Validation of the Mobile App-Recorded Circadian Rhythm by a Digital Footprint

Developing Methods for Assessing Mental Activity Using Human-Smartphone Interactions: Comparative Analysis of Activity Levels and Phase Patterns in General Mental Activities, Working Mental Activities, and Physical Activities

BACKGROUND

Human biological rhythms are commonly assessed through physical activity (PA) measurement, but mental activity may offer a more substantial reflection of human biological rhythms.

OBJECTIVE

This study proposes a novel approach based on human-smartphone interaction to compute mental activity, encompassing general mental activity (GMA) and working mental activity (WMA).

METHODS

A total of 24 health care professionals participated, wearing wrist actigraphy devices and using the "Staff Hours" app for more than 457 person-days, including 332 workdays and 125 nonworkdays. PA was measured using actigraphy, while GMA and WMA were assessed based on patterns of smartphone interactions. To model WMA, machine learning techniques such as extreme gradient boosting and convolutional neural networks were applied, using human-smartphone interaction patterns and GPS-defined work hours. The data were organized by date and divided into person-days, with an 80:20 split for training and testing data sets to minimize overfitting and maximize model robustness. The study also adopted the M10 metric to quantify daily activity levels by calculating the average acceleration during the 10-hour period of highest activity each day, which facilitated the assessment of the interrelations between PA, GMA, and WMA and sleep indicators. Phase differences, such as those between PA and GMA, were defined using a second-order Butterworth filter and Hilbert transform to extract and calculate circadian rhythms and instantaneous phases. This calculation involved subtracting the phase of the reference signal from that of the target signal and averaging these differences to provide a stable and clear measure of the phase relationship between the signals. Additionally, multilevel modeling explored associations between sleep indicators (total sleep time, midpoint of sleep) and next-day activity levels, accounting for the data's nested structure.

RESULTS

Significant differences in activity levels were noted between workdays and nonworkdays, with WMA occurring approximately 1.08 hours earlier than PA during workdays (P<.001). Conversely, GMA was observed to commence about 1.22 hours later than PA (P<.001). Furthermore, a significant negative correlation was identified between the activity level of WMA and the previous night's midpoint of sleep (β=-0.263, P<.001), indicating that later bedtimes and wake times were linked to reduced activity levels in WMA the following day. However, there was no significant correlation between WMA's activity levels and total sleep time. Similarly, no significant correlations were found between the activity levels of PA and GMA and sleep indicators from the previous night.

CONCLUSIONS

This study significantly advances the understanding of human biological rhythms by developing and highlighting GMA and WMA as key indicators, derived from human-smartphone interactions. These findings offer novel insights into how mental activities, alongside PA, are intricately linked to sleep patterns, emphasizing the potential of GMA and WMA in behavioral and health studies.

Comparing Human-Smartphone Interactions and Actigraphy Measurements for Circadian Rhythm Stability and Adiposity: Algorithm Development and Validation Study

BACKGROUND

This study aimed to investigate the relationships between adiposity and circadian rhythm and compare the measurement of circadian rhythm using both actigraphy and a smartphone app that tracks human-smartphone interactions.

OBJECTIVE

We hypothesized that the app-based measurement may provide more comprehensive information, including light-sensitive melatonin secretion and social rhythm, and have stronger correlations with adiposity indicators.

METHODS

We enrolled a total of 78 participants (mean age 41.5, SD 9.9 years; 46/78, 59% women) from both an obesity outpatient clinic and a workplace health promotion program. All participants (n=29 with obesity, n=16 overweight, and n=33 controls) were required to wear a wrist actigraphy device and install the Rhythm app for a minimum of 4 weeks, contributing to a total of 2182 person-days of data collection. The Rhythm app estimates sleep and circadian rhythm indicators by tracking human-smartphone interactions, which correspond to actigraphy. We examined the correlations between adiposity indices and sleep and circadian rhythm indicators, including sleep time, chronotype, and regularity of circadian rhythm, while controlling for physical activity level, age, and gender.

RESULTS

Sleep onset and wake time measurements did not differ significantly between the app and actigraphy; however, wake after sleep onset was longer (13.5, SD 19.5 minutes) with the app, resulting in a longer actigraphy-measured total sleep time (TST) of 20.2 (SD 66.7) minutes. The obesity group had a significantly longer TST with both methods. App-measured circadian rhythm indicators were significantly lower than their actigraphy-measured counterparts. The obesity group had significantly lower interdaily stability (IS) than the control group with both methods. The multivariable-adjusted model revealed a negative correlation between BMI and app-measured IS (P=.007). Body fat percentage (BF%) and visceral adipose tissue area (VAT) showed significant correlations with both app-measured IS and actigraphy-measured IS. The app-measured midpoint of sleep showed a positive correlation with both BF% and VAT. Actigraphy-measured TST exhibited a positive correlation with BMI, VAT, and BF%, while no significant correlation was found between app-measured TST and either BMI, VAT, or BF%.

CONCLUSIONS

Our findings suggest that IS is strongly correlated with various adiposity indicators. Further exploration of the role of circadian rhythm, particularly measured through human-smartphone interactions, in obesity prevention could be warranted.

Developing a Machine Learning Algorithm to Predict the Probability of Medical Staff Work Mode Using Human-Smartphone Interaction Patterns: Algorithm Development and Validation Study

BACKGROUND

Traditional methods for investigating work hours rely on an employee's physical presence at the worksite. However, accurately identifying break times at the worksite and distinguishing remote work outside the worksite poses challenges in work hour estimations. Machine learning has the potential to differentiate between human-smartphone interactions at work and off work.

OBJECTIVE

In this study, we aimed to develop a novel approach called "probability in work mode," which leverages human-smartphone interaction patterns and corresponding GPS location data to estimate work hours.

METHODS

To capture human-smartphone interactions and GPS locations, we used the "Staff Hours" app, developed by our team, to passively and continuously record participants' screen events, including timestamps of notifications, screen on or off occurrences, and app usage patterns. Extreme gradient boosted trees were used to transform these interaction patterns into a probability, while 1-dimensional convolutional neural networks generated successive probabilities based on previous sequence probabilities. The resulting probability in work mode allowed us to discern periods of office work, off-work, breaks at the worksite, and remote work.

RESULTS

Our study included 121 participants, contributing to a total of 5503 person-days (person-days represent the cumulative number of days across all participants on which data were collected and analyzed). The developed machine learning model exhibited an average prediction performance, measured by the area under the receiver operating characteristic curve, of 0.915 (SD 0.064). Work hours estimated using the probability in work mode (higher than 0.5) were significantly longer (mean 11.2, SD 2.8 hours per day) than the GPS-defined counterparts (mean 10.2, SD 2.3 hours per day; P<.001). This discrepancy was attributed to the higher remote work time of 111.6 (SD 106.4) minutes compared to the break time of 54.7 (SD 74.5) minutes.

CONCLUSIONS

Our novel approach, the probability in work mode, harnessed human-smartphone interaction patterns and machine learning models to enhance the precision and accuracy of work hour investigation. By integrating human-smartphone interactions and GPS data, our method provides valuable insights into work patterns, including remote work and breaks, offering potential applications in optimizing work productivity and well-being.

Examining Human-Smartphone Interaction as a Proxy for Circadian Rhythm in Patients With Insomnia: Cross-Sectional Study

BACKGROUND

The sleep and circadian rhythm patterns associated with smartphone use, which are influenced by mental activities, might be closely linked to sleep quality and depressive symptoms, similar to the conventional actigraphy-based assessments of physical activity.

OBJECTIVE

The primary objective of this study was to develop app-defined circadian rhythm and sleep indicators and compare them with actigraphy-derived measures. Additionally, we aimed to explore the clinical correlations of these indicators in individuals with insomnia and healthy controls.

METHODS

The mobile app "Rhythm" was developed to record smartphone use time stamps and calculate circadian rhythms in 33 patients with insomnia and 33 age- and gender-matched healthy controls, totaling 2097 person-days. Simultaneously, we used standard actigraphy to quantify participants' sleep-wake cycles. Sleep indicators included sleep onset, wake time (WT), wake after sleep onset (WASO), and the number of awakenings (NAWK). Circadian rhythm metrics quantified the relative amplitude, interdaily stability, and intradaily variability based on either smartphone use or physical activity data.

RESULTS

Comparisons between app-defined and actigraphy-defined sleep onsets, WTs, total sleep times, and NAWK did not reveal any significant differences (all P>.05). Both app-defined and actigraphy-defined sleep indicators successfully captured clinical features of insomnia, indicating prolonged WASO, increased NAWK, and delayed sleep onset and WT in patients with insomnia compared with healthy controls. The Pittsburgh Sleep Quality Index scores were positively correlated with WASO and NAWK, regardless of whether they were measured by the app or actigraphy. Depressive symptom scores were positively correlated with app-defined intradaily variability (β=9.786, SD 3.756; P=.01) and negatively correlated with actigraphy-based relative amplitude (β=-21.693, SD 8.214; P=.01), indicating disrupted circadian rhythmicity in individuals with depression. However, depressive symptom scores were negatively correlated with actigraphy-based intradaily variability (β=-7.877, SD 3.110; P=.01) and not significantly correlated with app-defined relative amplitude (β=-3.859, SD 12.352; P=.76).

CONCLUSIONS

This study highlights the potential of smartphone-derived sleep and circadian rhythms as digital biomarkers, complementing standard actigraphy indicators. Although significant correlations with clinical manifestations of insomnia were observed, limitations in the evidence and the need for further research on predictive utility should be considered. Nonetheless, smartphone data hold promise for enhancing sleep monitoring and mental health assessments in digital health research.

Pilot feasibility testing of biomathematical model recommendations for personalising sleep timing in shift workers

Sleep disturbances and circadian disruption play a central role in adverse health, safety, and performance outcomes in shift workers. While biomathematical models of sleep and alertness can be used to personalise interventions for shift workers, their practical implementation is undertested. This study tested the feasibility of implementing two biomathematical models-the Phillips-Robinson Model and the Model for Arousal Dynamics-in 28 shift-working nurses, 14 in each group. The study examined the overlap and adherence between model recommendations and sleep behaviours, and changes in sleep following the implementation of recommendations. For both groups combined, the mean (SD) percentage overlap between when a model recommended an individual to sleep and when sleep was obtained was 73.62% (10.24%). Adherence between model recommendations and sleep onset and offset times was significantly higher with the Model of Arousal Dynamics compared to the Phillips-Robinson Model. For the Phillips-Robinson model, 27% of sleep onset and 35% of sleep offset times were within ± 30 min of model recommendations. For the Model of Arousal Dynamics, 49% of sleep onset, and 35% of sleep offset times were within ± 30 min of model recommendations. Compared to pre-study, significant improvements were observed post-study for sleep disturbance (Phillips-Robinson Model), and insomnia severity and sleep-related impairments (Model of Arousal Dynamics). Participants reported that using a digital, automated format for the delivery of sleep recommendations would enable greater uptake. These findings provide a positive proof-of-concept for using biomathematical models to recommend sleep in operational contexts.

Measuring Daily Activity Rhythms in Young Adults at Risk of Affective Instability Using Passively Collected Smartphone Data: Observational Study

BACKGROUND

Irregularities in circadian rhythms have been associated with adverse health outcomes. The regularity of rhythms can be quantified using passively collected smartphone data to provide clinically relevant biomarkers of routine.

OBJECTIVE

This study aims to develop a metric to quantify the regularity of activity rhythms and explore the relationship between routine and mood, as well as demographic covariates, in an outpatient psychiatric cohort.

METHODS

Passively sensed smartphone data from a cohort of 38 young adults from the Penn or Children's Hospital of Philadelphia Lifespan Brain Institute and Outpatient Psychiatry Clinic at the University of Pennsylvania were fitted with 2-state continuous-time hidden Markov models representing active and resting states. The regularity of routine was modeled as the hour-of-the-day random effects on the probability of state transition (ie, the association between the hour-of-the-day and state membership). A regularity score, Activity Rhythm Metric, was calculated from the continuous-time hidden Markov models and regressed on clinical and demographic covariates.

RESULTS

Regular activity rhythms were associated with longer sleep durations (P=.009), older age (P=.001), and mood (P=.049).

CONCLUSIONS

Passively sensed Activity Rhythm Metrics are an alternative to existing metrics but do not require burdensome survey-based assessments. Low-burden, passively sensed metrics based on smartphone data are promising and scalable alternatives to traditional measurements.

Development of Digital Biomarkers of Mental Illness via Mobile Apps for Personalized Treatment and Diagnosis

The development of precision psychiatry is largely based on multi-module measurements from the molecular, cellular, and behavioral levels, which are integrated to assess neurocognitive performances and clinically observed psychopathology. Nevertheless, quantifying mental activities and functions accurately and continuously has been a major difficulty within this field. This article reviews the latest efforts that utilize mobile apps to collect human–smartphone interaction data and contribute towards digital biomarkers of mental illnesses. The fundamental principles underlying a behavioral analysis with mobile apps were introduced, such as ways to monitor smartphone use under different circumstances and construct long-term patterns and trend changes. Examples were also provided to illustrate the potential applications of mobile apps that gain further insights into traditional research topics in occupational health and sleep medicine. We suggest that, with an optimized study design and analytical approach that accounts for technical challenges and ethical considerations, mobile apps will enhance the systemic understanding of mental illnesses.

A systematic review and meta-analysis of discrepancies between logged and self-reported digital media use

There is widespread public and academic interest in understanding the uses and effects of digital media. Scholars primarily use self-report measures of the quantity or duration of media use as proxies for more objective measures, but the validity of these self-reports remains unclear. Advancements in data collection techniques have produced a collection of studies indexing both self-reported and log-based measures. To assess the alignment between these measures, we conducted a pre-registered meta-analysis of this research. Based on 106 effect sizes, we found that self-reported media use correlates only moderately with logged measurements, that self-reports were rarely an accurate reflection of logged media use and that measures of problematic media use show an even weaker association with usage logs. These findings raise concerns about the validity of findings relying solely on self-reported measures of media use.

Novel statistical approach for assessing the persistence of the circadian rhythms of social activity from telephone call detail records in older adults

How circadian rhythms of activity manifest themselves in social life of humans remains one of the most intriguing questions in chronobiology and a major issue for personalized medicine. Over the past years, substantial advances have been made in understanding the personal nature and the robustness—i.e. the persistence—of the circadian rhythms of social activity by the analysis of phone use. At this stage however, the consistency of such advances as their statistical validity remains unclear. The present paper has been specifically designed to address this issue. To this end, we propose a novel statistical procedure for the measurement of the circadian rhythms of social activity which is particularly well-suited for the existing framework of persistence analysis. Furthermore, we illustrate how this procedure works concretely by assessing the persistence of the circadian rhythms of telephone call activity from a 12-month call detail records (CDRs) dataset of adults over than 65 years. The results show the ability of our approach for assessing persistence with a statistical significance. In the field of CDRs analysis, this novel statistical approach can be used for completing the existing methods used to analyze the persistence of the circadian rhythms of a social nature. More importantly, it provides an opportunity to open up the analysis of CDRs for various domains of application in personalized medicine requiring access to statistical significance such as health care monitoring.

Assessing User Retention of a Mobile App: Survival Analysis

BACKGROUND

A mobile app generates passive data, such as GPS data traces, without any direct involvement from the user. These passive data have transformed the manner of traditional assessments that require active participation from the user. Passive data collection is one of the most important core techniques for mobile health development because it may promote user retention, which is a unique characteristic of a software medical device.

OBJECTIVE

The primary aim of this study was to quantify user retention for the "Staff Hours" app using survival analysis. The secondary aim was to compare user retention between passive data and active data, as well as factors associated with the survival rates of user retention.

METHODS

We developed an app called "Staff Hours" to automatically calculate users' work hours through GPS data (passive data). "Staff Hours" not only continuously collects these passive data but also sends an 11-item mental health survey to users monthly (active data). We applied survival analysis to compare user retention in the collection of passive and active data among 342 office workers from the "Staff Hours" database. We also compared user retention on Android and iOS platforms and examined the moderators of user retention.

RESULTS

A total of 342 volunteers (224 men; mean age 33.8 years, SD 7.0 years) were included in this study. Passive data had higher user retention than active data (P=.011). In addition, user retention for passive data collected via Android devices was higher than that for iOS devices (P=.015). Trainee physicians had higher user retention for the collection of active data than trainees from other occupations, whereas no significant differences between these two groups were observed for the collection of passive data (P=.700).

CONCLUSIONS

Our findings demonstrated that passive data collected via Android devices had the best user retention for this app that records GPS-based work hours.

Exploitation of Outgoing and Incoming Telephone Calls in the Context of Circadian Rhythms of Social Activity Among Elderly People: Observational Descriptive Study

Background

In the elderly population, analysis of the circadian rhythms of social activity may help in supervising homebound disabled and chronically ill populations. Circadian rhythms are monitored over time to determine, for example, the stability of the organization of daily social activity rhythms and the occurrence of particular desynchronizations in the way older adults act and react socially during the day. Recently, analysis of telephone call detail records has led to the possibility of determining circadian rhythms of social activity in an objective unobtrusive way for young patients from their outgoing telephone calls. At this stage, however, the analysis of incoming call rhythms and the comparison of their organization with respect to outgoing calls remains to be performed in underinvestigated populations (in particular, older populations).

Objective

This study investigated the persistence and synchronization of circadian rhythms in telephone communication by older adults.

Methods

The study used a longitudinal 12-month data set combining call detail records and questionnaire data from 26 volunteers aged 70 years or more to determine the existence of persistent and synchronized circadian rhythms in their telephone communications. The study worked with the following four specific telecommunication parameters: (1) recipient of the telephone call (alter), (2) time at which the call began, (3) duration of the call, and (4) direction of the call. We focused on the following two issues: (1) the existence of persistent circadian rhythms of outgoing and incoming telephone calls in the older population and (2) synchronization with circadian rhythms in the way the older population places and responds to telephone calls.

Results

The results showed that older adults have their own specific circadian rhythms for placing telephone calls and receiving telephone calls. These rhythms are partly structured by the way in which older adults allocate their communication time over the day. In addition, despite minor differences between circadian rhythms for outgoing and incoming calls, our analysis suggests the two rhythms could be synchronized.

Conclusions

These results suggest the existence of potential persistent and synchronized circadian rhythms in the outgoing and incoming telephone activities of older adults.