App Installation Research Articles

Disentangled Representation Learning in Heterogeneous Information Network for Large-scale Android Malware Detection in the COVID-19 Era and Beyond

In the fight against the COVID-19 pandemic, many social activities have moved online; society's overwhelming reliance on the complex cyberspace makes its security more important than ever. In this paper, we propose and develop an intelligent system named Dr.HIN to protect users against the evolving Android malware attacks in the COVID-19 era and beyond. In Dr.HIN, besides app content, we propose to consider higher-level semantics and social relations among apps, developers and mobile devices to comprehensively depict Android apps; and then we introduce a structured heterogeneous information network (HIN) to model the complex relations and exploit meta-path guided strategy to learn node (i.e., app) representations from HIN. As the representations of malware could be highly entangled with benign apps in the complex ecosystem of development, it poses a new challenge of learning the latent explanatory factors hidden in the HIN embeddings to detect the evolving malware. To address this challenge, we propose to integrate domain priors generated from different views (i.e., app content, app authorship, app installation) to devise an adversarial disentangler to separate the distinct, informative factors of variations hidden in the HIN embeddings for large-scale Android malware detection. This is the first attempt of disentangled representation learning in HIN data. Promising experimental results based on the large-scale and real sample collections from security industry demonstrate the performance of Dr.HIN in evolving Android malware detection, by comparison with baselines and popular mobile security products.

Upping uptake of COVID contact tracing apps.

To contain the COVID-19 pandemic, many countries around the world rushed to develop digital contact tracing apps. However, the low rates of app installation have undermined the efficacy of such tools. A study by Munzert et al. shines light on potential barriers to adoption, as well as levers that could be used to increase uptake.

Incentivizing Data Donations and the Adoption of COVID-19 Contact-Tracing Apps: A Randomized Controlled Online Experiment on the German Corona-Warn-App

Data donations promise to unlock the social benefits of personal data. Most recently, contact-tracing apps have been developed to collect individuals' donated contact and health data to fight the COVID-19 pandemic. As the effectiveness of contact-tracing apps hinges critically on widespread app installation and continuous usage, we investigate whether monetary incentives can stimulate app adoption and data donations: In a randomized controlled online experiment, the effects of different monetary incentive mechanisms on verified installations as well as short- and long-term usage of the German Corona-Warn-App (CWA) are evaluated. We find monetary incentives to be effective in the short run as they significantly increase app installations and app usage 14 days after installation, tripling the number of users compared to no compensation. An additional choice of non-monetary compensation in the form of an optional charity donation is found to be ineffective in promoting installations or usage beyond outcomes of monetary incentives, suggesting that there is no substantial crowding-out of intrinsic motives in the short run. From a theoretical perspective, this is in line with 'avoidance of stigma' being the primary pro-social motivation for the adoption of contact-tracing apps. However, the positive adoption stimulus of monetary incentives vanishes in the long run: After eight months, adopters in treatments with extrinsic monetary incentives are significantly more likely to have stopped using the app than intrinsically motivated adopters who do not receive monetary incentives. This suggests that one-time payments are not sufficient to promote app usage and data donations in the long run. Finally, we present experimental evidence that empirical analyses based on hypothetical scenarios without verified actions are prone to over-estimating individuals' pro-social behavior in the context of data donations.

Real-time Analysis of Privacy-(un)aware IoT Applications

Abstract Abstract: Users trust IoT apps to control and automate their smart devices. These apps necessarily have access to sensitive data to implement their functionality. However, users lack visibility into how their sensitive data is used, and often blindly trust the app developers. In this paper, we present IoTWATcH, a dynamic analysis tool that uncovers the privacy risks of IoT apps in real-time. We have designed and built IoTWATcH through a comprehensive IoT privacy survey addressing the privacy needs of users. IoTWATCH operates in four phases: (a) it provides users with an interface to specify their privacy preferences at app install time, (b) it adds extra logic to an app’s source code to collect both IoT data and their recipients at runtime, (c) it uses Natural Language Processing (NLP) techniques to construct a model that classifies IoT app data into intuitive privacy labels, and (d) it informs the users when their preferences do not match the privacy labels, exposing sensitive data leaks to users. We implemented and evaluated IoTWATcH on real IoT applications. Specifically, we analyzed 540 IoT apps to train the NLP model and evaluate its effectiveness. IoTWATcH yields an average 94.25% accuracy in classifying IoT app data into privacy labels with only 105 ms additional latency to an app’s execution.

Digital Life Coaching for Myeloma Patients Undergoing Transplantation

BACKGROUND: Patients undergoing autologous stem cell transplantation (ASCT) for multiple myeloma (MM) face sudden exacerbations of anxiety, insomnia, and other symptoms within the initial weeks following ASCT. Even as these symptoms abate in subsequent months, long-term consequences include post-traumatic stress disorder (Griffith 2020), quality of life (QOL) impairments (El-Jawahri 2016), and chronic reliance on higher-risk medications such as benzodiazepines (Banerjee 2020). These findings are particularly relevant to MM patients given their older age at diagnosis, longer expected post-ASCT survival, and poorer QOL at baseline compared with other cancer patients (Kent 2015). Compared to other integrative interventions in the peri-ASCT setting, life coaching transcends a symptomatic focus while directly addressing the root determinants of impaired QOL. Life coaches work with patients using structured frameworks (Figure 1A) to provide longitudinal support, education, and accountability to meet patient-identified wellness goals. Digital life coaching (DLC) combines the strengths of life coaching with the capabilities of digital health by channeling patient-coach communication through patients' personal phones. Compared to in-person coaching, DLC is location-agnostic and allows patients to work their coaches more conveniently and frequently. DLC is feasible among ASCT survivors (Chen 2016) but has not yet been studied in the active peri-ASCT setting. We are conducting a pilot study of a 16-week DLC subscription to assess its feasibility and effects on QOL during an intensive period spanning from pre-ASCT hospitalization through Day +100 after ASCT. If successful, we plan to then pursue a randomized Phase II study comparing DLC versus usual care in the peri-ASCT setting. METHODS: Our study is registered at clinicaltrials.gov as NCT04432818. We plan to enroll 27 adult patients with MM undergoing first ASCT at our institution. Inclusion criteria include English language proficiency and ownership of a personal cellphone. Notably, neither ownership of a smartphone nor installation of a specific mobile app is required for patient enrollment. Enrolled patients will receive unlimited access to a certified life coach beginning at Day -5 before ASCT; bidirectional communication is encouraged via phone, text, or email. The life coaches will reach out at least once per week to help patients accomplish self-identified goals such as symptom management, stress reduction, and physical activity. Our study's primary endpoint is ongoing patient engagement, defined as least one patient-initiated outreach to their coach during each of four 4-week study subperiods. Our study's secondary endpoints include patient-reported outcome (PRO) assessments of QOL, distress, and sleep disturbances (to be collected using electronic surveys every 1-2 weeks as shown in Figure 1B). Exploratory endpoints include benzodiazepine usage and rates of electronic/phone communication with patients' treatment teams. We will analyze endpoints using descriptive methods, including stratification of secondary & exploratory endpoints by DLC usage and specific 4-week study subperiod. PROGRESS TO DATE: Of 18 approached patients as of the data cutoff (8/1/20), 15 (83%) have expressed interest. Reasons for non-enrollment include skepticism about the value of interactions with coaches who do not themselves have MM. Of the 15 patients who have expressed interest in the study, the median age is 65 (range: 50-81) and all but one patient report owning a personal smartphone. All 6 patients with finalized ASCT hospitalization dates have been enrolled and paired with life coaches. Adherence to weekly electronic PRO assessments has been 100% (n = 9 timepoints) to date, consistent with previous studies (Wood 2013). CONCLUSIONS: Our pilot study is ongoing. Our findings to date suggest that certain MM patients are phone-savvy and would be interested in digital health tools, which will continue to gain prominence in light of the ongoing COVID-19 pandemic. Strengths of DLC include its scalability across institutional lines and its ability to reach patients at home in an integrative manner. Results of this study will inform innovative approaches to support the wellbeing of patients with hematologic malignancies, both in the peri-transplantation setting and beyond. Disclosures Brassil: Pack Health: Current Employment. Patel:Pack Health: Current Employment. Jackson:Pack Health: Current Employment. Wong:Janssen: Research Funding; Roche: Research Funding; Amgen: Consultancy; Sanofi: Membership on an entity's Board of Directors or advisory committees; GSK: Research Funding; Bristol Myers Squibb: Research Funding; Fortis: Research Funding. Wolf:Adaptive: Consultancy, Membership on an entity's Board of Directors or advisory committees, Speakers Bureau. Martin:Seattle Genetics: Research Funding; AMGEN: Research Funding; GSK: Consultancy; Sanofi: Research Funding; Janssen: Research Funding. Shah:BMS, Janssen, Bluebird Bio, Sutro Biopharma, Teneobio, Poseida, Nektar: Research Funding; GSK, Amgen, Indapta Therapeutics, Sanofi, BMS, CareDx, Kite, Karyopharm: Consultancy.

Ask a(n)droid to tell you the odds: probabilistic security-by-contract for mobile devices

Security-by-contract is a paradigm proposed for the secure installation, usage, and monitoring of apps into mobile devices, with the aim of establishing, controlling, and, if necessary, enforcing security-critical behaviors. In this paper, we extend this paradigm with new functionalities allowing for a quantitative estimation of such behaviors, in order to reveal in real time the more and more challenging subtleties of new-generation malware and repackaged apps. The novel paradigm is based on formal means and techniques ranging from statistical analysis to probabilistic model checking. The framework, deployed in the Android environment, is evaluated by examining both its effectiveness with respect to a benchmark of real-world malware and its effect on the execution of genuine, secure apps.

Internet of Things and Blockchain-Based Framework for Coronavirus (COVID-19) Disease

The COVID-19 is an exponentially growing disease that has intentioned nations to use technologies to detect the coronavirus infection. Several nations are working greatly to fight against COVID-19. Many nations have been using a range of devices to combat the pandemic, seeking information about growth, monitoring as well as the leaking the confidential information of the residents. This research aims to assist infected people online using the Internet of Things (IoT) and Blockchain technologies through smart devices. IoT-based healthcare devices gather useful information, provide additional insight through symptoms and behaviors, allow remote monitoring, and simply give people better self - determination and healthcare. Blockchain allows the secure transfer of patient health information, regulates the medical distribution network. A four-layer architecture is proposed using IoT and Blockchain to detect and prevent individuals to be COVID 19. This research provides a framework for patients with COVID-19 infectious disease and recognizes health issues and diagnoses online. Smart devices such as smartphones can install any mobile apps such as Aarogya Setu, Tawakkalna, and so on. These applications can track COVID-19 patients properly. The installation of mobile apps on smart devices focuses to reduce the time and cost and increase the performance of the infectious patient's condition. A four-layer architecture is proposed using IoT and Blockchain technologies. Many research works focus on investigating, analyzing, and highlighting the affected individuals through guiding the COVID-19 infection. Eventually, various mobile apps are recognized and addressed in this paper.

One app to trace them all? Examining app specifications for mass acceptance of contact-tracing apps

ABSTRACT The current COVID-19 crisis has seen governments worldwide mobilising to develop and implement contact-tracing apps as an integral part of their lockdown exit strategies. The challenge facing policy makers is that tracing can only be effective if the majority of the population uses the one app developed; its specifications must therefore be carefully considered. We theorise on tracing apps and mass acceptance and conduct a full-factorial experiment to investigate how app installation intention is influenced by different app specifications based on three benefit appeals, two privacy designs, and two convenience designs. By applying quantile regression, we not only estimate the general effect of these app specifications but also uncover how their influence differs among citizens with different propensities for acceptance (i.e. critics, undecided, advocates) – a crucial insight for succeeding with mass acceptance. This study contributes to research in three ways: we theorise how mass acceptance differs from established app acceptance, we provide a fine-grained approach to investigating the app specifications salient for mass acceptance, and we reveal contextualised insights specific to tracing apps with multi-layered benefit structures. Our findings can guide policy makers by providing specification recommendations for facilitating mass acceptance of tracing apps during pandemics or other societal crises.

Project DiabEHT: An approach to improve self-care management of diabetes

To determine whether the project DiabEHT (Diabetic Electronic Health Tool) has significantly improved self-care management of participants with diabetes along with the aspects of general diet, physical activities, blood glucose monitoring, and foot-care; and their blood glucose level 6 weeks after the project implementation. Pre-experimental, one group pretest-posttest research study was conducted among 30 participants medically diagnosed with Diabetes Mellitus regardless of type. The project which included weekly support group activities and lecture series on diabetes, installation and use of the DiabEHT mobile app, and diabooth in the health center was implemented for 6 weeks. Participants' blood glucose levels were obtained before the start of each weekly session for 6 weeks. A modified version of the "Summary of Diabetes Self-Care Activities (SDSCA)" measure was used to evaluate participants' self-care management before and after the intervention. After 6 weeks of project implementation, the participants have showed significant improvement on the following diabetes self-care activities: general diet (P=0.000), physical activities (P=0.007), blood glucose monitoring (P=0.000), and foot-care (P=0.000). Their blood glucose levels had also significantly reduced (P=0.005). Indeed, the project had improved the diabetic participants' self-care management and compliance, and glycemic control. Nursescan take advantage of this innovation and consider integration into patient care. However, further studies are recommended to ensure sustainable incorporation and application into various settings.

A digital decision support system (selfBACK) for improved self-management of low back pain: a pilot study with 6-week follow-up

BackgroundVery few of the publicly available apps directed towards self-management of low back pain (LBP) have been rigorously tested and their theoretical underpinnings seldom described. The selfBACK app was developed in collaboration with end-users and clinicians and its content is supported by best evidence on self-management of LBP. The objectives of this pilot study were to investigate the basis for recruitment and screening procedures for the subsequent randomized controlled trial (RCT), to test the inclusion process in relation to questionnaires and app installation, and finally to investigate the change in primary outcome over time.MethodsThis single-armed pilot study enrolled 51 participants who had sought help for LBP of any duration from primary care (physiotherapy, chiropractic, or general practice) within the past 8 weeks. Participants were screened for eligibility using the PROMIS-Physical-Function-4a questionnaire. Participants were asked to use the selfBACK app for 6 weeks. The app provided weekly tailored self-management plans targeting physical activity, strength and flexibility exercises, and education. The construction of the self-management plans was achieved using case-based reasoning (CBR) methodology to capture and reuse information from previous successful cases. Participants completed the primary outcome pain-related disability (Roland-Morris Disability Questionnaire [RMDQ]) at baseline and 6-week follow-up along with a range of secondary outcomes. Metrics of app use were collected throughout the intervention period.ResultsFollow-up data at 6 weeks was obtained for 43 participants. The recruitment procedures were feasible, and the number needed to screen was acceptable (i.e., 1.6:1). The screening questionnaire was altered during the pilot study. The inclusion process, answering questionnaires and app installation, were feasible. The primary outcome (RMDQ) improved from 8.6 (SD 5.1) at baseline to 5.9 (SD 4.0) at 6-week follow-up (change score 1.8, 95% CI 0.7 to 2.9). Participants spent on average 134 min (range 0–889 min) using the app during the 6-week period.ConclusionThe recruitment, screening, and inclusion procedures were feasible for the subsequent RCT with a small adjustment. The improvement on the RMDQ from baseline to follow-up was small. Time pattern of app usage varied considerably between the participants.Trial registrationNCT03697759. Registered on August 10, 2018. https://clinicaltrials.gov/ct2/show/NCT03697759

Covert Device Association Among Colluding Apps via Edge Processor Workload

While thriving application (app) distribution systems involving incentivized third-party app vendors are desirable for the emerging edge computing paradigm, they also bring security challenges as faced by the current mobile app distribution systems. This article studies a threat called covert device association , in which the vendors of two apps collude to figure out which of their app installations run on the same edge device. The threat can widely spread when the two apps are popular. It is also a stepping stone for: 1) the de-anonymization attacks against the users anonymous to one of the two vendors and 2) privilege escalation in which the two colluding vendors have united privileges. We show that the threat can be implemented via a reliable and ubiquitous covert channel based on the edge device’s processor workload without requiring any privileged permissions. We present the implementation details for three attack scenarios of: 1) two Android apps; 2) an Android app and a Web session running in the mobile Tor browser; and 3) two Android Things apps. Evaluation on two smartphones and an embedded edge device shows that the covert channel gives at least 0.25 b/s data rate with zero empirical bit error rate and the covert device association can be completed within 3.2 min.

Abstract WP451: “Development, Feasibility and Validation of “Stroke Home Care” Application in a Resource Limited Setting: A Proof of Concept Study”

Introduction: Stroke rehabilitation and caregivers training is central to improve post stroke care and reduce caregivers’ burden. Mobile applications(app) may provide a patient and caregiver centric modality to improve stroke care Aim: To develop and evaluate feasibility of a medical application for delivering post stroke care. Methods: A mobile app was developed on an android operating system following a preliminary assessment of post stroke complications to train caregivers. App consists of videos of home based care strategies for bedsore prevention, feeding, mouth care, ROM exercises, catheter care, psychological support to patients etc. App includes awareness videos on stroke, problems faced after stroke, follow up schedule, feedback option. App feasibility was assessed among 25 bedridden stroke survivors and their caregivers selected purposely. App validation was done by 16 stroke experts including neurologists, nurses, psychologists, physiotherapists using semi-structured-questionnaire for data collection. Following this, final "Stroke Home Care" app was developed. Results Feasibility: Mean age of patients and caregivers was 52.6±14.8 and 32.4±8.9years, respectively. 64% patients females, 75% caregivers males. 56% lived in rural. Median NIHSS 14 (IQR: 12-17). Complications were 56% Ryle’s tube, 72% Foley’s catheter, 12% bedsore. 64% caregivers were graduates. 52% sons. All caregivers responded that app contents, videos and language was understandable and appropriate. 92% preferred ‘Hindi’ language. All agreed to App enhancing their stroke knowledge. All were satisfied. Validation: Mean age of experts was 33.2±4years. 75% females. 56% nursing experts and postgraduates,19% MDs. 50% Nursing teachers, 19% Neurology fellows. None faced any app installation problem. 81.3% experts highly satisfied with app functions, its contents, voice clarity, video clarity and duration, contents’ sequence, understandability. Discussion/Conclusion: “Stroke Home Care” App is feasible, pragmatic and user-friendly for use by caregivers of stroke survivors in a resource limited setting/developing country. It should be tested by an RCT to evaluate its efficacy in reducing post stroke complications and reducing caregivers’ burden.

Status quo and analysis of the use of smartphone APP in medical staffs

Objective To explore the current installation and use of smartphone APP in medical workers and to provide a basis for the proper use of smartphones for mobile learning and developing APPs for medical workers. Methods Totally 529 medical staffs were selected from two ClassⅢ hospitals in Beijing by simple random sampling from June to September 2018. These subjects were investigated with the self-designed questionnaire, which mainly included basic information, overall use of smartphone APP, use of various smartphone APPs, and conditions that a good APP should have. All the questionnaires were filled out by the subjects themselves. Results Totally 76.9% question naires were distributed, and 503 valid ones were collected. Totally 76.9% (387/503) of the medical workers used smartphones for 2 years, among whom 84.4% (425/503) had at least 6 APPs installed on their smartphones. The top 3 kinds of APPs were communication and information (98.6%, 496/503) , document readers (93.2%, 454/503) , and medicine-associated APPs (90.3%, 454/503) . Totally 22.9% (115/503) of the medical workers used APPs for 120 mins accumulatively every day, mostly when waiting for the bus, taking the bus, waiting for someone, or there was a difficult question that needed them to find some information. Conclusions Medical workers have made smartphone APPs a necessary tool for their work and life, especially in communication, learning and improving working efficiency. More APPs that are suitable for medical workers may be developed in the future, so they can improve the capability and efficiency of medical and nursing work by mobile micro-learning and micro-office. Key words: Medical staffs; Smartphone APP; Status quo

Predictors of the Number of Installs in Psychiatry Smartphone Apps: Systematic Search on App Stores and Content Analysis

BackgroundMental health is integral to our salubrity, but mental disorders are very debilitating and common. Therefore, it is critical to provide accessible, timely, and inexpensive mental care. This can be done through mobile health (mHealth), namely, mobile medical apps, which are gaining popularity among clinicians and patients. mHealth is a fast-paced field, and there is significant variation in the number of installs among psychiatry apps. However, the factors that influence psychiatry app installs have yet to be studied.ObjectiveThis study aimed to identify predictors of the number of app installs in psychiatry.MethodsA literature review identified which factors influence app installs. Psychiatry apps available in the Google Play Store were reviewed, and publicly available data were collected. A multivariate ordinal logistic regression analysis was performed to evaluate the effect of said factors on the number of installs.ResultsOur search identified 128 psychiatry apps: 2.3% (3/128) had never been installed, approximately half (53.1%, 68/128) had less than 500 installs, and only 0.8% (1/128) had over 10,000,000 installs. A multivariate logistic regression analysis identified that apps with a lower price (P<.001), a higher rating (P<.001), optional in-app purchases (P<.001), and age restriction (P=.04) had a higher number of installs. The involvement of a psychiatrist or other health care professional (HCP) had no statistically significant influence on the number of installs. Only data from the Google Play Store and the developers’ websites were available for analysis, and the depth of involvement of HCPs was impossible to document.ConclusionsPsychiatry apps with a lower price, optional in-app purchases, age restriction, and a higher rating are expected to have a higher number of installs. Unlike other medical fields, in this study, the explicit participation of psychiatrists in app development was not a significant predictor of the number of installs. Research is needed to identify other factors that may influence the number of installs, as that can help mHealth app development.

An Improved User Authentication Model for Mobile Application Systems: Statistical Assessment of User Acceptance

One of the reasons mobile phones become one of the worldwide commonly usedcommunication devices nowadays is because they allow the installation of various mobile apps which are mostly interesting and useful to mobiles users. Unfortunately, mobile apps involve transmissions of digital data wirelessly and vulnerable to hacking activities. An improved user authentication modelhas been introduced in this study. Its strength in preventing hacking activities and the level of user acceptance are being analyzed. The strength is built based on the multi-factoring, ciphering and watermarking techniques being introduced in the model. It is technically measured based on the vulnerability and penetration tests done by an appointed independent party but excluded in this paper. On the other hand, the level of acceptance is measured using a quantitative method. Even though the quantitative method in this study undergoes expert review, pilot study and survey, this paper only focuses on the survey since its outcome is used to conclude the level of acceptance by mobile users. The statistical analysis results indicate that mobile users perceive ciphering technique contributes the most to this strength while watermarking technique has the strongest relationshipsandbecome the dominant factor in making the model acceptable by users.

Objective User Engagement With Mental Health Apps: Systematic Search and Panel-Based Usage Analysis.

BackgroundUnderstanding patterns of real-world usage of mental health apps is key to maximizing their potential to increase public self-management of care. Although developer-led studies have published results on the use of mental health apps in real-world settings, no study yet has systematically examined usage patterns of a large sample of mental health apps relying on independently collected data.ObjectiveOur aim is to present real-world objective data on user engagement with popular mental health apps.MethodsA systematic engine search was conducted using Google Play to identify Android apps with 10,000 installs or more targeting anxiety, depression, or emotional well-being. Coding of apps included primary incorporated techniques and mental health focus. Behavioral data on real-world usage were obtained from a panel that provides aggregated nonpersonal information on user engagement with mobile apps.ResultsIn total, 93 apps met the inclusion criteria (installs: median 100,000, IQR 90,000). The median percentage of daily active users (open rate) was 4.0% (IQR 4.7%) with a difference between trackers (median 6.3%, IQR 10.2%) and peer-support apps (median 17.0%) versus breathing exercise apps (median 1.6%, IQR 1.6%; all z≥3.42, all P<.001). Among active users, daily minutes of use were significantly higher for mindfulness/meditation (median 21.47, IQR 15.00) and peer support (median 35.08, n=2) apps than for apps incorporating other techniques (tracker, breathing exercise, psychoeducation: medians range 3.53-8.32; all z≥2.11, all P<.05). The medians of app 15-day and 30-day retention rates were 3.9% (IQR 10.3%) and 3.3% (IQR 6.2%), respectively. On day 30, peer support (median 8.9%, n=2), mindfulness/meditation (median 4.7%, IQR 6.2%), and tracker apps (median 6.1%, IQR 20.4%) had significantly higher retention rates than breathing exercise apps (median 0.0%, IQR 0.0%; all z≥2.18, all P≤.04). The pattern of daily use presented a descriptive peak toward the evening for apps incorporating most techniques (tracker, psychoeducation, and peer support) except mindfulness/meditation, which exhibited two peaks (morning and night).ConclusionsAlthough the number of app installs and daily active minutes of use may seem high, only a small portion of users actually used the apps for a long period of time. More studies using different datasets are needed to understand this phenomenon and the ways in which users self-manage their condition in real-world settings.

Smartphone App as Motivational Intervention to Improve Glycemic Control in Adolescents with Type 1 Diabetes.

Type 1 diabetes (T1D) adolescents often do not achieve good glycemic control. In the context of growing number of technologically savvy adolescents, this study was done to examine the effectiveness of a motivational smartphone app to improve their glycemic control. Eleven to eighteen year old adolescents, treated by Pediatric endocrine team of CMC, Vellore, who had T1D ≥ 1 y duration with poor glycemic control (mean HbA1c ≥ 8.5% in preceding 12 mo) were recruited. An app programmed to provide 3 reminders per day regarding insulin, meals and physical exercise was installed on their phone. Diabetes management was continued as per the standard of care. HbA1C was measured after 3 mo. Thirty seven adolescents were recruited; 3 were excluded as the app became non-functional. Seventeen were boys, mean age was 13.8 y (11-18 y) and mean duration of diabetes was 4.9 y (0.8-16 y). The mean HbA1c levels over preceding 12 mo and at recruitment were 10.75% (1.88) and 10.6% (2.08) respectively. Twenty eight participants returned for repeat HbA1C after 3-4 mo. As compared to baseline there was significant reduction in HbA1c level: 10.6% (2.08) vs. 9.65% (1.6); p = 0.004. Twenty two of twenty eight participants showed reduction in HbA1c after app installation. The magnitude of change in HbA1c levels over a 3 mo period before and after the app use was analyzed. There was significant difference between mean HbA1c levels before and after app use; +0.28 (2.06) vs. -0.914 (1.52); p = 0.019. Following usage of smartphone app as a motivational intervention in adolescents with Type 1 diabetes, there was significant reduction in HbA1c level after 3 mo. With continued use, this may benefit them to achieve target HbA1c levels. Use of mobile phone apps as motivational interventions is feasible in adolescents with Type 1 diabetes in India.

Is a smartphone application effective in improving physical activity among medical school students? Results from a quasi-experimental study.

Physical activity (PA) is proven to be an effective strategy to avert the life threatening cardiovascular diseases. There is need for developing feasible aids to improve compliance to PA. Hence, we conducted a study among medical college students a) to assess the prevalence of recommended PA level and b) to assess the effectiveness of installing a smartphone application (app) in improving PA. A quasi-experimental study was conducted among medical college students in Puducherry, India. The baseline PA was assessed using the Global Physical Activity Questionnaire (GPAQ) and anthropometric measurements such as height and weight were measured as per World Health Organization (WHO) standards. A smartphone app (Runtastic) was installed on the mobile phones of all study participants. At the end of 1 month, the end line PA and anthropometric measurements were captured using same scales. Of the total 350 students who were included, the mean age of the participants was 18.9 (0.9) years and 58% of them were male. The proportion of participants with the WHO recommended level of PA increased from 81% at the baseline to 91% after 1 month of installation of the mobile app (p < 0.001). There was also a statistically significant increase in the leisure time PA [median (interquartile range - IQR) of metabolic equivalents (METS): 0 (0-1600) vs. 1260.0 (0-1920)]. Clinically significant change was not seen in body mass index (BMI) though the reduction was statistically significant [(mean (standard deviation - SD) of BMI: 22.54 (2.49) vs. after intervention 22.46 (2.47); p = 0.018]. This quasi-experimental study conducted among medical college students reported significant improvement in total and leisure time PA.

Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review.

BackgroundState-of-the-art classifiers based on convolutional neural networks (CNNs) were shown to classify images of skin cancer on par with dermatologists and could enable lifesaving and fast diagnoses, even outside the hospital via installation of apps on mobile devices. To our knowledge, at present there is no review of the current work in this research area.ObjectiveThis study presents the first systematic review of the state-of-the-art research on classifying skin lesions with CNNs. We limit our review to skin lesion classifiers. In particular, methods that apply a CNN only for segmentation or for the classification of dermoscopic patterns are not considered here. Furthermore, this study discusses why the comparability of the presented procedures is very difficult and which challenges must be addressed in the future.MethodsWe searched the Google Scholar, PubMed, Medline, ScienceDirect, and Web of Science databases for systematic reviews and original research articles published in English. Only papers that reported sufficient scientific proceedings are included in this review.ResultsWe found 13 papers that classified skin lesions using CNNs. In principle, classification methods can be differentiated according to three principles. Approaches that use a CNN already trained by means of another large dataset and then optimize its parameters to the classification of skin lesions are the most common ones used and they display the best performance with the currently available limited datasets.ConclusionsCNNs display a high performance as state-of-the-art skin lesion classifiers. Unfortunately, it is difficult to compare different classification methods because some approaches use nonpublic datasets for training and/or testing, thereby making reproducibility difficult. Future publications should use publicly available benchmarks and fully disclose methods used for training to allow comparability.

Using Smartphone Apps to Promote Psychiatric Rehabilitation in a Peer-Led Community Support Program: Pilot Study.

BackgroundManagement of severe and persistent mental illness is a complex, resource-intensive challenge for individuals, their families, treaters, and the health care system at large. Community-based rehabilitation, in which peer specialists provide support for individuals managing their own condition, has demonstrated effectiveness but has only been implemented in specialty centers. It remains unclear how the peer-based community rehabilitation model could be expanded, given that it requires significant resources to both establish and maintain.ObjectiveHere, we describe the results from a study of one such program implemented within Waverley Place, a community support program at McLean Hospital, emphasizing psychiatric rehabilitation for individuals with severe and persistent mental illness, as well as describing the challenges encountered during the implementation of the program. Key questions were whether the patients could, and would, successfully use the app.MethodsThe smartphone app offered multiple features relevant to psychiatric rehabilitation, including daily task lists, activity tracking, and text messaging with peer specialists. A 90-day program of activities, goals, and content specific to the community support program was created on the basis of a prior pilot, in collaboration between members of the app development team (WellFrame), and peers, clinical, and research staff associated with the program. Hospital research staff recruited patients into the study, monitored peer and patient engagement, and handled all raw data acquired from the study.ResultsOf 100 people approached for the study, a total of 13 provided consent, of which 10 downloaded and used the app. Two patients were unable to complete the app installation. Five used the app regularly as part of their daily lives for at least 20 days of the 90-day program. We were unable to identify any specific factors (eg, clinical or demographic) that affected willingness to consent or engage with the app platform in the very limited sample, although the individuals with significant app use were generally satisfied with the experience.ConclusionsSmartphone apps may become a useful tool for psychiatric rehabilitation, addressing both psychiatric and co-occurring medical problems. Individualizing functions to each patient and facilitating connection with a certified peer specialist may be an important feature of useful apps. Unlike prior reports emphasizing that patients with schizophrenia will adopt smartphone platforms, we found that implementation of digital tools into existing community support programs for severe and persistent mental illness has many challenges yet to be fully overcome to realize the potential benefits such apps could have to promote systematization and cost reduction for psychiatric rehabilitation.