The increase in mobile phone users led to increased attention toward mobile health apps. More than 10,000 mobile applications target mental health issues. This increased attention urged a study that provides a clear view of current research. However, there is a lack of recent studies on mobile sensing apps for mental health. This paper aims to fill this gap by exploring the theoretical and practical methods and technical development of mobile apps. We reviewed 77 studies examining mobile sensing apps for mental health and classified them by research goal into Association, Detection, and Intervention apps. The paper investigates various themes, including targeted mental issues, sensing types, mental health indicators, goals, and focus. Our study revealed that most apps are designed for the Android platform, neglecting other platforms; there is a lack of comprehensive tools to study multiple health issues, and many studies did not take users’ privacy into account.

This retrospective study of 428 patients with acute ischemic stroke at a county-level hospital in China found that implementing the Xheart novel mobile app significantly reduced the median door-to-needle time from 52 to 38 minutes (P<.001) and was associated with lower National Institutes of Health Stroke Scale scores 24 hours after thrombolysis (P=.02), indicating the potential of mobile health technologies to improve the emergency management of patients with acute ischemic stroke in resource-constrained settings.

The rising global aging population has increased the prevalence of Alzheimer’s disease (AD), a condition with limited treatment options, making non-pharmacological interventions essential. While mobile health apps are increasingly common, there is currently a lack of theory-based, user-centered research to support the development of mobile health apps for family caregivers of persons living with AD. This study aimed to design a theory-based and user-centered mobile application that supports family caregivers by leveraging non-pharmacological interventions to aid in the management and potential slowing of AD progression, with the ultimate goals of improving care quality and reducing their burden. The study employed a three-phase methodology: (1) Establishing a theoretical framework based on Narrative Evidence-Based Medicine and Maslow’s hierarchy of needs; (2) Conducting semi-structured interviews with target users (n = 18), with transcripts analyzed thematically to inform the app’s development by an interdisciplinary team; (3) Performing a preliminary evaluation with participants (n = 20) who used the app for three weeks, after which a questionnaire assessed its short-term impact and user-friendliness. Thematic analysis yielded five key themes: Content, Platform, Functionality, Interactivity, and Interface. The mWITH ME app consists of four modules: educational support, professional support, peer support, and health monitoring. In the preliminary evaluation, 75% (n = 15) of participants reported that using the app reduced their daily caregiving burden, 80% (n = 16) expressed satisfaction with the application, and 70% (n = 14) acknowledged its role in improving care quality. The modules for Educational, Professional, and Peer Support received particularly positive feedback, which aligns with the app’s underlying theoretical framework of Narrative Evidence-Based Medicine and Maslow’s hierarchy of needs. Nonetheless, the Health Monitoring module was identified as requiring further enhancements to better meet user expectations. The mWITH ME app demonstrates feasibility in supporting family caregivers by addressing their professional, educational, and emotional needs. Future work should focus on developing features for mood and fatigue monitoring, while long-term studies are needed to evaluate its integration into standard care pathways and its potential to improve the quality of life for both the caregivers and persons living with AD.

Mobile application development has evolved significantly with the emergence of cross-platform frameworks that enable developers to build applications for both Android and iOS using a single codebase. Among these frameworks, Flutter and React Native have gained substantial popularity due to their performance efficiency, development speed, and strong community support. This research paper presents a comparative analysis of Flutter and React Native, focusing on architecture, performance, UI capabilities, developer experience, community ecosystem, and future trends. The study evaluates how these frameworks influence modern mobile development practices and explores their advantages, limitations, and suitability for different types of applications. The findings suggest that while both frameworks significantly reduce development time and cost, Flutter offers better UI consistency and performance due to its native rendering engine, whereas React Native benefits from JavaScript flexibility and a mature ecosystem.

Background: Hemovigilance is a critical surveillance system designed to enhance blood transfusion safety by monitoring, detecting, and preventing adverse transfusion reactions. Despite the launch of the Hemovigilance Program of India, awareness and engagement remain notably low among entry-level medical professionals, potentially compromising patient safety and quality of care.Objective: This study aimed to assess the knowledge, attitude, and practice (KAP) related to hemovigilance, identify barriers to adverse transfusion reaction reporting, and recommend strategies to enhance participation and improve reporting culture among entry-level medical professionals at a tertiary care teaching hospital in northern India.Methods: A descriptive, cross-sectional questionnaire-based survey was conducted among 414 entry-level medical professionals, including MBBS students (first & second professional years), postgraduate medical trainees, and resident doctors. The 20-item questionnaire explored various domains such as demographic characteristics, knowledge related to hemovigilance, and attitudes toward transfusion reaction reporting, actual reporting practices, perceived barriers, and potential strategies to enhance reporting. Data were collected in offline mode over a period of three months using a pen-and-paper approach.Results: The majority of participants, 376 (90.8%), were between 20 and 30 years of age, with a predominance of female participants, 234 (56.5%). Awareness of transfusion reactions was high (386; 93.2%), and most participants recognized their preventability (328; 79.2%), yet only 152 (36.7%) were aware of the National Hemovigilance Program. Positive attitudes towards hemovigilance were evident, with nearly all participants endorsing its benefits (414; 100%) and acknowledging professional responsibility to report (396; 95.6%). Support for curricular integration (402; 97.1%) and enrolment of every institution under PvPI (384; 92.7%) was strong. However, only 56 (13.5%) had witnessed a transfusion reaction, and a meagre 22 (5.3%) had reported one, signifying a substantial practice gap. Suggested improvements included user-friendly mobile app development, compulsory reporting, and targeted educational interventions.Conclusion: Although medical professionals demonstrated strong knowledge and positive attitudes toward hemovigilance, practical implementation is lacking. Enhanced education, streamlined reporting tools, and institutional support are imperative to bridge the gap between awareness and practice, thereby improving blood transfusion safety and patient outcomes. Early introduction of hemovigilance and incentivization like certificates of appreciation, acknowledgement of names on hospital display boards or newsletters/magazines, grace marks, attendance credit for students, and a token of appreciation for faculty members can play a big role in improving reporting.

Leptospirosis is the most common zoonotic cause of mortality, with most of its burden occurring in tropical regions and low-income countries. It is endemic in Southeast and South Asian nations. Leptospirosis outbreaks occur after natural disasters. In Malaysia, the e-notification system of the Communicable Diseases Control Information System recorded 5217 leptospirosis cases in 2019 with 32 fatalities. The incidence rate was 15.61 per 100,000 people. Male individuals comprised 67% of leptospirosis cases, while people aged 25 to 55 years accounted for 45% of the cases. Information and perception are crucial in influencing positive behavior. Nonetheless, information on urban and rural people's knowledge, attitude, and practice (KAP) regarding the incidence of leptospirosis is limited. We aimed to develop a mobile app with information on leptospirosis and measure its effectiveness in improving KAP regarding leptospirosis among wet market workers in Selangor, Malaysia. A 3-phase study will be conducted and includes development of a mobile app containing information about leptospirosis, analysis of its acceptability, and application of the intervention. Participants will be recruited based on specific inclusion criteria by using purposive sampling. Four wet markets in Hulu Langat district, Selangor, will be selected according to a list provided by local municipal councils. The respondents from each selected wet market will be workers aged 18 years and older. Mobile app development will begin with an idea description, storyboard creation, and content approval through the nominal group technique. The mobile app content will be constructed using the Health Belief Model theory. Subsequently, the usability of the mobile app prototype will be evaluated using the validated Malay version of the System Usability Scale questionnaire for the evaluation of mobile apps. This protocol entails a 12-week intervention stage, in which the baseline assessment is regarded as a pretest evaluation and the follow-up assessment as a posttest evaluation. Participant selection will be based on the inclusion and exclusion criteria. This study will incorporate a set of validated questionnaires created by a group of leptospirosis experts. The validated questionnaire will comprise 9 sections with open-ended questions on sociodemographic data, KAP, and mobile app requirements. Mobile app development and usability testing were completed between January 2024 and March 2025. Participant recruitment is scheduled in April to May 2025 after submission of this manuscript, with the 12-week intervention and data collection running from May to July 2025. As of manuscript submission, recruitment, data collection, and data analysis have not yet begun. Data analysis is expected to be completed by September 2025, and results are anticipated for publication in late 2025. Due to the high number of reported leptospirosis cases in the Hulu Langat district, Selangor, this intervention study will be conducted there. The development of the mobile app may contribute to improving wet market workers' KAP regarding leptospirosis. PRR1-10.2196/75809.

In recent years, there has been increasing interest in the study of the gut–brain axis. Furthermore, there appears to be a relationship between abdominal pain, selective eating patterns, emotional instability, and intestinal disorders in Autism Spectrum Disorder (ASD). This work describes the development and accessibility evaluation of the INCE mobile app. This mobile app allows users to obtain levels of gut–brain interaction severity using two scientifically proven scales: The Gastrointestinal Symptom Severity Scale (GSSS) and the Pain and Sensitivity Reactivity Scale (PSRS). The validity of both instruments was established in previous studies in neurotypical and autistic populations. Statistically significant improvements were found following post-design changes in the use and accessibility of the INCE app (.NET Maui 9 Software) reported by professionals (p = 0.013), families (p = 0.011), and adolescents (p = 0.004). INCE represents an important contribution to evidence-based applications and clearly translates into society.

Technological progress has completely altered the landscape of educational libraries, evolving them from mere collections of physical books into lively centers for online education, remote support, smart search mechanisms using artificial intelligence, and advanced systems for organizing information. This hands-on research examines how college libraries are adapting to this tech-focused environment by closely looking at what users think at Hindu College in Sonipat a prominent institution providing a range of undergraduate and postgraduate courses in humanities, business, and sciences.Using a questionnaire available in both English and Hindi, we gathered firsthand information from 200 students and 40 faculty and staff (total sample size of 240, with everyone responding) in December 2025. The survey covered topics like how often people use the library, their knowledge of online materials, what they like or dislike, obstacles they face, how happy they are with services, and ideas for improvements. We crunched the numbers using basic stats like counts and percentages in Microsoft Excel, and grouped open-ended answers into common themes. Graphs such as pie charts and tables help make the information clearer.Main discoveries point to a clear move toward technology: 58% favor online materials compared to just 10% for printed ones, and 42% access digital content weekly versus 38% visiting in person that often. People mainly go for personal learning (35%) and checking out electronic materials (18%). About 72% learn about these through introductory sessions and emails, but issues remain 70% mention unreliable internet, 43% point to weak facilities, and 40% note insufficient guidance. Overall, 60% are content or very content, with the library's preparedness scoring an average of 3.2 out of 5. Faculty appreciate help with studies, while learners focus on project support.Breaking it down by field, science majors lead with 65% preferring digital, then business at 58% and humanities at 52%. Free-form comments stress better wireless access (76%), frequent training sessions (70%), and specialized tech helpers (50%). When compared to country-wide standards from INFLIBNET documents, these facility shortcomings appear common in mid-tier schools.Our research suggests a structured approach with five key areas for tech upgrades: (1) Boosting facilities, (2) Required tech skills training, (3) Increasing subscriptions to online content, (4)Mobile app development, and (5) Institutional repository creation. These practical suggestions aim to make Hindu College's library a benchmark for local tech evolution, improving learning results even with limited funds. This work offers useful advice for decision-makers, library professionals, and school leaders dealing with today's tech-savvy students.

Mobile application (app) reviews provide valuable information that facilitates understanding of users’ needs, leading to better design of developed products. They have abundant data that can be utilized by different models to explain the prediction results to stakeholders. This will lead mobile app developers to trust and rely on the models that are used to develop their apps and satisfy the users’ needs. To leverage this information, outstanding improvements in complex learning algorithms have led to the development of transformer-based models that are used for natural language processing (NLP) and to exploit rating predictions. However, such models are complex and lack explainability, especially for Arabic reviews. Most studies have applied explainability models for transformer-based models to the English language and various other languages but not the Arabic language. This study presents a rating prediction explain-ability (RPE) framework that combines transformer-based and explainability models for review rating predictions from mobile government (m-government) apps. The transformer-based models predict the ratings for reviews written in English or Arabic. Then, local explainability models, such as SHapley Additive exPlanation (SHAP) and local interpretable model-agnostic explanations (LIME), explain and visualize the results. In RPE, not only high prediction accuracy was achieved for both English and Arabic reviews, but the resulted predictions were also justified with consistency between the different explainability models. The transformer-based model ELECTRA yielded the highest accuracy and F1 score of 96% for the rating prediction of English reviews, whereas the transformer-based model AraBERTv2 had 95%accuracy and F1 score for the rating prediction of Arabic reviews. The results of both explainability models provided equivalent explanations and emphasized the same words that affected the predicted ratings.

The authors present a study on the development and evaluation of the Trip Russia mobile app as a tool for increasing environmental responsibility in the field of domestic tourism. The relevance of the study is due to the growing anthropogenic pressure on natural areas caused by increased tourist traffic and the generation of solid municipal waste, while traditional approaches to waste management are often ineffective. The study used a combination of methods, including agent-based modeling in the NetLogo environment to create a digital twin of a recreational area and A/B testing of the app's interface to evaluate the impact of different design elements on user engagement. Modeling with 10 thousand virtual agents allowed us to compare scenarios with and without the application. The results showed that the implementation of the Trip Russia app, with an 80 % coverage rate, led to a 61 % reduction in unauthorized waste disposal, an 86 % increase in the likelihood of using separate collection containers, and a 26 % reduction in the average distance to a container. A/B testing revealed that an improved interface with instant visual rewards increased user engagement in replenishing the sustainability card by 42 % and increased retention by 22 %. The interpretation of the results confirms that the combination of smart navigation and gamification creates a synergistic effect, reducing physical and cognitive barriers to environmentally responsible behavior. The study concluded that the application is highly effective as a behavioral intervention tool that not only reduces environmental damage but also saves budget funds for cleaning up territories.

The increased demand for the development of adaptive and intelligent mobile apps has led to the rapid implementation of machine learning models in native iOS development, specifically using Swift. In this review, Swift programming and machine learning are discussed as coming together to enable real-time personalization in iOS applications. Using the power of on-device inference, frameworks such as CoreML and SwiftData, along with powerful API solutions, developers can build user-centric experiences that are secure, responsive, and contextual. This paper focuses on recent progress in emotion-aware design, which combines machine learning methods for identifying and reacting to the emotional state of users in real time through the analysis of inputs such as facial expressions, voice tone, typing behavior, and interaction patterns. Mobile deep learning and cross-platform deployment strategies are also discussed as shaping the future of personalized applications. Through an analysis of emerging trends such as federated learning and topic modeling, this review highlights the robustness of Swift-based development in providing a solid foundation for scalable, privacy-compliant, and intelligent user experiences. The results indicate that the convergence of Swift and machine learning is likely to characterize the next generation of personalization in mobile software development.

User reports submitted through feedback features or ticketing systems provide valuable insights for improving mobile applications. However, the high volume of reports creates challenges for review and decision-making. Effective classification and summarization are therefore essential to manage this information efficiently, allowing developers to quickly identify recurring issues and support data-driven development strategies. This study automates large-scale user feedback processing using Natural Language Processing (NLP) and evaluates multiple language models. The Bigbird-Small model achieved the highest agreement with the majority (81.51%) due to its ability to process long-text contexts. XLM-R-Base performed competitively (78.08%), while BERT-Base and Roberta-Base showed stable performance (75.68% and 74.32%). Distilbert-Base, though more computationally efficient, had slightly lower accuracy (74.32%). For summarization, Simple Prompt and Iterative Prompt approaches were compared. The Iterative Prompt with four iterations performed best, achieving similarity 0.911, compression 0.846, keyword overlap 0.624, and redundancy 0.070. These results demonstrate that combining automated classification with iterative summarization can significantly improve both efficiency and accuracy in managing user reports, supporting better decision-making and enhanced mobile app development.

Purpose This study aims to investigate ethical consideration into the data quality management and biases for fairness in artificial intelligence (AI) algorithms. It looks at how biases in AI systems could make it difficult to maintain data quality control in medical travel and tourism. Design/methodology/approach The systematic review of the literature from January 2019 to March 2025 (72 out of 925 articles) considers a variety of keyword combinations used for data quality control in AI systems. The process of systematic literature review aids in identifying studies on data quality management for medical tourism and travel. Findings The results of the study show that data quality visibility should be increased, data rectification should be done consistently and data momentum should be managed. It indicates that audience behavior in medical travel and tourism is significantly impacted by AI-powered digital branding and marketing. Research limitations/implications The research is limited to the single source of methodology, and it is limited in terms of articles collected from Jan 2019 to March 2025. It can be extended to the last decade for more insights and issues in AI use for medical travel and tourism. Practical implications Practical applications include efficient patient processing for international medical travel and tourism, as well as automated AI machine learning. Future research investigations should consistently segment data evaluation to overcome the limited regulatory compliance of data quality management. Social implications Patients (medical tourism) are primary elements in healthy social settings that can be facilitated through AI’s efficient use and maintaining the quality of the data management. Originality/value This study aims to address the main ethical concerns about the quality of AI data, data use monitoring and ethical support for data decisions and implementations inside the AI framework. The usage of digital branding, mobile app development, digital audience behavior, digital marketing principles and artificial intelligence in marketing are some of the important concepts used to accomplish the research goals.

Hemodialysis patients (HDPs) often experience depression, which negatively impacts their treatment adherence and quality of life. Drug therapy for depression in HDPs is often limited due to its effectiveness and drug safety concerns. Cognitive behavioral therapy (CBT) has emerged as a promising alternative. However, its delivery is hampered by various challenges, especially in this vulnerable population. We aimed to develop an innovative mobile application to overcome some of the challenges in delivering CBT for depression and evaluate its perceived usability among HDPs. This study was conducted in a nephrology department in a developing country between 2022 and 2023. Relevant topics were adapted into a CBT framework tailored to hemodialysis care and cultural context by a multidisciplinary expert panel including of a senior nephrologist with decades of clinical experience and a clinical psychologist before conversion into audio format for the application. Usability was assessed with 30 hemodialysis patients aged ≥ 18 years, receiving treatment for ≥ 3 months, with mild to moderate depression (Beck Depression Inventory short form (BDI-SF) score 5-15), owning Android smartphones, and possessing basic reading and writing literacy. This study focused on the development and usability evaluation of the application; clinical effectiveness was not assessed. Perceived usability was assessed using the Questionnaire for User Interface Satisfaction (QUIS). The hemodialysis-tailored CBT program comprised seven sessions aimed at addressing stress and depression in HDPs through skills such as goal setting, problem solving, and coping with negative emotions using language carefully developed and validated by clinical experts familiar with the needs and literacy levels of this population. The content was transformed into 26 audio episodes, each approximately 15min long, delivered via a user-friendly mobile app featuring educational CBT content, therapist communication, peer support, and reporting functions. Thirty HDPs participated in the usability evaluation; they were primarily aged 50 to 65 years, had predominantly elementary-level education, and more than one year of hemodialysis experience. They expressed high satisfaction, with an average usability score of 7.87 out of 9. The application achieved high usability scores among HDPs, supporting its feasibility and perceived usability as an audio-CBT delivery platform. These findings lay the groundwork for future studies to assess its clinical efficacy, cost-effectiveness, and role in providing psychological support in real-world care settings.

Evolution of the mobile app for early diagnosis and sustainable management of rice diseases

Correction to: Research Proposal for Mobile App Development to Achieve Color Balance in Home Interior Design

This research examines how digital marketing and mobile app development enable service innovation in German companies during the period of 2005- 2024. Using firm-level panel data from the Moody’s Orbis database, firm-level panel data examines the relationships between social media advertising expenses, mobile app features, educational campaigns, total customers, and the rate of active digital users (used to approximate service innovation). By applying a Random Effects panel regression model, findings indicate that social media advertising, mobile app functionality, educational campaigns, and total customers have a significant and positive influence on firms’ rate of digital innovation performance. Findings show that consistently investing in digital engagement strategies and technological capabilities increases firms’ ability to innovate services, acquire customers, and build competitiveness within the changing digital economy in Germany. The present study provides new firm-level evidence for the digital transformation literature, as it illustrates that marketing and mobile technology work together to drive service innovation in advanced economies.

Agile development methods have been proposed as a natural fit for mobile app development contexts. Despite many studies addressing the using of agile methods for traditional web and desktop applications, there is a lack of studies of how teams developing mobile apps can use agile methods and the difficulties they are facing. Our research examines this area to better understand how some representative industrial teams approach agile mobile app development, and the difficulties they are facing. We conducted a qualitative research involving four different mobile app development companies. Our research method is based on multiple-case research design. From our findings, we argue that not all agile development principals are necessarily applicable within the mobile app development context. Furthermore, teams developing mobile apps face additional difficulties when using agile methods such as development automation tools and on-line app store restrictions to mention a few.

Over the past decade, mobile devices have become an integral part of our daily routines, offering a broad spectrum of applications that enhance everyday tasks. As more people adopt smartphones, developers are increasingly focusing on improving app quality, particularly by incorporating artificial intelligence (AI) features. This growing trend has led to a surge of interest from both researchers and industry experts, who are aiming to explore AI integration in sectors such as healthcare, education, agriculture, and e-commerce. This study conducts a thorough review of AI applications on mobile platforms by analysing 98 scholarly articles published between 2014 and 2024 from databases including Scopus, IEEE Explore, and Science Direct. After screening for relevance, 50 articles were selected for in-depth evaluation. The findings show a significant emphasis on healthcare, which accounted for 38% of the reviewed studies, followed by agriculture at 30% and education at 18%. This advancement is in line with societal demands because AI-powered mobile apps improve vital industries like healthcare, agriculture, education, and corporate operations by offering predictive analytics. Notably, machine learning (ML) techniques were prominent, used in 66% of the articles, while deep learning (DL) appeared in 16%. The review also highlights convolutional neural networks (CNN) as a key algorithm, present in 56% of the studies. These insights demonstrate the profound influence of AI on mobile app development and point to emerging trends and future research opportunities in this field. The need for cross-platform AI development has increased dramatically as AI continues to transform mobile technology. This strategy is essential to the scalability, accessibility, and effectiveness of the larger mobile app ecosystem since AI-enabled apps are designed to function flawlessly across a variety of mobile operating systems (iOS, Android, etc.).

The rapid advancement of large language models (LLMs) for code generation has largely centered on English programming queries. This paper targets a low-resource language scenario, Turkish, in Flutter mobile app development. Two representative LLMs (a 4B-parameter multilingual model and a 3B code-specialized model) on a new Turkish question-and-answer dataset for Flutter/Dart are fine-tuned in this study. Fine-tuning with parameter-efficient techniques yields dramatic improvements in code generation quality: Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation (ROUGE-L), Metric for Evaluation of Translation with Explicit Ordering (METEOR), Bidirectional Encoder Representations from Transformers Score (BERTScore), and CodeBLEU scores show significant increases. The rate of correct solutions increased from ~30–70% (for base models) to 80–90% after fine-tuning. The performance trade-offs between models are analyzed, revealing that the multilingual model slightly outperforms the code-focused model in accuracy after fine-tuning. However, the code-focused model demonstrates faster inference speeds. These results demonstrate that even with very limited non-English training data, customizing LLMs can bridge the gap in code generation, enabling high-quality assistance for Turkish developers comparable to that for English. The dataset was released on GitHub to facilitate further research in multilingual code generation.