin was more prone to false positives (false trips not logged). Day-level agreement for PALMS and Garmin versus logs was favorable across trip modes, though PALMS performed best. Fitbit significantly underestimated daily cycling. Results were similar but slightly less favorable for children than adults. The PALMS showed good convergent validity in children and adults and were about 50% and 27% more accurate than Fitbit and Garmin (based on F1). Empirically-based recommendations for improving PALMS' pedestrian classification are provided. Since the consumer devices capture both indoor and outdoor walking/running and cycling, they are less appropriate for trip-based research.

Consumer Wearables for Patient Monitoring in Otolaryngology: A State of the Art Review.

Consumer wearables, such as the Apple Watch or Fitbit devices, have become increasingly commonplace over the past decade. The application of these devices to health care remains an area of significant yet ill-defined promise. This review aims to identify the potential role of consumer wearables for the monitoring of otolaryngology patients. PubMed. A PubMed search was conducted to identify the use of consumer wearables for the assessment of clinical outcomes relevant to otolaryngology. Articles were included if they described the use of wearables that were designed for continuous wear and were available for consumer purchase in the United States. Articles meeting inclusion criteria were synthesized into a final narrative review. In the perioperative setting, consumer wearables could facilitate prehabilitation before major surgery and prediction of clinical outcomes. The use of consumer wearables in the inpatient setting could allow for early recognition of parameters suggestive of poor or declining health. The real-time feedback provided by these devices in the remote setting could be incorporated into behavioral interventions to promote patients' engagement with healthy behaviors. Various concerns surrounding the privacy, ownership, and validity of wearable-derived data must be addressed before their widespread adoption in health care. Understanding how to leverage the wealth of biometric data collected by consumer wearables to improve health outcomes will become a high-impact area of research and clinical care. Well-designed comparative studies that elucidate the value and clinical applicability of these data are needed.

Abstract 11436: Trends in Consumer Wearable Devices in a Primary Care Cohort

Introduction: Consumer wearable devices that record data relevant to cardiac health are widely available. However, whether providers find these devices relevant to clinical care, and in which patients, is unknown. Methods: We identified mention of wearable devices in provider notes between 2005 and 2020 in an EHR cohort of primary care patients in the Mass General Brigham healthcare system. Outpatient notes containing &gt;250 characters were included. Search terms included “AliveCor,” “Apple Watch,” “Fitbit,” “Garmin,” “smartwatch,” “fitness tracker,” and alternative spellings. Demographics and cardiovascular comorbidities were compared between patients with and without device mentions. Notes with and without device mention were compared with respect to clinic type and diagnosis codes occurring on the same date. Incidence rates for device mention were calculated for each year. Results: The final sample comprised 494,254 patients and 27,221,019 notes. The mean age was 49.1 ± 17.0 years, and median follow-up was 6.9 (Q1 2.7, Q3 11.9) years. A total of 8,955 (1.8%) patients had ≥1 note mentioning a device. The proportion of notes mentioning devices increased over time (Figure), with increased incidence of device mention from 0.006 to 7.5 per 1000 person-years between 2005 and 2019. Most patients with device mentions were female (69.4%) and white (86.7%). At the time of first device mention, the mean age was 55.3 ± 14.0 years and 1,183 (13.2%) patients had prevalent atrial fibrillation (AF). Cardiology clinic notes comprised a greater proportion of notes with device mentions versus notes without device mentions (15.7% [5,336] vs 3.7% [996,971], p&lt;0.001). A total of 9.3% (3,160) of notes with device mentions had same-day diagnosis codes for AF, versus 2.7% (730,614) of notes without device mentions (p &lt; 0.001). Conclusion: Provider mention of consumer wearable devices in EHR notes has increased over time, and is associated with cardiology clinic notes and diagnosis codes for AF.

Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling

BackgroundDepression is a prevalent mental disorder that is undiagnosed and untreated in half of all cases. Wearable activity trackers collect fine-grained sensor data characterizing the behavior and physiology of users (ie, digital biomarkers), which could be used for timely, unobtrusive, and scalable depression screening.ObjectiveThe aim of this study was to examine the predictive ability of digital biomarkers, based on sensor data from consumer-grade wearables, to detect risk of depression in a working population.MethodsThis was a cross-sectional study of 290 healthy working adults. Participants wore Fitbit Charge 2 devices for 14 consecutive days and completed a health survey, including screening for depressive symptoms using the 9-item Patient Health Questionnaire (PHQ-9), at baseline and 2 weeks later. We extracted a range of known and novel digital biomarkers characterizing physical activity, sleep patterns, and circadian rhythms from wearables using steps, heart rate, energy expenditure, and sleep data. Associations between severity of depressive symptoms and digital biomarkers were examined with Spearman correlation and multiple regression analyses adjusted for potential confounders, including sociodemographic characteristics, alcohol consumption, smoking, self-rated health, subjective sleep characteristics, and loneliness. Supervised machine learning with statistically selected digital biomarkers was used to predict risk of depression (ie, symptom severity and screening status). We used varying cutoff scores from an acceptable PHQ-9 score range to define the depression group and different subsamples for classification, while the set of statistically selected digital biomarkers remained the same. For the performance evaluation, we used k-fold cross-validation and obtained accuracy measures from the holdout folds.ResultsA total of 267 participants were included in the analysis. The mean age of the participants was 33 (SD 8.6, range 21-64) years. Out of 267 participants, there was a mild female bias displayed (n=170, 63.7%). The majority of the participants were Chinese (n=211, 79.0%), single (n=163, 61.0%), and had a university degree (n=238, 89.1%). We found that a greater severity of depressive symptoms was robustly associated with greater variation of nighttime heart rate between 2 AM and 4 AM and between 4 AM and 6 AM; it was also associated with lower regularity of weekday circadian rhythms based on steps and estimated with nonparametric measures of interdaily stability and autocorrelation as well as fewer steps-based daily peaks. Despite several reliable associations, our evidence showed limited ability of digital biomarkers to detect depression in the whole sample of working adults. However, in balanced and contrasted subsamples comprised of depressed and healthy participants with no risk of depression (ie, no or minimal depressive symptoms), the model achieved an accuracy of 80%, a sensitivity of 82%, and a specificity of 78% in detecting subjects at high risk of depression.ConclusionsDigital biomarkers that have been discovered and are based on behavioral and physiological data from consumer wearables could detect increased risk of depression and have the potential to assist in depression screening, yet current evidence shows limited predictive ability. Machine learning models combining these digital biomarkers could discriminate between individuals with a high risk of depression and individuals with no risk.