Incorporation of Mobile Application (App) Measures Into the Diagnosis of Smartphone Addiction

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.

The problematic use of smartphones in public: the development and validation of a measure of smartphone “zombie” behaviour

Purpose

We have witnessed an evolution in the use of smartphones in recent years. We have been aware for some time of the potentially deleterious impact of smartphones on users' lives and their propensity for user addiction, as reflected in the large and growing body of work on this topic. One modern phenomenon – the distracted mobile phone user in public, or “smartphone zombie” – has received limited research attention. The purpose of the present study is to develop a robust measure of smartphone zombie behaviour.

Design/methodology/approach

The research deign comprises three studies: A round of focus groups (n = 5) and two online surveys (survey one n = 373, survey two n = 386), in order to develop and validate a three-factor, 15-item measure named the Smartphone Zombie Scale (SZS).

Findings

Following the round of focus groups conducted, Exploratory Factor Analysis and a Confirmatory Factor Analysis, the SZS measure (Cronbach's α = .932) is demonstrated to be robust and comprises three factors: Attention Deficit (Cronbach's α = .922), Jeopardy (Cronbach's α = .817) and Preoccupation (Cronbach's α = .835), that is shown to be distinct to existing closely related measures (Smartphone Addiction scale and Obsessive Compulsive Use).

Originality/value

The present study represents the first extant attempt to produce a measure of smartphone zombie behaviour, and provides us with a reliable and valid measure with which we can study this growing phenomenon.

Prevalence of smartphone addiction among Asian medical students: A meta-analysis of multinational observational studies

BACKGROUND

High prevalence of smartphone addiction among medical students may contribute to adverse physical and mental health outcomes.

AIM

To estimate the prevalence of smartphone addiction, and explore the influencing factors and related mental health symptoms of smartphone addiction among Asian medical students.

DESIGN

Systematic review and meta-analysis.

METHODS

PubMed (MEDLINE), the Cochrane Central Register of Controlled Trials, and EMBASE were searched for relevant literature from the inception to September 10, 2021. Using Stata software 11.0, the meta-analysis of prevalence and the influencing factors of smartphone addiction were determined with 95% confidence intervals.

RESULTS

Nineteen articles, published between 2014 and 2019, were included, producing medical student studies from seven different Asian countries. The included studies were conducted in India (n = 11) and Malaysia (n = 3), with China, Saudi Arabia, Turkey, Nepal, and Iran each contributing one study. Among a total of 5,497 medical students, the participants included 3,214 females, of whom 2,181 were medical students with smartphone addiction. The prevalence of smartphone addiction among Asian medical students was 41.93% (95% CI [36.24%, 47.72%]). The influencing factors of smartphone addiction among medical students included gender, duration of smartphone use, smartphone function, and marital status. Ten studies (52.63%) explored related mental health symptoms of smartphone addiction among Asian medical students. Smartphone addiction was positively correlated with poor sleep quality (r = .17-.31), stress (r = .30-.40), anxiety, depression, neuroticism, and general health among Asian medical students.

CONCLUSION

Smartphone addiction is highly prevalent among Asian medical students. Smartphone addiction may adversely affect mental health, resulting in sleep disturbance, stress, anxiety, depression, and neuroticism. It is necessary to take appropriate precautionary actions and interventions to prevent smartphone overuse among medical students.

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.

Two-dimensional taxonomy of internet addiction and assessment of smartphone addiction with diagnostic criteria and mobile apps

A recent review by Montag et al. raised a taxonomical argument about internet addiction. We propose a two-dimensional taxonomy of internet addiction by both the device and the content as the solution. For the assessment of smartphone addiction, measurements should be based on functional impairment and validated by diagnostic criteria rather than solely on self-reported questionnaires. We detail the potential of mobile applications (apps) to improve the assessment of smartphone addiction. App-generated indicators could fulfill the unmet need of assessment of smartphone addiction and facilitate future assessment and treatment planning of smartphone addiction.

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.

Passive objective measures in the assessment of problematic smartphone use: A systematic review

Research focussing on problematic smartphone use has predominantly employed psychometric tests which cannot capture the automatic processes and behaviours associated with problematic use. The present review aimed to identify passive objective measures that have been used or developed to assess problematic smartphone use. A systematic search was conducted using Web of Science, Scopus, PsychInfo and PubMed databases to identify passive objective measures that have been employed to assess problematic smartphone use, resulting in 18 studies meeting the inclusion criteria. Objective data that were monitored predominantly focussed on general screen usage time and checking patterns. Findings demonstrate that passive monitoring can enable smartphone usage patterns to be inferred within a relatively short timeframe and provide ecologically valid data on smartphone behaviour. Challenges and recommendations of employing passive objective measures in smartphone-based research are discussed.

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

Background

Modern smartphone use is pervasive and could be an accessible method of evaluating the circadian rhythm and social jet lag via a mobile app.

Objective

This study aimed to validate the app-recorded sleep time with daily self-reports by examining the consistency of total sleep time (TST), as well as the timing of sleep onset and wake time, and to validate the app-recorded circadian rhythm with the corresponding 30-day self-reported midpoint of sleep and the consistency of social jetlag.

Methods

The mobile app, Rhythm, recorded parameters and these parameters were hypothesized to be used to infer a relative long-term pattern of the circadian rhythm. In total, 28 volunteers downloaded the app, and 30 days of automatically recorded data along with self-reported sleep measures were collected.

Results

No significant difference was noted between app-recorded and self-reported midpoint of sleep time and between app-recorded and self-reported social jetlag. The overall correlation coefficient of app-recorded and self-reported midpoint of sleep time was .87.

Conclusions

The circadian rhythm for 1 month, daily TST, and timing of sleep onset could be automatically calculated by the app and algorithm.

Development of a mobile application (App) to delineate "digital chronotype" and the effects of delayed chronotype by bedtime smartphone use

The widespread use and deep reach of smartphones motivate the use of mobile applications to continuously monitor the relationship between circadian system, individual sleep patterns, and environmental effects. We selected 61 adults with 14-day data from the "Know Addiction" database. We developed an algorithm to identify the "sleep time" based on the smartphone behaviors. The total daily smartphone use duration and smartphone use duration prior to sleep onset were identified respectively. We applied mediation analysis to investigate the effects of total daily smartphone use on sleep through pre-sleep use (PS). The results showed participants' averaged pre-sleep episodes within 1 h prior to sleep are 2.58. The duration of three pre-sleep uses (PS_1∼3) maybe a more representative index for smartphone use before sleep. Both total daily duration and the duration of the last three uses prior to sleep of smartphone use significantly delayed sleep onset, midpoint of sleep and reduced total sleep time. One hour of increased smartphone use daily, delays the circadian rhythm by 3.5 min, and reduced 5.5 min of total sleep time (TST). One hour of increased pre-sleep smartphone use delayed circadian rhythm by 1.7 min, and reduced 39 s of TST. The mediation effects of PS_1∼3 significantly impacted on these three sleep indicators. PS_1∼3 accounted for 14.3% of total daily duration, but the proportion mediated of delayed circadian rhythm was 44.0%. We presented "digital chronotype" with an automatic system that can collect high temporal resolution data from naturalistic settings with high ecological validity. Smartphone screen time, mainly mediated by pre-sleep use, delayed the circadian rhythm and reduced the total sleep time.

Smartphone Addiction in Japanese College Students: Usefulness of the Japanese Version of the Smartphone Addiction Scale as a Screening Tool for a New Form of Internet Addiction

OBJECTIVE

Smartphone use is pervasive among youth in Japan, as with many other countries, and is associated with spending time online and on social media anywhere at any time. This study aimed to test a Japanese version of the Smartphone Addiction Scale-Short Version (SAS-SV) among Japanese college students.

METHODS

The subjects of this study were 602 college students in Japan. The study questionnaire consisted of questions about demographics (age, gender etc.), possession of a smartphone, internet use [length of internet use on weekdays and weekend, favorite social networking service (SNS) etc.], Young's Internet Addiction Test (IAT), and the Smartphone Addiction Scale-Short Version (SAS-SV) translated into Japanese.

RESULTS

There was a total of 573 respondents (180 male, 393 female) who completed the questionnaire (mean 19.3±1.3 years). LINE was the most popular social media platform (52.0%) followed by Twitter (36.3%). The overall Internet Addiction Test (IAT) score was 45.3±13.2, with 4.5% classified as having severe addiction (IAT ≥70). The mean SAS-SV scores were 24.4±10.0 for males and 26.8±9.9 for females. Based on proposed cutoff scores, 22.8% of males and 28.0% of females screened positive for smartphone addiction. The total scores of the SAS-SV and the IAT was correlated significantly.

CONCLUSION

As the number of smartphone users becomes higher, problems related to smartphone use also become more serious. Our.

RESULTS

suggest that the Japanese version of SAS-SV may assist in early detection of problematic use of smartphones.

Factors Affecting User Acceptance in Overuse of Smartphones in Mobile Health Services: An Empirical Study Testing a Modified Integrated Model in South Korea

Smartphones have become crucial in people's everyday lives, including in the medical field. However, as people become close to their smartphones, this leads easily to overuse. Overuse leads to fatigue due to lack of sleep, depressive symptoms, and social relationship failure, and in the case of adolescents, it hinders academic achievement. Self-control solutions are needed, and effective tools can be developed through behavioral analysis. Therefore, the aim of this study was to investigate the determinants of users' intentions to use m-Health for smartphone overuse interventions. A research model was based on TAM and UTAUT, which were modified to be applied to the case of smartphone overuse. The studied population consisted of 400 randomly selected smartphone users aged from 19 to 60 years in South Korea. Structural equation modeling was conducted between variables to test the hypotheses using a 95% confidence interval. Perceived ease of use had a very strong direct positive association with perceived usefulness, and perceived usefulness had a very strong direct positive association with behavioral intention to use. Resistance to change had a direct positive association with behavioral intention to use and, lastly, social norm had a very strong direct positive association with behavioral intention to use. The findings that perceived ease of use influenced perceived usefulness, that perceived usefulness influenced behavioral intention to use, and social norm influenced behavioral intention to use were in accordance with prior related research. Other results that were not consistent with previous research imply that these are unique behavioral findings regarding smartphone overuse. This research identifies the critical factors that need to be considered when implementing systems or solutions in the future for tackling the issue of smartphone overuse.

Mobile Phone Use and Mental Health. A Review of the Research That Takes a Psychological Perspective on Exposure

The purpose of this study was to carry out a review of observational studies that consider links between mobile phone use and mental health from a psychological or behavioral perspective. Systematic literature searches in PubMed and PsycINFO for articles published until 2017 were done. Exclusion criteria included: papers that considered radiofrequency fields, attention, safety, relational consequences, sexual behavior, cyberbullying, and reviews, qualitative, and case or experimental studies. A total of 4738 papers were screened by title and abstract, 404 were retrieved in full text, and 290 were included. Only 5% had any longitudinal design. Self-reporting was the dominating method of measurement. One third of the studies included children or youth. A majority of adult populations consisted of university students and/or self-selected participants. The main research results included associations between frequent mobile phone use and mental health outcomes, such as depressive symptoms and sleep problems. Mobile phone use at bedtime was associated with, e.g., shorter sleep duration and lower sleep quality. "Problematic use" (dependency) was associated with several negative outcomes. In conclusion, associations between mobile phone use and adverse mental health outcomes are found in studies that take a psychological or behavioral perspective on the exposure. However, more studies of high quality are needed in order to draw valid conclusions about the mechanisms and causal directions of associations.

Problematic smartphone use: Digital approaches to an emerging public health problem

Problematic smartphone use is an emerging public health problem since the launch of the first smartphone 10 years ago. In this article, pathways to problematic use of smartphones, approaches to deal with this issue and their limitations are discussed. This includes problematic use of smartphones by people who self-identify that they or their family members use mobile devices in a problematic way. Extreme problematic use (e.g. relating to online gambling or heavy gaming) that severely disrupts people’s lives is a form of digital addiction is excluded from this discussion. Smartphone use can be problematic for some people due to the availability of constant connection, the addictiveness of applications (apps) combined with personal psychological factors. This is facilitated by characteristics of the technology, including easy access, the possibility of escaping daily life, being able to remain anonymous online, and the frequency of alerts and messages. While various non-technical interventions, such as digital detoxes, and digital interventions, including apps to limit use, have been developed to help people control their smartphone use, none of these has proven to work yet. An overview of currently available apps for problematic smartphone use is provided. Further work is needed on various aspects of problematic smartphone use, including the understanding of how smartphone use impacts on people’s lives, strengthening the definition of problematic smartphone use, and validation of its measurement, and more rigorous development and assessment of tools. We hope that these efforts will help people to use their smartphones in a healthy and effective way.

Development of short-form and screening cutoff point of the Smartphone Addiction Inventory (SPAI-SF)

Smartphone addiction is considered a form of technological addiction that has attracted increasing attention. The present study developed and validated the short-form Smartphone Addiction Inventory (SPAI-SF) and established cutoff point for screening smartphone addiction based on diagnostic criteria established by psychiatric interview. A total of 268 participants completed an online survey that collected demographic data, smartphone use behaviours, and responses to the 26-item SPAI. Each participant also completed a psychiatric interview. Confirmatory factor analysis (CFA) revealed that the 10-item SPAI-SF replicated the structure of original 26-item SPAI accurately, yielding a four-factor model consisting of compulsive behaviour, functional impairment, withdrawal, and tolerance. For maximal diagnostic accuracy, a cutoff point of 24/25 best discriminated cases of smartphone addiction from diagnostic negatives. The present findings suggest that both the 26-item SPAI and SPAI-SF manifest the four constructs of behavioural addiction and the characteristics of smartphone addiction. The cutoff point determined by psychiatrists' diagnostic interview will be useful for clinical screening and epidemiologic research.

To use or not to use? Compulsive behavior and its role in smartphone addiction

Global smartphone penetration has led to unprecedented addictive behaviors. To develop a smartphone use/non-use pattern by mobile application (App) in order to identify problematic smartphone use, a total of 79 college students were monitored by the App for 1 month. The App-generated parameters included the daily use/non-use frequency, the total duration and the daily median of the duration per epoch. We introduced two other parameters, the root mean square of the successive differences (RMSSD) and the Similarity Index, in order to explore the similarity in use and non-use between participants. The non-use frequency, non-use duration and non-use-median parameters were able to significantly predict problematic smartphone use. A lower value for the RMSSD and Similarity Index, which represent a higher use/non-use similarity, were also associated with the problematic smartphone use. The use/non-use similarity is able to predict problematic smartphone use and reach beyond just determining whether a person shows excessive use.

Proposed Diagnostic Criteria for Smartphone Addiction

Background

Global smartphone penetration has led to unprecedented addictive behaviors. The aims of this study are to develop diagnostic criteria of smartphone addiction and to examine the discriminative ability and the validity of the diagnostic criteria.

Methods

We developed twelve candidate criteria for characteristic symptoms of smartphone addiction and four criteria for functional impairment caused by excessive smartphone use. The participants consisted of 281 college students. Each participant was systematically assessed for smartphone-using behaviors by psychiatrist’s structured diagnostic interview. The sensitivity, specificity, and diagnostic accuracy of the candidate symptom criteria were analyzed with reference to the psychiatrists’ clinical global impression. The optimal model selection with its cutoff point of the diagnostic criteria differentiating the smartphone addicted subjects from non-addicted subjects was then determined by the best diagnostic accuracy.

Results

Six symptom criteria model with optimal cutoff point were determined based on the maximal diagnostic accuracy. The proposed smartphone addiction diagnostic criteria consisted of (1) six symptom criteria, (2) four functional impairment criteria and (3) exclusion criteria. Setting three symptom criteria as the cutoff point resulted in the highest diagnostic accuracy (84.3%), while the sensitivity and specificity were 79.4% and 87.5%, respectively. We suggested determining the functional impairment by two or more of the four domains considering the high accessibility and penetration of smartphone use.

Conclusion

The diagnostic criteria of smartphone addiction demonstrated the core symptoms “impaired control” paralleled with substance related and addictive disorders. The functional impairment involved multiple domains provide a strict standard for clinical assessment.