Automatic Work-Hours Recorder for Medical Staff (Staff Hours): Mobile App Development

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.

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.

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.

Assessing Physicians' Recall Bias of Work Hours With a Mobile App: Interview and App-Recorded Data Comparison

Background

Previous studies have shown inconsistencies in the accuracy of self-reported work hours. However, accurate documentation of work hours is fundamental for the formation of labor policies. Strict work-hour policies decrease medical errors, improve patient safety, and promote physicians’ well-being.

Objective

The aim of this study was to estimate physicians’ recall bias of work hours with a mobile app, and to examine the association between the recall bias and physicians’ work hours.

Methods

We quantified recall bias by calculating the differences between the app-recorded and self-reported work hours of the previous week and the penultimate week. We recruited 18 physicians to install the “Staff Hours” app, which automatically recorded GPS-defined work hours for 2 months, contributing 1068 person-days. We examined the association between work hours and two recall bias indicators: (1) the difference between self-reported and app-recorded work hours and (2) the percentage of days for which work hours were not precisely recalled during interviews.

Results

App-recorded work hours highly correlated with self-reported counterparts (r=0.86-0.88, P<.001). Self-reported work hours were consistently significantly lower than app-recorded hours by –8.97 (SD 8.60) hours and –6.48 (SD 8.29) hours for the previous week and the penultimate week, respectively (both P<.001). The difference for the previous week was significantly correlated with work hours in the previous week (r=–0.410, P=.01), whereas the correlation of the difference with the hours in the penultimate week was not significant (r=–0.119, P=.48). The percentage of hours not recalled (38.6%) was significantly higher for the penultimate week (38.6%) than for the first week (16.0%), and the former was significantly correlated with work hours of the penultimate week (r=0.489, P=.002)

Conclusions

Our study identified the existence of recall bias of work hours, the extent to which the recall was biased, and the influence of work hours on recall bias.