A large scale analysis of mHealth app user reviews.

The global mHealth app market is rapidly expanding, especially since the COVID-19 pandemic. However, many of these mHealth apps have serious issues, as reported in their user reviews. Better understanding their key user concerns would help app developers improve their apps' quality and uptake. While app reviews have been used to study user feedback in many prior studies, many are limited in scope, size and/or analysis. In this paper, we introduce a very large-scale study and analysis of mHealth app reviews. We extracted and translated over 5 million user reviews for 278 mHealth apps. These reviews were then classified into 14 different aspects/categories of issues reported. Several mHealth app subcategories were examined to reveal differences in significant areas of user concerns, and to investigate the impact of different aspects of mhealth apps on their ratings. Based on our findings, women's health apps had the highest satisfaction ratings. Fitness activity tracking apps received the lowest and most unfavourable ratings from users. Over half of users who reported troubles leading them to uninstall mHealth apps gave a 1-star rating. Half of users gave the account and logging aspect only one star due to faults and issues encountered while registering or logging in. Over a third of users who expressed privacy concerns gave the app a 1-star rating. However, only 6% of users gave apps a one-star rating due to UI/UX concerns. 20% of users reported issues with handling of user requests and internationalisation concerns. We validated our findings by manually analysing a sample of 1,000 user reviews from each investigated aspect/category. We developed a list of recommendations for mHealth apps developers based on our user review analysis.

Digital Era of Mobile Communications and Smartphones: A Novel Analysis of Patient Comprehension of Cancer-Related Information Available Through Mobile Applications.

Many Americans use smartphone-based mobile applications to acquire health information. Our study evaluated the readability of mobile application-based patient educational materials (PEMs) about five prevalent cancers in the United States. The Apple and Google mobile application marketplaces were queried for breast, colon, lung, prostate, and stomach cancer-related applications, which were subsequently screened for PEMs and assessed with 10 validated readability assessments. Twenty-one pertinent applications yielded 249 articles that were written at an 11.8 ± 2.3 grade level; only 12 (4.8%) articles were written below an eighth grade level. The majority of cancer-related PEMs were written at too difficult reading levels for American patients.

Identifying and resolving conflict in mobile application features through contradictory feedback analysis.

As mobile applications proliferate and user feedback becomes abundant, the task of identifying and resolving conflicts among application features is crucial for delivering satisfactory user experiences. This research, motivated to align application development with user preferences, introduces a novel methodology that leverages advanced Natural Language Processing techniques. The paper showcases the use of sentiment analysis using RoBERTa, topic modeling with Non-negative matrix factorization (NMF), and semantic similarity measures from Sentence-BERT. These techniques enable the identification of contradictory sentiments, the discovery of latent topics representing application features, and the clustering of related feedback instances. The approach detects conflicts by analyzing sentiment distributions within semantically similar clusters, further enhanced by incorporating antonym detection and negation handling. It employs majority voting, weighted ranking based on rating scores, and frequency analysis of feature mentions to resolve conflicts, providing actionable insights for prioritizing requirements. Comprehensive evaluations on large-scale iOS App Store and Google Play Store datasets demonstrate the approach's effectiveness, outperforming baseline methods and existing techniques. The research improves mobile application development and user experiences by aligning features with user preferences and providing interpretable conflict resolution strategies, thereby introducing a novel approach to the field of mobile application development.

Quality Assessment of Smartphone Medication Management Apps in France: Systematic Search.

BACKGROUND: Adherence to medication is estimated to be around 50% for chronically ill patients in high-income countries. Improving the effectiveness of adherence interventions could have a far greater impact on population health than any improvement in specific medical treatments. Mobile health (mHealth) is one of the most effective solutions for helping patients improve their medication intake, notably through the use of mobile apps with reminder systems. With more than 327,000 apps available in the mHealth field, it is difficult for health care professionals and patients alike to choose which apps to recommend and use. OBJECTIVE: We aim to carry out a systematic search of medication management smartphone apps available in France that send reminders to patients and assess their quality using a validated scale. METHODS: Mobile apps were identified in October and November 2022 after a systematic keyword search on the 2 main app download platforms: App Store (Apple Inc) and Google Play Store. Inclusion criteria were free availability, date of last update, and availability in French. Next, 2 health care professionals independently evaluated the included apps using the French version of the Mobile App Rating Scale (MARS-F), an objective scoring system validated for assessing the overall quality of apps in the mHealth field. An intraclass correlation coefficient was calculated to determine interrater reliability. RESULTS: In total, 960 apps were identified and 49 were selected (25 from the App Store and 24 from the Google Play Store). Interrater reliability was excellent (intraclass correlation coefficient 0.92; 95% CI 0.87-0.95; P<.001). The average MARS-F score was 3.56 (SD 0.49) for apps on the App Store and 3.51 (SD 0.46) for those on the Google Play Store, with 10 apps scoring above 4 out of 5. Further, 2 apps were tested in at least one randomized controlled trial and showed positive results. The 2 apps with the highest ratings were Mediteo rappel de médicaments (Mediteo GmbH) and TOM rappel medicaments, pilule (Innovation6 GmbH), available on both platforms. Each app's MARS-F score was weakly correlated with user ratings on the App Store and moderately correlated on the Google Play Store. CONCLUSIONS: To our knowledge, this is the first study that used a validated scoring system to evaluate medication management apps that send medication reminders. The quality of the apps was heterogeneous, with only 2 having been studied in a randomized controlled trial with positive results. The evaluation of apps in real-life conditions by patients is necessary to determine their acceptability and effectiveness. Certification of apps is also essential to help health care professionals and patients identify validated apps.

Quality and Accessibility of Home Assessment mHealth Apps for Community Living: Systematic Review.

BACKGROUND: Home assessment is a critical component of successful home modifications, enabling individuals with functional limitations to age in place comfortably. A high-quality home assessment tool should facilitate a valid and reliable assessment involving health care and housing professionals, while also engaging and empowering consumers and their caregivers who may be dealing with multiple functional limitations. Unlike traditional paper-and-pencil assessments, which require extensive training and expert knowledge and can be alienating to consumers, mobile health (mHealth) apps have the potential to engage all parties involved, empowering and activating consumers to take action. However, little is known about which apps contain all the necessary functionality, quality appraisal, and accessibility. OBJECTIVE: This study aimed to assess the functionality, overall quality, and accessibility of mHealth home assessment apps. METHODS: mHealth apps enabling home assessment for aging in place were identified through a comprehensive search of scholarly articles, the Apple (iOS) and Google Play (Android) stores in the United States, and fnd.io. The search was conducted between November 2022 and January 2023 following a method adapted from PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Reviewers performed a content analysis of the mobile app features to evaluate their functionality, overall quality, and accessibility. The functionality assessment used a home assessment component matrix specifically developed for this study. For overall quality, the Mobile Application Rating Scale (MARS) was used to determine the apps' effectiveness in engaging and activating consumers and their caregivers. Accessibility was assessed using the Web Content Accessibility Guidelines (WCAG) 2.1 (A and AA levels). These 3 assessments were synthesized and visualized to provide a comprehensive evaluation. RESULTS: A total of 698 apps were initially identified. After further screening, only 6 apps remained. Our review revealed that none of the apps used thoroughly tested assessment tools, offered all the functionality required for reliable home assessment, achieved the "good" quality threshold as measured by the MARS, or met the accessibility criteria when evaluated against WCAG 2.1. However, DIYModify received the highest scores in both the overall quality and accessibility assessments. The MapIt apps also showed significant potential due to their ability to measure the 3D environment and the inclusion of a desktop version that extends the app's functionality. CONCLUSIONS: Our review revealed that there are very few apps available within the United States that possess the necessary functionality, engaging qualities, and accessibility to effectively activate consumers and their caregivers for successful home modification. Future app development should prioritize the integration of reliable and thoroughly tested assessment tools as the foundation of the development process. Furthermore, efforts should be made to enhance the overall quality and accessibility of these apps to better engage and empower consumers to take necessary actions to age in place.

COVID-19 Mobile Apps Trends Derived from Long-Term Google Play Analysis.

In this paper, we describe the 5-year trends of COVID-related mobile apps in the Google Play platform obtained by retrospectively analyzing app descriptions. Out of 21764 and 48750 unique apps available free of charge in the "medical" and "health and fitness", there were 161 and 143 COVID-related apps, respectively. The prominentrise in apps' prevalence occurred in January 2021.

Medical Apps for Android and iOS: Differences and Similarities.

Google Play and Apple's App Store dominate the mobile health app market. We analyzed the metadata and descriptive texts of apps in the medical category using semi-automated retrospective app store analysis (SARASA) and compared the store offerings in terms of their number, descriptive texts, user ratings, medical device status, diseases, and conditions (both keyword-based). Relatively speaking, the store listings for the selected items were comparable.

Performance evaluation of machine learning models on large dataset of android applications reviews.

With an ever-increasing number of mobile users, the development of mobile applications (apps) has become a potential market during the past decade. Billions of users download mobile apps for divergent use from Google Play Store, fulfill tasks and leave comments about their experience. Such reviews are replete with a variety of feedback that serves as a guide for the improvement of existing apps and intuition for novel mobile apps. However, application reviews are challenging and very broad to approach. Such reviews, when segregated into different classes guide the user in the selection of suitable apps. This study proposes a framework for analyzing the sentiment of reviews for apps of eight different categories like shopping, sports, casual, etc. A large dataset is scrapped comprising 251661 user reviews with the help of 'Regular Expression' and 'Beautiful Soup'. The framework follows the use of different machine learning models along with the term frequency-inverse document frequency (TF-IDF) for feature extraction. Extensive experiments are performed using preprocessing steps, as well as, the stats feature of app reviews to evaluate the performance of the models. Results indicate that combining the stats feature with TF-IDF shows better performance and the support vector machine obtains the highest accuracy. Experimental results can potentially be used by other researchers to select appropriate models for the analysis of app reviews. In addition, the provided dataset is large, diverse, and balanced with eight categories and 59 app reviews and provides the opportunity to analyze reviews using state-of-the-art approaches.

A Primer on the Role of iPhone Apps in Medical and Radiology Education and How to Develop Them.

Among the numerous innovations implemented in medical education since the beginning of the 21st century, small-group learning experiences have worked well for modern students and the application of computer technology provided access to thousands of lectures, images, and slides via the internet. This has helped to build an electronic foundation on which further educational adaptations have arisen in the current era, coupled with the altered communications landscape represented by Apple's introduction of the iPhone and Google's subsequent entrance onto the playing field. With the advent of smartphone applications (apps), education has taken on an even more personalized approach. Data show that the use of educational apps has been embraced by today's nursing and medical students, notably including radiology students. We survey recent research on the use and desirability of medical apps and offer practical tips for those ready to embark on developing medical, particularly radiology, educational apps including how to assess and hone them for optimal use.

The Validity of Mobile Applications to Facilitate Patient Care Provided to Cancer Patients: Opportunities and Limitations.

BACKGROUND: The use of health-related applications (apps) on smartphones has become widespread. This is especially of value during the ongoing SAR-COV-2 pandemic, where accessibility to health care services has been greatly limited. Patients with free access to apps can obtain information to improve their understanding and management of health issues. Currently, there are cancer-related apps available on iPhones and androids. However, there are no guidelines to control these apps and ensure their quality. Furthermore, these apps may significantly modify the patients' perception and knowledge about drug-related health services. OBJECTIVES: The aim of this study was to assess the convenience, quality, safety and efficacy of apps for cancer patient care. METHODS: The study was conducted by searching all apps related to cancer care on both Google Play Store and Apple iTunes Store. A detailed assessment was then performed using the mobile application rating scale (MARS) and risk assessment tools. RESULTS: The results indicated that on a scale from 1-5, 47% of the apps were rated ≥ 4. The MARS assessment of the apps yielded an overall quality rating of 3.38 ± 0.9 (mean ± SD). The visual appeal of the app was found to have a significant effect on app functionality and user engagement. The potential benefits of these apps come with challenges and limitations. Patents related to smartphone applications targeting patients were also discussed. CONCLUSION: We recommend a greater emphasis toward producing evidence-based apps. These apps should be rigorously tested, evaluated and updated by experts, particularly clinical pharmacists. Also, these apps may alter patient attitudes toward services provided by physicians and pharmacists. Finally, these apps should not replace in-person interactive health services.

Mobile Applications in Mood Disorders and Mental Health: Systematic Search in Apple App Store and Google Play Store and Review of the Literature.

OBJECTIVES: The main objective of this work was to explore and characterize the current landscape of mobile applications available to treat mood disorders such as depression, bipolar disorder, and dysthymia. METHODS: We developed a tool that makes both the Apple App Store and the Google Play Store searchable using keywords and that facilitates the extraction of basic app information of the search results. All app results were filtered using various inclusion and exclusion criteria. We characterized all resultant applications according to their technical details. Furthermore, we searched for scientific publications on each app's website and PubMed, to understand whether any of the apps were supported by any type of scientific evidence on their acceptability, validation, use, effectiveness, etc. Results: Thirty apps were identified that fit the inclusion and exclusion criteria. The literature search yielded 27 publications related to the apps. However, these did not exclusively concern mood disorders. 6 were randomized studies and the rest included a protocol, pilot-, feasibility, case-, or qualitative studies, among others. The majority of studies were conducted on relatively small scales and 9 of the 27 studies did not explicitly study the effects of mobile application use on mental wellbeing. CONCLUSION: While there exists a wealth of mobile applications aimed at the treatment of mental health disorders, including mood disorders, this study showed that only a handful of these are backed by robust scientific evidence. This result uncovers a need for further clinically oriented and systematic validation and testing of such apps.

Public Trust in Artificial Intelligence Applications in Mental Health Care: Topic Modeling Analysis.

BACKGROUND: Mental disorders (MDs) impose heavy burdens on health care (HC) systems and affect a growing number of people worldwide. The use of mobile health (mHealth) apps empowered by artificial intelligence (AI) is increasingly being resorted to as a possible solution. OBJECTIVE: This study adopted a topic modeling (TM) approach to investigate the public trust in AI apps in mental health care (MHC) by identifying the dominant topics and themes in user reviews of the 8 most relevant mental health (MH) apps with the largest numbers of reviewers. METHODS: We searched Google Play for the top MH apps with the largest numbers of reviewers, from which we selected the most relevant apps. Subsequently, we extracted data from user reviews posted from January 1, 2020, to April 2, 2022. After cleaning the extracted data using the Python text processing tool spaCy, we ascertained the optimal number of topics, drawing on the coherence scores and used latent Dirichlet allocation (LDA) TM to generate the most salient topics and related terms. We then classified the ascertained topics into different theme categories by plotting them onto a 2D plane via multidimensional scaling using the pyLDAvis visualization tool. Finally, we analyzed these topics and themes qualitatively to better understand the status of public trust in AI apps in MHC. RESULTS: From the top 20 MH apps with the largest numbers of reviewers retrieved, we chose the 8 (40%) most relevant apps: (1) Wysa: Anxiety Therapy Chatbot; (2) Youper Therapy; (3) MindDoc: Your Companion; (4) TalkLife for Anxiety, Depression & Stress; (5) 7 Cups: Online Therapy for Mental Health & Anxiety; (6) BetterHelp-Therapy; (7) Sanvello; and (8) InnerHour. These apps provided 14.2% (n=559), 11.0% (n=431), 13.7% (n=538), 8.8% (n=356), 14.1% (n=554), 11.9% (n=468), 9.2% (n=362), and 16.9% (n=663) of the collected 3931 reviews, respectively. The 4 dominant topics were topic 4 (cheering people up; n=1069, 27%), topic 3 (calming people down; n=1029, 26%), topic 2 (helping figure out the inner world; n=963, 25%), and topic 1 (being an alternative or complement to a therapist; n=870, 22%). Based on topic coherence and intertopic distance, topics 3 and 4 were combined into theme 3 (dispelling negative emotions), while topics 2 and 1 remained 2 separate themes: theme 2 (helping figure out the inner world) and theme 1 (being an alternative or complement to a therapist), respectively. These themes and topics, though involving some dissenting voices, reflected an overall high status of trust in AI apps. CONCLUSIONS: This is the first study to investigate the public trust in AI apps in MHC from the perspective of user reviews using the TM technique. The automatic text analysis and complementary manual interpretation of the collected data allowed us to discover the dominant topics hidden in a data set and categorize these topics into different themes to reveal an overall high degree of public trust. The dissenting voices from users, though only a few, can serve as indicators for health providers and app developers to jointly improve these apps, which will ultimately facilitate the treatment of prevalent MDs and alleviate the overburdened HC systems worldwide.

Gamification for Diabetes Type 1 Management: A Review of the Features of Free Apps in Google Play and App Stores.

PURPOSE: The objective of this study was to review most of the existing free m-Health applications (Apps) that use the gamification approach to manage diabetes type 1 in both App and Google Play stores. METHODS: Free mobile health applications "apps" that were related to diabetes mellitus have been identified in both App and Google Play stores. In order to cover all the mentioned applications, the following keywords, "game for type 1 diabetes" and "gamification for type 1 diabetes" were used in English and Arabic languages. All applications that were collected in the inclusion process were carefully analyzed, and the game name, game description, game features, game mechanics, game themes, and operating systems were recorded. RESULTS: A total of eight gamified applications related to type 1 diabetes were identified. Seven of these applications were in English language and only one application was in Arabic language. The applications were categorized into three main categories based on the theme of the application. The categories were taking care of a character, quizzes, and the storytelling theme. Moreover, there was no application that included the social networking feature. CONCLUSION: This study highlighted the most important features of the free mobile health applications "apps" for diabetes type 1 available in Google Play and App stores that can contribute to enhance the self-management of the diabetes condition by patients in Saudi Arabia. The identified applications have important characteristics that can be used in the future for the care and self-control of type 1 diabetic patients in Saudi Arabia.

Mobile applications in otolaryngology for patients: An update.

OBJECTIVE: Recently smartphones and tablets have spread in developed countries, and healthcare-related apps are growing incredibly in different specialties. The aim of this study is to provide an up-to-date review of the current OtoHNS (otolaryngology-head and neck surgery) apps developed for patients. METHODS: This mobile applications review was conducted in September 2017. Relevant apps about OtoHNS were searched in the Apple Store and in the Google Play using various keywords. We included helpful apps for OtoHNS patients. Apps for medical students, physician (95 apps) and non-English apps (6 apps) were excluded. RESULTS: At the end of our selection process, 216 apps have been included for mobile applications review. The number of apps published per year in OtoHNS has increased each year. The most common apps were about hearing, in particular 63 of 216 (29%) were hearing test; 75 of 216 (35%) for tinnitus treatment; 10 of 216 (5%) for sounds measurement around the patients; and 7 of 216 (3%) to treat vertigo. One hundred thirty-seven of 216 (63%) apps were free of charge. Physicians were clearly involved in the app's development in only 73 of 216 (34%) apps. One hundred sixty-three of 216 (75%) had no user ratings. CONCLUSIONS: Apps are increasingly and easily accessible, although their use in clinical practice is not yet totally accepted. Our review showed that most apps have been created with no guidance from otolaryngologist. Further steps are needed to regulate apps' development. Hoping an "App Board," such as editorial board for scientific journal, to assess app quality, validity, and effectiveness before they can be fully incorporated into clinical practice and medical education. LEVEL OF EVIDENCE: N/A.