Search Results (338)

Physical inactivity is a major preventable cause of non-communicable disease and premature mortality. Mobile health interventions can promote physical activity, but their effectiveness depends on the ability to adapt to user’s context and motivation. Reinforcement learning (RL), particularly contextual bandits (CBs), offers a promising framework for such adaptive personalization. However, in practice, RL-based models face the cold start problem (CSP), due to the lack of initial training data. This study examines whether theory-driven simulated data can mitigate the CSP in training RL systems for personalized physical activity recommendations. A scoping review of 18 empirical studies on the Integrated Behavioral Change Model (IBC) provided population parameters for key constructs, used to simulate 2000 virtual users via multivariate modeling and structural equation calibration. A CB algorithm with an ε-greedy policy was trained with this dataset and compared with data from real world pilot using the Apptivate mHealth web-app (n = 588). Results showed close alignment between simulated and real behaviors. Our findings demonstrate that behaviorally informed synthetic data can effectively be used to train RL algorithms, offering an interpretable, sustainable, scalable, and privacy-safe solution to the CSP in personalized digital health interventions. Full article

The rapid expansion of mobile healthcare (mHealth) applications has transformed health-related e-commerce, creating new challenges for understanding and responding to user needs. This study proposes a data-driven framework to systematically identify and prioritize unmet user requirements from negative reviews of Chinese mHealth applications. Using a dataset of 31,124 user reviews collected between 2019 and 2025, the framework integrates sentiment analysis, topic modeling, and machine learning regression to uncover six key areas of user concern and examine their temporal evolution. Among several predictive models linking user concerns to app ratings, the k-nearest neighbors (KNN) model demonstrated superior performance. Subsequent SHAP-based interpretability analysis reveals that account authentication, system accessibility, and application stability have the most significant impact on user ratings, highlighting the critical roles of trust and technical reliability in health e-commerce. This research not only provides actionable insights for platform governance but also contributes a generalizable methodology for leveraging user-generated content to inform evidence-based management and policy decisions in mobile digital services. Full article

Ants are vital bioindicators that contribute to soil health and food webs, making accurate identification essential for biodiversity monitoring and conservation. However, traditional taxonomic methods are time-consuming and require specialized expertise, limiting large-scale data collection and public participation. This paper presents AntID_APP, a web-based application designed to support citizen scientists in Taiwan by enabling real-time, image-based detection and the identification of native ant genera. Fine-tuned YOLO models first detect ants in user-uploaded images and then classify them at the genus level. The models were trained on a curated dataset of 60,429 open-access images from iNaturalist, covering 54 native ant species. To ensure robustness in real-world conditions, we applied targeted data augmentation and evaluated multiple YOLO versions (v9–v12). The best-performing model achieved a mean Average Precision (mAP50: 0.935–0.948, mAP50-95: 0.777–0.807) for the detection task, followed by accurate genus-level identification. The application features an intuitive interface and a lightweight asynchronous server architecture, allowing users to upload images and receive both visual detection results (bounding boxes) and genus predictions efficiently. By combining high accuracy with accessibility, AntID_APP offers a scalable solution for biodiversity monitoring and public engagement in ecological research. Full article

The evolution of the mHealth era offers the possibility of behavioral interventions to promote changes in lifestyle habits with prevention relevance. These tools are considered digital therapeutics (DTx) and follow the MDR 745/2017 for testing, validation, and certification. In the frame of the ACTIVE3 project, we developed a platform composed of a mobile app, a wearable device, and a cloud backend to support healthy aging intervention in a population of 60–80-year-old subjects. This paper describes the clinical trial protocol and the baseline data of the recruited population. The explored parameters describe the effect of the DTx in the physical, nutritional (and metabolic), and cognitive domains, leveraging the Walking Group initiatives coordinated by ATS Brianza that are active in the Lecco area; in addition, system usability and acceptance were analyzed. The study started on 1 September 2024, and the analyzed baseline data are presented here. With respect to an expected population of 200 subjects, we received interest and consent to participate from 237 subjects: over-enrollment was allowed and all these subjects were accepted into the study. The characterization of the study population at the initial time of the trial was carried out, and the outcomes are presented here. The population is generally more active than Italian people of the same age. According to the outcome of the 6MWT, the population was divided into three groups: trained participants (42 subjects), active participants (142 subjects), and sedentary participants (58 subjects). The tests at month 12 were recently competed, and the final results will be available in winter 2025–2026. Full article

This cross-sectional study investigated the associations between the acute-phase proteins (APP) serum amyloid A (SAA) and haptoglobin (Hp), herd-level factors, and the seroprevalence of respiratory pathogens in Estonian dairy herds. Serum samples were analysed from 938 cows (95 herds) and 921 heifers (94 herds). Seroprevalence was tested for bovine herpesvirus 1 (BHV-1), bovine respiratory syncytial virus (BRSV), bovine parainfluenza virus 3, bovine viral diarrhoea virus, bovine coronavirus, bovine adenovirus, and Mycoplasma bovis (M. bovis). Farm visits included questionnaires on herd management practices. Linear random-intercept regression models showed higher serum SAA concentrations in cows from farms with BHV-1 seroprevalence of >50% and on BRSV-positive farms (p < 0.05), while farms employing a veterinarian had lower serum SAA concentrations. Cows had higher serum Hp concentrations in M. bovis-positive herds (p = 0.030). In heifers, serum SAA concentrations increased with low to moderate BHV-1 seroprevalence, decreased with higher M. bovis seroprevalence, and were higher in free-stall or mixed housing compared to tie-stall housing. Heifers’ serum Hp concentrations were lower in BHV-1-positive herds, but higher in herds with breeding bulls and larger herd sizes. To conclude, APP may reflect the herd health status and management-related effects on animals, supporting their use in herd-level monitoring. Full article

This study investigated the associations between acute-phase proteins (APPs) such as serum amyloid A (SAA), haptoglobin (Hp), and albumin (Alb) as well as immunoglobulin G (IgG) with bovine respiratory disease (BRD), seroconversion to respiratory infections and farm-level factors in rearing calves. Datasets were obtained from a randomised trial of 476 calves in Finland that compared morbidity in large- versus small-group housing. Calves were assessed for clinical BRD, and their blood was sampled three times during the first 50 rearing days to measure APPs and IgG concentrations and virus-specific antibodies against Mycoplasma bovis (M. bovis), bovine respiratory syncytial virus (BRSV), bovine parainfluenza virus 3 (BPIV3), and bovine coronavirus (BCV). Linear mixed-effects regression models showed higher serum SAA and Hp concentrations in calves with clinical BRD. BRSV seroconversion was associated with increased serum SAA and lower Alb while M. bovis seroconversion with increased serum Hp. Calves in larger groups had lower serum Hp, SAA and Alb, and pens with higher BRD cases were associated with increased serum SAA and lower Alb. IgG concentration was associated with BRSV seroconversion. These results suggest that early immune monitoring using APPs and IgG could help guide targeted management strategies to improve calf health and welfare. Full article

Background: Physical inactivity remains a major public health challenge, particularly for underserved populations lacking exercise facility access. AI-powered smartphone applications with real-time human pose estimation offer scalable solutions, but they lack rigorous clinical validation. Objective: This study validates the clinical efficacy of a 16-week on-device AI-driven resistance training program using MediaPipe pose estimation technology in young adults with limited facility access. Primary outcomes included muscular strength (1RM squat), body composition, functional movement (FMS), and cardiorespiratory fitness (VO₂max). Methods: A single-group pre–post study enrolled 216 participants (mean age 23.77 ± 4.02 years; 69.2% male), with 146 (67.6%) completing the protocol. Participants performed three 30 min weekly sessions of seven compound exercises delivered via a smartphone app providing real-time pose analysis (97.2% key point accuracy, 28.6 ms inference), multimodal feedback, and personalized progression using self-selected equipment. Results: Significant improvements across all domains: muscular strength (+4.39 kg 1RM squat, p < 0.001, d = 1.148), body fat (−2.92%, p < 0.001, d = −1.373), skeletal muscle mass (+2.19 kg, p < 0.001, d = 1.433), FMS (+0.29 points, p = 0.001, d = 0.285), and VO₂max (+1.82 mL/kg/min, p < 0.001, d = 0.917). Pose classification accuracy reached 95.8% vs. physiotherapist assessment (ICC = 0.94). Conclusions: This study provides the first clinical evidence that on-device AI pose estimation enables facility-independent resistance training with outcomes comparable to traditional programs. Unlike cloud-based systems, our lightweight model (28.6 ms inference) supports real-time mobile deployment, advancing accessible precision exercise medicine. Limitations include a single-arm design and gender imbalance, warranting future RCTs with diverse cohorts. Full article

Background/Objectives: Alzheimer’s disease (AD) is a progressive multifactorial neurodegenerative disorder. Current AD therapies offer minimal benefits and do not prevent or repair neuronal damage. More effective therapeutic approaches are needed to restore normal bioenergetics and metabolic function to AD neurons. Simufilam is a small-molecule oral drug that targets filamin A, a scaffolding protein in brain cells. Phase III clinical trials of simufilam failed to show any significant cognitive or functional improvements in AD patients. The purpose of this study is to identify and explain the molecular mechanisms that may have contributed to this drug’s lack of clinical success. Methods: Our study investigates the effects of simufilam on amyloid processing, neuronal health, and mitochondrial functioning in the SH-SY5Y human neuronal cell model. SH-SY5Y cells were differentiated into neurons using 10 µM retinoic acid. Undifferentiated and differentiated SH-SY5Y were exposed to simufilam (5 µM, 50 µM; 24 hr). Results: Simufilam did not affect the expression of genes involved in amyloid processing. Amyloid precursor protein (APP), β-secretase, and α-secretase mRNA levels in simufilam-treated SH-SY5Y cells were all unchanged compared to untreated cells. However, amyloidogenic β-secretase protein was significantly increased (fold change 1.17) at 50 µM of simufilam only in differentiated SH-SY5Y cells without affecting APP or α-secretase protein expression. Simufilam at the 50 µM concentration reduced brain-derived neurotrophic factor protein levels (fold change 0.7) only in differentiated SH-SY5Y. Further, simufilam did not improve mitochondrial genes or structure. Conclusions: Our results align with clinical outcomes and indicate that insufficient activity across multiple tests of ability to impact processes related to neuronal health can serve as a preliminary indicator of limited clinical utility. Full article

Digital Mental Health Interventions (DMHIs) offer a scalable solution to the global mental health crisis, yet their real-world impact is often hampered by low user engagement. Gamification has been widely adopted as a strategy to enhance adherence, but its implementation creates a complex and often unacknowledged “Engagement–Efficacy–Ethics Trilemma”. This systematic review synthesises the current literature to deconstruct this trilemma, arguing that an uncritical focus on maximising engagement can fail to improve—or may even undermine—clinical efficacy, while simultaneously introducing significant ethical risks. Our analysis reveals a persistent “Engagement–Efficacy Gap”, where increased usage of mobile health applications (mHealth apps) does not consistently translate to better therapeutic outcomes. Furthermore, we map the ethical landscape, identifying potential harms such as manipulation, psychological distress, and privacy violations that arise from persuasive design. The roles of Artificial Intelligence (AI) in personalising these experiences and Human–Computer Interaction (HCI) in mediating user responses are critically examined as key factors that both amplify and potentially mitigate the tensions of the trilemma. The findings indicate a pressing need for a paradigm shift toward an integrated approach that concurrently evaluates engagement, efficacy, and ethical integrity. We conclude by proposing a framework for responsible innovation, emphasising theory-driven design, co-design with users, and prioritising intrinsic motivation to harness the potential of gamified DMHIs safely and effectively. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a systematic search was conducted across Scopus, Web of Science, MEDLINE, and PsycINFO for studies published between 2015 and 2025. Full article

The widespread adoption of mobile health applications has increased the volume of sensitive personal and physiological data processed through interconnected devices. Ensuring privacy compliance in this context remains a challenge, as existing app stores and privacy labeling systems rely heavily on self-declared information. App-PI is a data-driven ecosystem designed to offer end users with tools they can easily manage and privacy researchers with structured and reliable app metadata. It is designed to automate the collection, analysis, and visualization of privacy-related metadata from mobile applications. Heterogeneous data sources are integrated into a unified repository (App-PIMD), enabling the empirical assessment of privacy risks. The data flow design is critical to ensure that the data used to assess privacy impact is of good quality, as well as the privacy indicators that end users will be offered. It is shown on a popular mHealth application, demonstrating the importance of data flow design in order to be able to obtain, from documents and files created for consumption by an operating system, a set of data and tools ready for consumption by the true recipients of health apps: people. Full article

Falls are a leading cause of morbidity and loss of independence among community-dwelling older adults. Mobile health (mHealth) application (app)-based interventions have emerged as a scalable approach to fall prevention. However, evidence from individual trials remains fragmented, underscoring the need for a comprehensive quantitative synthesis. This systematic review and meta-analysis examined whether mHealth app-based interventions reduce fall incidence and improve fall-related risk factors. A systematic search of PubMed, EMBASE, CENTRAL, and Web of Science identified randomized controlled trials meeting predefined eligibility criteria. Nine trials comprising 3437 participants were included, with dual-independent data extraction, quality appraisal, and assessment of evidence certainty. Compared with usual care or control conditions, mHealth app-based interventions reduced fall risk by 11% over 12 months (risk ratio 0.89, 95% CI 0.81–0.98), corresponding to an absolute risk reduction of 6.6%. The pooled reduction in fall rate, however, did not reach statistical significance. Secondary analyses showed moderate improvements in balance, strength, and mobility, a significant decrease in fear of falling, and no serious adverse events. Overall, mHealth app-based interventions provide modest but meaningful benefits and may complement comprehensive fall-prevention strategies for older adults. Full article

Background/Objectives: Up-to-date, relevant and detailed food composition databases (FCDs) are a central component of mHealth apps. Thus, the expansion and/or update of such FCDs though the aggregation of branded food data (BFCDs) could prove as a cost-efficient methodology. However, a framework for data aggregation from BFCDs has yet to be documented. Methods: Products (n = 3988) available in the HelTH BFCD were grouped following a three-step process. Firstly, foods were grouped based on their name, and then the aggregated nutritional composition was tested for heterogeneity using a coefficient of variation cut-off of 20% followed by a search of the ingredient list and other product characteristics to identify descriptors that reduced heterogeneity. Results: Following a three-step process, n = 347 new generic food names were proposed, each derived from at least three branded products, of which n = 235 were populated with aggregated nutritional content values. We found that 95.3%, 88.6%, 86% and 82.6% of aggregated energy, protein, carbohydrate and sodium values, respectively, had a coefficient of variation <40%. Aggregated saturated fatty acid and total sugar values were less likely to fall in the homogeneity level (76.3% and 65.3%, respectively). The heterogeneity was concentrated in specific subcategories like baked goods, milk products and milk imitation products, primarily. Conclusions: BFCDs can be used as a resource to expand existing databases with relatively homogeneous and up-to-date nutritional composition data. The application of this framework on larger datasets could improve the generic food name yield and homogeneity and support mHealth apps and other uses. Full article

The global rise in nursing home (NH) populations presents substantial challenges, as residents frequently experience physical and cognitive decline, low physical activity, and high fall risk. This study evaluates the effectiveness of the BeSt Age App, a tablet-based, staff-supported mHealth intervention designed to promote physical activity and prevent falls among NH residents. Primary outcomes were fall incidence and fall risk (assessed using Berg Balance Scale [BBS] and Timed Up and Go [TUG]); fear of falling was a secondary outcome. In a cluster-randomized controlled trial across 19 German NHs, 229 residents (mean age = 85.4 ± 7.4 years; 74.7% female) were assigned to an intervention group (IG) or control group (CG). The 12-week intervention comprised twice-weekly, tablet-guided exercise sessions implemented by NH staff. Mixed models and generalized estimating equations were used under an intention-to-treat framework. The IG showed significantly greater improvement in BBS scores than the CG (group × time: F(1, 190.81) = 8.25, p = 0.005, d = 0.22), while group × time changes in TUG performance, fear of falling, and fall incidence were nonsignificant. These findings demonstrate the feasibility of a staff-mediated mHealth approach to fall prevention in NH residents, showing significant improvements in BBS scores as one functional indicator of fall risk, while TUG, fall incidence and fear of falling showed no change. Full article

The rapid digitalization of healthcare has led to the widespread availability of mobile health (mHealth) applications, including those aimed at mental health and well-being. The present study followed the PRISMA guidelines and systematically reviewed English and/or German mental health apps available in the Google Play Store to evaluate their functional quality and behavior-change potential. It utilized the Mobile App Rating Scale (MARS) to assess app quality, including engagement, functionality, esthetics, and information quality, and the App Behavior Change Scale (ABACUS) to evaluate the potential for behavior change by inclusion of behavior change techniques (BCTs). A total of 77 apps were reviewed, with findings indicating an average functional quality and moderate behavior-change potential, as the reviewed apps only utilized a limited amount of BCTs. Notably, only a small fraction of apps had been evaluated in randomized controlled trials (RCTs). Further analysis showed that MARS and ABACUS scores had limited predictive power regarding app popularity as measured by stars awarded by users and number of user ratings in the Google Play Store. The study highlights the need for more rigorous testing of mHealth apps and suggests that factors beyond those measured by MARS and ABACUS may influence app popularity. In addition to the scientific value, this review provides insights for both users interested in mental health support via apps and developers aiming to enhance the quality and impact of mental health applications. Full article

Background/Objectives: Mobile health (mHealth) technologies are increasingly used to support preventive oral care and patient self-management. CarieCheck is a Portuguese app intended to improve oral health literacy and support caries-risk self-assessment. This prospective pilot study focused on users’ perceived app quality and usability, assessed with uMARS-PT. Methods: Thirty participants from the academic community of Egas Moniz School of Health and Science used the app for 30 days and completed the uMARS-PT questionnaire. Descriptive statistics were used to calculate mean scores for Engagement, Functionality, Aesthetics, Information Quality, Subjective Quality, and Perceived Impact. Results: The overall mean uMARS-PT score was 4.22, indicating excellent perceived quality. The highest domain scores were Functionality (4.51), Aesthetics (4.45), and Information Quality (4.22). Engagement (3.71) and Subjective Quality (3.05) were moderate. Perceived Impact (3.85) reflected self-reported perception of increased awareness and motivation regarding oral health behaviors. Conclusions: CarieCheck was rated highly in usability, aesthetics, and information quality. These findings suggest that CarieCheck may be considered as a digital tool for preventive education and user-supported caries-risk self-assessment. Larger, longer-term studies in diverse populations using objective behavioral and clinical outcomes are warranted. Full article