JMIR Publications

JMIR mHealth and uHealth

Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.

JMIR's Thomson Reuter Impact Factor of 4.636 for 2016

Journal Description

JMIR mHealth and uHealth (JMU, ISSN 2291-5222) is a spin-off journal of JMIR, the leading eHealth journal (Impact Factor 2016: 5.175). JMIR mHealth and uHealth is indexed in PubMed, PubMed Central, and Science Citation Index Expanded (SCIE), and in June 2017 received a stunning inaugural Impact Factor of 4.636

The journal focusses on health and biomedical applications in mobile and tablet computing, pervasive and ubiquitous computing, wearable computing and domotics.

JMIR mHealth and uHealth publishes since 2013 and was the first mhealth journal in Pubmed. It publishes even faster and has a broader scope with including papers which are more technical or more formative/developmental than what would be published in the Journal of Medical Internet Research

JMIR mHealth and uHealth features a rapid and thorough peer-review process, professional copyediting, professional production of PDF, XHTML, and XML proofs.

JMIR mHealth and uHealth adheres to the same quality standards as JMIR and all articles published here are also cross-listed in the Table of Contents of JMIR, the worlds' leading medical journal in health sciences / health services research and health informatics.


Recent Articles:

  • Smarter Pregnancy, an mHealth platform to improve nutrition and lifestyle during the periconception period. Source: Peercode /; Copyright: JMIR Publications; URL:; License: Creative Commons Attribution (CC-BY).

    Opportunities of mHealth in Preconception Care: Preferences and Experiences of Patients and Health Care Providers and Other Involved Professionals


    Background: The importance of the preconception period and preconception care (PCC) are broadly acknowledged and the potential benefits regarding health promotion have been studied extensively. PCC provides the opportunity to identify, prevent, and treat modifiable and nonmodifiable risk factors to optimize the health of couples trying to become pregnant. The prevalence of modifiable and nonmodifiable risk factors in these couples is high, but the uptake of PCC remains low. Objective: The aim of this study is to identify the preferences and experiences of women and men (patients) trying to become pregnant and of health care providers and other involved professionals regarding mobile health (mHealth), in particular the coaching platform Smarter Pregnancy, and its potential role in PCC. Methods: Patients who participated in the Smarter Pregnancy randomized controlled trial (RCT) and health care providers and professionals also involved in PCC were invited to participate in a qualitative study. The barriers, benefits, and opportunities of big data collection by mHealth were discussed in focus group sessions, prompted with statements regarding PCC. Results: We composed five focus groups, consisting of 27 patients in total (23 women and 4 men), who participated in the RCT, and nine health care providers and other professionals. Of the patients, 67% (18/27) were familiar with the concept of PCC, but only 15% (4/27) received any form of PCC. A majority of 56% (combined percentages of statements 1 [n=18], 2 [n=11], and 3 [n=16]) of the patients believed in the benefit of receiving PCC, and all agreed that men should be involved in PCC as well. Patients did not have a problem using anonymized data obtained from mHealth tools for scientific purposes. Patients and health care providers and other professionals both acknowledged the lack of awareness regarding the importance of PCC and stated that mHealth provides several opportunities to support clinical PCC. Conclusions: Our findings substantiate previous studies addressing the low uptake of PCC due to unawareness or lack of perception of its relevance by couples who are trying to become pregnant. The positive judgment and experiences with mHealth, in particular Smarter Pregnancy, will stimulate future research and further development of effective and cost-effective personalized mHealth apps for patients, health care providers, and other professionals as an add-on to clinical PCC.

  • Movn smartphone app (montage). Source: The Authors /; Copyright: JMIR Publications; URL:; License: Creative Commons Attribution (CC-BY).

    Quantifying Human Movement Using the Movn Smartphone App: Validation and Field Study


    Background: The use of embedded smartphone sensors offers opportunities to measure physical activity (PA) and human movement. Big data—which includes billions of digital traces—offers scientists a new lens to examine PA in fine-grained detail and allows us to track people’s geocoded movement patterns to determine their interaction with the environment. Objective: The objective of this study was to examine the validity of the Movn smartphone app (Moving Analytics) for collecting PA and human movement data. Methods: The criterion and convergent validity of the Movn smartphone app for estimating energy expenditure (EE) were assessed in both laboratory and free-living settings, compared with indirect calorimetry (criterion reference) and a stand-alone accelerometer that is commonly used in PA research (GT1m, ActiGraph Corp, convergent reference). A supporting cross-validation study assessed the consistency of activity data when collected across different smartphone devices. Global positioning system (GPS) and accelerometer data were integrated with geographical information software to demonstrate the feasibility of geospatial analysis of human movement. Results: A total of 21 participants contributed to linear regression analysis to estimate EE from Movn activity counts (standard error of estimation [SEE]=1.94 kcal/min). The equation was cross-validated in an independent sample (N=42, SEE=1.10 kcal/min). During laboratory-based treadmill exercise, EE from Movn was comparable to calorimetry (bias=0.36 [−0.07 to 0.78] kcal/min, t82=1.66, P=.10) but overestimated as compared with the ActiGraph accelerometer (bias=0.93 [0.58-1.29] kcal/min, t89=5.27, P<.001). The absolute magnitude of criterion biases increased as a function of locomotive speed (F1,4=7.54, P<.001) but was relatively consistent for the convergent comparison (F1,4=1.26, P<.29). Furthermore, 95% limits of agreement were consistent for criterion and convergent biases, and EE from Movn was strongly correlated with both reference measures (criterion r=.91, convergent r=.92, both P<.001). Movn overestimated EE during free-living activities (bias=1.00 [0.98-1.02] kcal/min, t6123=101.49, P<.001), and biases were larger during high-intensity activities (F3,6120=1550.51, P<.001). In addition, 95% limits of agreement for convergent biases were heterogeneous across free-living activity intensity levels, but Movn and ActiGraph measures were strongly correlated (r=.87, P<.001). Integration of GPS and accelerometer data within a geographic information system (GIS) enabled creation of individual temporospatial maps. Conclusions: The Movn smartphone app can provide valid passive measurement of EE and can enrich these data with contextualizing temporospatial information. Although enhanced understanding of geographic and temporal variation in human movement patterns could inform intervention development, it also presents challenges for data processing and analytics.

  • Spatial span test (montage). Source: The Authors / Dribbble; Copyright: Amir Hamdi; URL:; License: Creative Commons Attribution (CC-BY).

    Validation of a Smartphone-Based Approach to In Situ Cognitive Fatigue Assessment


    Background: Acquired Brain Injuries (ABIs) can result in multiple detrimental cognitive effects, such as reduced memory capability, concentration, and planning. These effects can lead to cognitive fatigue, which can exacerbate the symptoms of ABIs and hinder management and recovery. Assessing cognitive fatigue is difficult due to the largely subjective nature of the condition and existing assessment approaches. Traditional methods of assessment use self-assessment questionnaires delivered in a medical setting, but recent work has attempted to employ more objective cognitive tests as a way of evaluating cognitive fatigue. However, these tests are still predominantly delivered within a medical environment, limiting their utility and efficacy. Objective: The aim of this research was to investigate how cognitive fatigue can be accurately assessed in situ, during the quotidian activities of life. It was hypothesized that this assessment could be achieved through the use of mobile assistive technology to assess working memory, sustained attention, information processing speed, reaction time, and cognitive throughput. Methods: The study used a bespoke smartphone app to track daily cognitive performance, in order to assess potential levels of cognitive fatigue. Twenty-one participants with no prior reported brain injuries took place in a two-week study, resulting in 81 individual testing instances being collected. The smartphone app delivered three cognitive tests on a daily basis: (1) Spatial Span to measure visuospatial working memory; (2) Psychomotor Vigilance Task (PVT) to measure sustained attention, information processing speed, and reaction time; and (3) a Mental Arithmetic Test to measure cognitive throughput. A smartphone-optimized version of the Mental Fatigue Scale (MFS) self-assessment questionnaire was used as a baseline to assess the validity of the three cognitive tests, as the questionnaire has already been validated in multiple peer-reviewed studies. Results: The most highly correlated results were from the PVT, which showed a positive correlation with those from the prevalidated MFS, measuring 0.342 (P<.008). Scores from the cognitive tests were entered into a regression model and showed that only reaction time in the PVT was a significant predictor of fatigue (P=.016, F=2.682, 95% CI 9.0-84.2). Higher scores on the MFS were related to increases in reaction time during our mobile variant of the PVT. Conclusions: The results show that the PVT mobile cognitive test developed for this study could be used as a valid and reliable method for measuring cognitive fatigue in situ. This test would remove the subjectivity associated with established self-assessment approaches and the need for assessments to be performed in a medical setting. Based on our findings, future work could explore delivering a small set of tests with increased duration to further improve measurement reliability. Moreover, as the smartphone assessment tool can be used as part of everyday life, additional sources of data relating to physiological, psychological, and environmental context could be included within the analysis to improve the nature and precision of the assessment process.

  • Source: The Authors /; Copyright: JMIR Publications; URL:; License: Creative Commons Attribution (CC-BY).

    Developing and Evaluating JIApp: Acceptability and Usability of a Smartphone App System to Improve Self-Management in Young People With Juvenile Idiopathic...


    Background: Flare-ups in juvenile idiopathic arthritis (JIA) are characterized by joint pain and swelling and often accompanied with fatigue, negative emotions, and reduced participation in activities. To minimize the impact of JIA on the physical and psychosocial development and well-being of young people (YP), it is essential to regularly monitor disease activity and side effects, as well as to support self-management such as adherence to treatment plans and engagement in general health-promoting behaviors. Smartphone technology has the potential to engage YP with their health care through convenient self-monitoring and easy access to information. In addition, having a more accurate summary of self-reported fluctuations in symptoms, behaviors, and psychosocial problems can help both YP and health care professionals (HCPs) better understand the patient’s condition, identify barriers to self-management, and assess treatment effectiveness and additional health care needs. No comprehensive smartphone app has yet been developed in collaboration with YP with JIA, their parents, and HCPs involved in their care. Objectives: The objective of this study was to design, develop, and evaluate the acceptability and usability of JIApp, a self-management smartphone app system for YP with JIA and HCPs. Methods: We used a qualitative, user-centered design approach involving YP, parents, and HCPs from the rheumatology team. The study was conducted in three phases: (1) phase I focused on developing consensus on the features, content, and design of the app; (2) phase II was used for further refining and evaluating the app prototype; and (3) phase III focused on usability testing of the app. The interview transcripts were analyzed using qualitative content analysis. Results: A total of 29 YP (aged 10-23, median age 17) with JIA, 7 parents, and 21 HCPs were interviewed. Major themes identified as the ones that helped inform app development in phase I were: (1) remote monitoring of symptoms, well-being, and activities; (2) treatment adherence; and (3) education and support. During phase II, three more themes emerged that informed further refinement of the app prototype. These included (4) adapting a reward system to motivate end users for using the app; (5) design of the app interface; and (6) clinical practice integration. The usability testing during phase III demonstrated high rates of overall satisfaction and further affirmed the content validity of the app. Conclusions: We present the development and evaluation of a smartphone app to encourage self-management and engagement with health care for YP with JIA. The app was found to have high levels of acceptability and usability among YP and HCPs and has the potential to improve health care and outcomes for this age group. Future feasibility testing in a prospective study will firmly establish the reliability, efficacy, and cost-effectiveness of such an app intervention for patients with arthritis.

  • Check Up GP menu (montage). Source: The Authors /; Copyright: JMIR Publications; URL:; License: Creative Commons Attribution (CC-BY).

    Improving Patient-Centered Care for Young People in General Practice With a Codesigned Screening App: Mixed Methods Study


    Background: Despite experiencing a high prevalence and co-occurrence of mental health disorders and health-compromising behaviors, young people tend not to seek professional help for these concerns. However, they do regularly attend primary care, making primary care providers ideally situated to identify and discuss mental health and lifestyle issues as part of young people’s routine health care. Objective: The aim was to investigate whether using a codesigned health and lifestyle-screening app, Check Up GP, in general practice influenced young people’s assessment of the quality of their care (measures of patient-centered care and youth friendliness), and their disclosure of sensitive issues. In addition, this study aimed to explore young people’s acceptance and experience of using a screening app during regular health care. Methods: This was a mixed methods implementation study of Check Up GP with young people aged 14 to 25 years attending a general practice clinic in urban Melbourne, Australia. A 1-month treatment-as-usual group was compared to a 2-month intervention group in which young people and their general practitioners (GPs) used Check Up GP. Young people in both groups completed an exit survey immediately after their consultation about disclosure, patient-centered and youth-friendly care, and judgment. In addition, participants in the intervention group were surveyed about app acceptability and usability and their willingness to use it again. Semistructured interviews with participants in the intervention group expanded on themes covered in the survey. Results: The exit survey was completed by 30 young people in the treatment-as-usual group and 85 young people in the intervention group. Young people using Check Up GP reported greater disclosure of health issues (P<.001), and rated their GP higher in patient-centered care: communication and partnership (P=.01), personal relationship (P=.01), health promotion (P=.03), and interest in effect on life (P<.001). No differences were found on core indicators of youth-friendly care: trust, level of comfort, expectations met, and time to ask questions. In all, 86% (73/85) of young people felt the app was a “good idea” and only 1% (1/85) thought it a “bad idea.” Thematic analysis of qualitative interviews with 14 participants found that Check Up GP created scope to address unmet health needs and increased sense of preparedness, with use moderated by honesty, motivation, app content and functionality, and app administration. Conclusions: Integrating a health and lifestyle-screening app into face-to-face care can enrich young people’s experience of seeing their GP, create scope to identify and address unmet health needs, and increase patient-centered care. Further research is needed to investigate the effect of using a health and lifestyle-screening app in a diverse range of clinic types and settings, and with a diverse range of GPs and youth.

  • Source: The Authors /; Copyright: The Authors; URL:; License: Creative Commons Attribution (CC-BY).

    How Accurate Is Your Activity Tracker? A Comparative Study of Step Counts in Low-Intensity Physical Activities


    Background: As commercially available activity trackers are being utilized in clinical trials, the research community remains uncertain about reliability of the trackers, particularly in studies that involve walking aids and low-intensity activities. While these trackers have been tested for reliability during walking and running activities, there has been limited research on validating them during low-intensity activities and walking with assistive tools. Objective: The aim of this study was to (1) determine the accuracy of 3 Fitbit devices (ie, Zip, One, and Flex) at different wearing positions (ie, pants pocket, chest, and wrist) during walking at 3 different speeds, 2.5, 5, and 8 km/h, performed by healthy adults on a treadmill; (2) determine the accuracy of the mentioned trackers worn at different sites during activities of daily living; and (3) examine whether intensity of physical activity (PA) impacts the choice of optimal wearing site of the tracker. Methods: We recruited 15 healthy young adults to perform 6 PAs while wearing 3 Fitbit devices (ie, Zip, One, and Flex) on their chest, pants pocket, and wrist. The activities include walking at 2.5, 5, and 8 km/h, pushing a shopping cart, walking with aid of a walker, and eating while sitting. We compared the number of steps counted by each tracker with gold standard numbers. We performed multiple statistical analyses to compute descriptive statistics (ie, ANOVA test), intraclass correlation coefficient (ICC), mean absolute error rate, and correlation by comparing the tracker-recorded data with that of the gold standard. Results: All the 3 trackers demonstrated good-to-excellent (ICC>0.75) correlation with the gold standard step counts during treadmill experiments. The correlation was poor (ICC<0.60), and the error rate was significantly higher in walker experiment compared to other activities. There was no significant difference between the trackers and the gold standard in the shopping cart experiment. The wrist worn tracker, Flex, counted several steps when eating (P<.01). The chest tracker was identified as the most promising site to capture steps in more intense activities, while the wrist was the optimal wearing site in less intense activities. Conclusions: This feasibility study focused on 6 PAs and demonstrated that Fitbit trackers were most accurate when walking on a treadmill and least accurate during walking with a walking aid and for low-intensity activities. This may suggest excluding participants with assistive devices from studies that focus on PA interventions using commercially available trackers. This study also indicates that the wearing site of the tracker is an important factor impacting the accuracy performance. A larger scale study with a more diverse population, various activity tracker vendors, and a larger activity set are warranted to generalize our results.

  • Source: Flickr; Copyright: Vin on the move; URL:; License: Creative Commons Attribution + Noncommercial + NoDerivatives (CC-BY-NC-ND).

    Mobile Phone Detection of Semantic Location and Its Relationship to Depression and Anxiety


    Background: Is someone at home, at their friend’s place, at a restaurant, or enjoying the outdoors? Knowing the semantic location of an individual matters for delivering medical interventions, recommendations, and other context-aware services. This knowledge is particularly useful in mental health care for monitoring relevant behavioral indicators to improve treatment delivery. Local search-and-discovery services such as Foursquare can be used to detect semantic locations based on the global positioning system (GPS) coordinates, but GPS alone is often inaccurate. Mobile phones can also sense other signals (such as movement, light, and sound), and the use of these signals promises to lead to a better estimation of an individual’s semantic location. Objective: We aimed to examine the ability of mobile phone sensors to estimate semantic locations, and to evaluate the relationship between semantic location visit patterns and depression and anxiety. Methods: A total of 208 participants across the United States were asked to log the type of locations they visited daily, using their mobile phones for a period of 6 weeks, while their phone sensor data was recorded. Using the sensor data and Foursquare queries based on GPS coordinates, we trained models to predict these logged locations, and evaluated their prediction accuracy on participants that models had not seen during training. We also evaluated the relationship between the amount of time spent in each semantic location and depression and anxiety assessed at baseline, in the middle, and at the end of the study. Results: While Foursquare queries detected true semantic locations with an average area under the curve (AUC) of 0.62, using phone sensor data alone increased the AUC to 0.84. When we used Foursquare and sensor data together, the AUC further increased to 0.88. We found some significant relationships between the time spent in certain locations and depression and anxiety, although these relationships were not consistent. Conclusions: The accuracy of location services such as Foursquare can significantly benefit from using phone sensor data. However, our results suggest that the nature of the places people visit explains only a small part of the variation in their anxiety and depression symptoms.

  • BeWell24 app. Source: Arizona State University; Copyright: Arizona Board of Regents; URL:; License: Licensed by the authors.

    Validation of a Smartphone App for the Assessment of Sedentary and Active Behaviors


    Background: Although current technological advancements have allowed for objective measurements of sedentary behavior via accelerometers, these devices do not provide the contextual information needed to identify targets for behavioral interventions and generate public health guidelines to reduce sedentary behavior. Thus, self-reports still remain an important method of measurement for physical activity and sedentary behaviors. Objective: This study evaluated the reliability, validity, and sensitivity to change of a smartphone app in assessing sitting, light-intensity physical activity (LPA), and moderate-vigorous physical activity (MVPA). Methods: Adults (N=28; 49.0 years old, standard deviation [SD] 8.9; 85% men; 73% Caucasian; body mass index=35.0, SD 8.3 kg/m2) reported their sitting, LPA, and MVPA over an 11-week behavioral intervention. During three separate 7-day periods, participants wore the activPAL3c accelerometer/inclinometer as a criterion measure. Intraclass correlation (ICC; 95% CI) and bias estimates (mean difference [δ] and root of mean square error [RMSE]) were used to compare app-based reported behaviors to measured sitting time (lying/seated position), LPA (standing or stepping at <100 steps/minute), and MVPA (stepping at >100 steps/minute). Results: Test-retest results suggested moderate agreement with the criterion for sedentary time, LPA, and MVPA (ICC=0.65 [0.43-0.82], 0.67 [0.44-0.83] and 0.69 [0.48-0.84], respectively). The agreement between the two measures was poor (ICC=0.05-0.40). The app underestimated sedentary time (δ=-45.9 [-67.6, -24.2] minutes/day, RMSE=201.6) and overestimated LPA and MVPA (δ=18.8 [-1.30 to 38.9] minutes/day, RMSE=183; and δ=29.3 [25.3 to 33.2] minutes/day, RMSE=71.6, respectively). The app underestimated change in time spent during LPA and MVPA but overestimated change in sedentary time. Both measures showed similar directions in changed scores on sedentary time and LPA. Conclusions: Despite its inaccuracy, the app may be useful as a self-monitoring tool in the context of a behavioral intervention. Future research may help to clarify reasons for under- or over-reporting of behaviors.

  • BRANCH App Drinking Diary. Source: Joanna Milward /; Copyright: The Authors; URL:; License: Creative Commons Attribution (CC-BY).

    Usability Testing of the BRANCH Smartphone App Designed to Reduce Harmful Drinking in Young Adults


    Background: Electronic screening and brief intervention (eSBI) apps demonstrate potential to reduce harmful drinking. However, low user engagement rates with eSBI reduce overall effectiveness of interventions. As “Digital Natives,” young adults have high expectations of app quality. Ensuring that the design, content, and functionality of an eSBI app are acceptable to young adults is an integral stage to the development process. Objective: The objective of this study was to identify usability barriers and enablers for an app, BRANCH, targeting harmful drinking in young adults. Methods: The BRANCH app contains a drinking diary, alcohol reduction goal setting functions, normative drinking feedback, and information on risks and advice for cutting down. The app includes a social feature personalized to motivate cutting down and to promote engagement with a point-based system for usage. Three focus groups were conducted with 20 users who had tested the app for 1 week. A detailed thematic analysis was undertaken. Results: The first theme, “Functionality” referred to how users wanted an easy-to-use interface, with minimum required user-input. Poor functionality was considered a major usability barrier. The second theme, “Design” described how an aesthetic with minimum text, clearly distinguishable tabs and buttons and appealing infographics was integral to the level of usability. The final theme, “Content” described how participants wanted all aspects of the app to be automatically personalized to them, as well as providing them with opportunities to personalize the app themselves, with increased options for social connectivity. Conclusions: There are high demands for apps such as BRANCH that target skilled technology users including young adults. Key areas to optimize eSBI app development that emerged from testing BRANCH with representative users include high-quality functionality, appealing aesthetics, and improved personalization.

  • Smoking Cessation webpage. Source: The Authors; Copyright:; URL:; License: Fair use/fair dealings.

    Feasibility and Acceptability of a Text Message-Based Smoking Cessation Program for Young Adults in Lima, Peru: Pilot Study


    Background: In Peru’s urban communities, tobacco smoking generally starts during adolescence and smoking prevalence is highest among young adults. Each year, many attempt to quit, but access to smoking cessation programs is limited. Evidence-based text messaging smoking cessation programs are an alternative that has been successfully implemented in high-income countries, but not yet in middle- and low-income countries with limited tobacco control policies. Objective: The objective was to assess the feasibility and acceptability of an short message service (SMS) text message-based cognitive behavioral smoking cessation program for young adults in Lima, Peru. Methods: Recruitment included using flyers and social media ads to direct young adults interested in quitting smoking to a website where interested participants completed a Google Drive survey. Inclusion criteria were being between ages 18 and 25 years, smoking at least four cigarettes per day at least 6 days per week, willing to quit in the next 30 days, owning a mobile phone, using SMS text messaging at least once in past year, and residing in Lima. Participants joined one of three phases: (1) focus groups and in-depth interviews whose feedback was used to develop the SMS text messages, (2) validating the SMS text messages, and (3) a pilot of the SMS text message-based smoking cessation program to test its feasibility and acceptability among young adults in Lima. The outcome measures included adherence to the SMS text message-based program, acceptability of content, and smoking abstinence self-report on days 2, 7, and 30 after quitting. Results: Of 639 participants who completed initial online surveys, 42 met the inclusion criteria and 35 agreed to participate (focus groups and interviews: n=12; validate SMS text messages: n=8; program pilot: n=15). Common quit practices and beliefs emerged from participants in the focus groups and interviews informed the content, tone, and delivery schedule of the messages used in the SMS text message smoking cessation program. A small randomized controlled pilot trial was performed to test the program’s feasibility and acceptability; nine smokers were assigned to the SMS text message smoking cessation program and six to a SMS text message nutrition program. Participant retention was high: 93% (14/15) remained until day 30 after quit day. In all, 56% of participants (5/9) in the SMS text message smoking cessation program reported remaining smoke-free until day 30 after quit day and 17% of participants (1/6) in the SMS text message nutrition program reported remaining smoke-free during the entire program. The 14 participants who completed the pilot reported that they received valuable health information and approved the delivery schedule of the SMS text messages. Conclusions: This study provides initial evidence that a SMS text message smoking cessation program is feasible and acceptable for young adults residing in Lima.

  • Inertial measurement unit (IMU) position: the spinous process of the 5th lumbar vertebra. Source: Figure 3 from; Copyright: the authors; License: Creative Commons Attribution (CC-BY).

    Feature-Free Activity Classification of Inertial Sensor Data With Machine Vision Techniques: Method, Development, and Evaluation


    Background: Inertial sensors are one of the most commonly used sources of data for human activity recognition (HAR) and exercise detection (ED) tasks. The time series produced by these sensors are generally analyzed through numerical methods. Machine learning techniques such as random forests or support vector machines are popular in this field for classification efforts, but they need to be supported through the isolation of a potentially large number of additionally crafted features derived from the raw data. This feature preprocessing step can involve nontrivial digital signal processing (DSP) techniques. However, in many cases, the researchers interested in this type of activity recognition problems do not possess the necessary technical background for this feature-set development. Objective: The study aimed to present a novel application of established machine vision methods to provide interested researchers with an easier entry path into the HAR and ED fields. This can be achieved by removing the need for deep DSP skills through the use of transfer learning. This can be done by using a pretrained convolutional neural network (CNN) developed for machine vision purposes for exercise classification effort. The new method should simply require researchers to generate plots of the signals that they would like to build classifiers with, store them as images, and then place them in folders according to their training label before retraining the network. Methods: We applied a CNN, an established machine vision technique, to the task of ED. Tensorflow, a high-level framework for machine learning, was used to facilitate infrastructure needs. Simple time series plots generated directly from accelerometer and gyroscope signals are used to retrain an openly available neural network (Inception), originally developed for machine vision tasks. Data from 82 healthy volunteers, performing 5 different exercises while wearing a lumbar-worn inertial measurement unit (IMU), was collected. The ability of the proposed method to automatically classify the exercise being completed was assessed using this dataset. For comparative purposes, classification using the same dataset was also performed using the more conventional approach of feature-extraction and classification using random forest classifiers. Results: With the collected dataset and the proposed method, the different exercises could be recognized with a 95.89% (3827/3991) accuracy, which is competitive with current state-of-the-art techniques in ED. Conclusions: The high level of accuracy attained with the proposed approach indicates that the waveform morphologies in the time-series plots for each of the exercises is sufficiently distinct among the participants to allow the use of machine vision approaches. The use of high-level machine learning frameworks, coupled with the novel use of machine vision techniques instead of complex manually crafted features, may facilitate access to research in the HAR field for individuals without extensive digital signal processing or machine learning backgrounds.

  • Source: Stocksnap; Copyright: Alexander Mils; URL:; License: Public Domain (CC0).

    How Do Apps Work? An Analysis of Physical Activity App Users’ Perceptions of Behavior Change Mechanisms


    Background: Physical activity apps are commonly used to increase levels of activity and health status. To date, the focus of research has been to determine the potential of apps to influence behavior, to ascertain the efficacy of a limited number of apps to change behavior, and to identify the characteristics of apps that users prefer. Objective: The purpose of this study was to identify the mechanisms by which the use of physical activity apps may influence the users’ physical activity behavior. Methods: This study used a cross-sectional survey of users of health-related physical activity apps during the past 6 months. An electronic survey was created in Qualtrics’ Web-based survey software and deployed on Amazon Mechanical Turk. Individuals who had used at least one physical activity app in the past 6 months were eligible to respond. The final sample comprised 207 adults living in the United States. 86.0% (178/207) of respondents were between the ages of 26 and 54 years, with 51.2% (106/207) of respondents being female. Behavior change theory informed the creation of 20 survey items relating to the mechanisms of behavior change. Respondents also reported about engagement with the apps, app likeability, and physical activity behavior. Results: Respondents reported that using a physical activity app in the past 6 months resulted in a change in their attitudes, beliefs, perceptions, and motivation. Engagement with the app (P<.001), frequency of app use (P=.03), and app price (P=.01) were related to the reported impact of the behavior change theory or mechanisms of change. The mechanisms of change were associated with self-reported physical activity behaviors (P<.001). Conclusions: The findings from this study provide an overview of the mechanisms by which apps may impact behavior. App developers may wish to incorporate these mechanisms in an effort to increase impact. Practitioners should consider the extent to which behavior change theory is integrated into a particular app when they consider making recommendations to others wishing to increase levels of physical activity.

Citing this Article

Right click to copy or hit: ctrl+c (cmd+c on mac)

Latest Submissions Open for Peer-Review:

View All Open Peer Review Articles
  • mHealth applications impact in improving immunization coverage and maternal-child health in Africa

    Date Submitted: Aug 17, 2017

    Open Peer Review Period: Aug 17, 2017 - Oct 12, 2017

    Background: Despite laudable efforts and achievement, maternal and child mortality remains high in Africa. The region accounts for 97% of maternal and 94% of children less than five mortality in 2015....

    Background: Despite laudable efforts and achievement, maternal and child mortality remains high in Africa. The region accounts for 97% of maternal and 94% of children less than five mortality in 2015. Limited resources, lack of infrastructures and shortage of healthcare workers have been identified as the main barriers towards healthcare outcomes improvement. Availability and use of mobile phones is increasing rapidly with 46% of African population having a mobile-cellular subscription in 2015. Mobile health (mHealth) interventions have proven to be beneficial in improving maternal and child health service delivery and outcomes in developed countries and elsewhere. In Africa, only few mhealth pilot research projects and small studies have been conducted, those limiting generalizability Objective: The objective of the project is to provide an overview about the current impact of mHealth applications and innovative strategies in improving large-scale (population-based) immunization coverage and maternal- child health service delivery in African countries Methods: Peer-reviewed papers were identified from Medline/PubMed, Google scholar and mHealthEvidence database via a combination of search terms Results: A total of 1217 articles were found of which only 17 met the inclusion criteria and were included in the project. Our findings indicates that there is some evidence on the potential of mHealth applications benefitsin increasing childhood immunization awareness, retention, coverage and effectiveness as well as maternal- child quality care delivery and outcomes Conclusions: Building robust and resilient government and stakeholders leadership, committed partnerships and platform is crucial in investing on large-scale and sustainable ownership of mhealth policies and programs, adequate infrastructure, building capacity and mHealth/eHealth management implementation in strengthening health systems. Moreover, addressing inherent issues of mhealth interoperatibility, patient data privacy. confidentiality and security is needed for socio-economic benefits, cost-effective digital landscape public health solutions and gains across African countries

  • M-health tools for self-management of complex patients in primary care settings: Understanding the patient and provider experience

    Date Submitted: Aug 3, 2017

    Open Peer Review Period: Aug 4, 2017 - Sep 29, 2017

    Background: Given the complex and evolving needs of individuals with multi-morbidity, the use of m-health tools to support self-management efforts is increasingly being explored, particularly in prima...

    Background: Given the complex and evolving needs of individuals with multi-morbidity, the use of m-health tools to support self-management efforts is increasingly being explored, particularly in primary care settings. The Electronic Patient Reported Outcomes (ePRO) tool was co-developed with patients and providers in an inter-disciplinary primary care team in Toronto, Canada to help facilitate self-management in community-dwelling adults diagnosed with multiple chronic conditions. Objective: Explore the experience and expectations of patients with multi-morbidity and their providers around the role of the ePRO tool in supporting self-management efforts to generate insights into how m-health applications targeted towards helping patients self-manage are perceived by patients and providers. Methods: A 4-week usability trial of the ePRO tool was conducted. Patient and provider experience and expectations were explored through focus groups that were conducted at the end of the usability trial. Thematic analyses were used to assess shared and contrasting perspectives of patients and providers on the role of the ePRO tool in facilitating self-management. Results: Eleven patients and six providers were involved in the usability trial. Findings revealed that both patients and providers emphasized the need for greater personalization and customizability of content to better adapt to the complexity and fluidity of self-management in this particular patient population. Providers recognized the ePRO tool’s value in providing insights into broader patient context and emphasized alignment with existing processes, i.e., goal setting techniques and linkage with electronic medical records. Conclusions: In developing the ePRO tool, a nuanced disconnect emerged between patient and provider expectations around the role of the ePRO tool in enabling self-management, specifically that patients indicated they see the tool ePRO as a supplement to existing interaction rather than a replacement of in-person consults with their providers. In contrast, provider expectations were centered on the ePRO tool’s potential to monitor patient progress remotely. More in-depth inquiry is needed to better understand whether m-health technologies can resolve this gap around expectations between user groups. The adoption of a more patient-centered lens in content and question design, and greater adaptability to accommodate patient complexity and provider workflow were identified as next steps in refining the ePRO tool ahead of full-scale application in a randomized pragmatic trial.

  • Web-based interventions supporting adolescents and young people with depressive symptoms: a systematic review and meta-analysis

    Date Submitted: Aug 2, 2017

    Open Peer Review Period: Aug 2, 2017 - Sep 27, 2017

    We conducted a systematic review and meta-analysis of trials to describe the effectiveness of web-based interventions to support adolescents with depression or depressive symptoms, anxiety and stress....

    We conducted a systematic review and meta-analysis of trials to describe the effectiveness of web-based interventions to support adolescents with depression or depressive symptoms, anxiety and stress. We also explored the content of the interventions, as there has previously been a lack of coherent understanding of the detailed content of the web-based interventions supporting adolescents’ mental wellbeing. We included parallel randomized control trials (RCT) targeted at adolescents, or young people between 10 and 24 years old, with symptoms or diagnoses of depression and/or anxi-ety. The interventions were from original studies aimed to support mental health among adolescents, and they were delivered by web-based information and communication technology (ICT). Out of 2,087 records identified, 27 articles (22 studies) met the inclusion criteria. Based on a narrative analysis of 22 studies, a variety of web-based interventions were found; the most commonly used intervention was based on cognitive behavioral therapy. Meta-analysis was further conducted with 15 studies (4,979 participants). At the end of the intervention, a statistically significant improvement was found in the intervention group (10 studies) regarding depressive symptoms (P<.02, median 1.68, 95% CI 3.11-0.25) and after 6 months (3 studies) (P<.01, median 1.78, 95% CI 3.20-0.37). Anxiety symptoms (8 studies) (P<.001, median 1.47, 95% CI 2.36-0.59) and moods and feelings (two studies) (P<.04, median 5.55, 95% CI 10.88-0.22) improved as well in the web-based in-tervention group. However, there was no difference in stress scores. On the other hand, adolescents in the intervention group left the study early more often, both in short-term (10 studies) (P<.01, median 1.33, 95% CI 1.06-1.66) and in mid-term (3 studies) (P<.02, median 1.65, 95% CI 1.09-2.49). We did not find any studies that had assessed the costs of the web-based interventions. Despite widely reported promises that information technology use is beneficial to adolescents with depression, the results of our review showed only short-term effects to adolescents’ mental wellbeing, while long-term effects can be questioned due to the limited number of studies reviewed. Information about the economic benefits of web-based interventions is still lacking. The quality of the studies, especially biases related to attrition rates and selective reporting, still needs serious attention.

  • Relationship between the medical environment of developing countries and dissemination of IT; Possibility of introducing telemedicine service in Asia and Africa countries

    Date Submitted: Jul 28, 2017

    Open Peer Review Period: Jul 28, 2017 - Sep 22, 2017

    Background: In some developing countries where medical resources are scarce despite the advancement of IT, there is a possibility that problems can be solved by introducing telemedicine services. In t...

    Background: In some developing countries where medical resources are scarce despite the advancement of IT, there is a possibility that problems can be solved by introducing telemedicine services. In this study, we examined the status of IT adoption, healthcare environment, as well as the economic situation, respectively, in developing countries; we attempted to visualize the data as basic material for examining the possibility of introducing telemedicine-based services in developing countries. Objective: In this study, we examined the status of IT adoption, healthcare environment, as well as the economic situation, respectively, in developing countries; we attempted to visualize the data as basic material for examining the possibility of introducing telemedicine-based services in developing countries. Methods: The surveyed countries consisted of developing countries in Asia and Africa. In Asia, the study was conducted in nine developing countries after exclusion of those whose data were unavailable; and in Africa, 13 countries were extracted after exclusion of those with a GDP per capita less than USD 1,000, as well as countries where data were unavailable. We set the number of doctors, the number of nurses and midwives as indicators of the medical environment. We used the number of Internet contracts and the number of mobile phone contracts as indicators of IT spreading situation, and set GDP per capita and GDP growth rate as economic indicators. Regarding the medical environment and the IT penetration situation, we conducted a survey separately for Asia and Africa. Furthermore, we integrated the data of Asia and Africa, we performed the principal component analysis and the cluster analysis. Results: The target countries were classified into 5 clusters by economic indicator, medical environment indicator, IT spread index (Cluster A: Algeria, Egypt, Morocco, Indonesia, Ghana, Tunisia, Madagascar, Nigeria, Thailand, Cluster B: Bangladesh, Ethiopia, Kenya, Uganda, India, Pakistan, Cluster C: Sudan, Malaysia, Viet Nam, Tanzania, Philippines, China, Cluster D: South Africa, Cluster E: Japan, Singapore).This study suggested that there is a high possibility of introducing the most telemedicine services in South Africa and that the possibility of introducing telemedicine services are high even in Thailand where the Internet is spreading widely. Conclusions: This study suggested that there is a high possibility of introducing the most remote telemedicine service in South Africa and that the possibility of introducing telemedicine service is high even in Thailand where the Internet spread is advanced.

  • Mobile health approaches in the management of skin cancer: Lessons from integrative mapping of evidence-based research

    Date Submitted: Jul 26, 2017

    Open Peer Review Period: Jul 26, 2017 - Sep 20, 2017

    Background: mHealth, which encompasses mobile health technologies and interventions, is rapidly evolving in various medical specialties, and its impact is evident in oncology. Mobile technologies are...

    Background: mHealth, which encompasses mobile health technologies and interventions, is rapidly evolving in various medical specialties, and its impact is evident in oncology. Mobile technologies are perceived as effective in prevention and as feasible for managing skin cancer, but the diagnostic accuracy of these tools remains in doubt. These drawbacks in the application of mHealth to teledermatology call for intensified research to strengthen its role in dermatology. Objective: The purpose of this review was to describe current trends in research addressing the integration of mHealth into the management of skin cancer by examining evaluations of mHealth and its contributions across the cancer care continuum. Methods: A systematic review framework was applied to the search using the three electronic databases, PubMed, Web of Science, and Embase. We extensively reviewed appropriate studies regarding skin cancer and mobile technology published between 2000 and present. Studies were included if they discussed the role and impact of mobile technology in the management and evaluation of skin cancer. 33 studies were selected for analysis adhering to inclusion and exclusion criteria. Results: Of the 33 studies, 15 studies (45%) assessed the diagnostic accuracy of mobile technology in detecting skin cancer and ten studies (30%) examined the feasibility and acceptability of mobile technology. The remaining studies (24%) concerned skin cancer prevention, early diagnosis, reduced treatment, and follow-up care through mHealth interventions. Not all phases of skin cancer involve mHealth, and not all have been addressed by research. While the focus of current research was skewed toward prevention and diagnosis phases, the treatment and follow-up phases were the least addressed in the literature. Conclusions: The present review extends knowledge not only on the contributions but also on the integration of mHealth technologies in different phases of skin cancer care. To optimize the effectiveness of mHealth in dermatology, larger numbers of robust, evidence-based studies on teledermatology implementations, evenly distributed across the care continuum, should be conducted so that research can be expanded to systematic reviews.

  • Text-Message Self-Regulation Support to Reduce Alcohol Consumption among Non-Treatment-Seeking Young Adults

    Date Submitted: Jul 22, 2017

    Open Peer Review Period: Jul 24, 2017 - Sep 18, 2017

    Background: Stand-alone text message-based interventions can reduce heavy drinking episodes among non-treatment seeking young adults, but may not be optimized. Self-regulation support could enhance ef...

    Background: Stand-alone text message-based interventions can reduce heavy drinking episodes among non-treatment seeking young adults, but may not be optimized. Self-regulation support could enhance effectiveness by assisting goal setting and striving, but it remains unknown how to best integrate into text-message interventions. Objective: To evaluate engagement with a text message intervention (TRAC2) focused on reducing weekend alcohol consumption incorporating drinking-limit goal-commitment ecological momentary assessments (EMA) tailored to past 2-week alcohol consumption, intra-weekend goal reminders, self-efficacy EMA with support tailored to goal confidence, and max weekend alcohol consumption EMA with drinking limit goal feedback. Methods: We enrolled 38 non-treatment seeking young adults who screened positive for hazardous drinking in an urban emergency department. Following a 2-week text message assessment-only run-in, participants were given the opportunity to enroll in 4-week intervention blocks. We examined patterns of EMA responses and voluntary re-enrollment. We then examined how goal commitment and goal self-efficacy related to event-level alcohol consumption. Finally, we examined the association of length of TRAC2 exposure with alcohol-related outcomes from baseline to 3-months follow-up. Results: Among a diverse sample of young adults (56% female, 54% black race, 32% college enrolled), response rates to EMA queries were, on average, 82.3% for the first 4-week intervention block, 75.3% for the second 4-week block, and 72.8% for the third 4-week block. There were high rates of event-level drinking limit goal commitment (94%) and goal success (89%). The percentage of subjects being prompted to commit to a drinking limit goal above the binge threshold was 51.7% on week 1 and decreased to 0% by week 4. Low situational confidence was associated with lower goal success. There were reductions in alcohol consumption from baseline to 3-months but reductions were not different by length of intervention exposure. Conclusions: Preliminary evidence suggests that non-treatment seeking young adults will engage with a text message intervention incorporating self-regulation support features, resulting in high rates of weekend drinking limit goal commitment and goal success. Clinical Trial: n/a