Frontiers in digital health最新文献

{"title":"Mobile health (mHealth) technologies for fall prevention among older adults in low-middle income countries: bibliometrics, network analysis and integrative review.","authors":"Michael Joseph Dino, Ladda Thiamwong, Rui Xie, Ma Kristina Malacas, Rommel Hernandez, Patrick Tracy Balbin, Joseph Carlo Vital, Jenica Ana Rivero, Vivien Wu Xi","doi":"10.3389/fdgth.2025.1559570","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1559570","url":null,"abstract":"<p><strong>Introduction: </strong>mHealth technologies offer promising solutions to reduce the incidence of falls among older adults. Unfortunately, publications on their application to Low-Middle Income Countries (LMIC) settings have not been collectively examined.</p><p><strong>Methods: </strong>A triadic research design involving bibliometrics, network analysis, and model-based integrative review was conducted to process articles (<i>n</i> = 22) from 629 publications extracted from major databases using keywords related to mHealth, falls prevention, and LMIC. The web-based application Covidence and stand-alone VosViewer software were used to process data following previously published review standards.</p><p><strong>Results: </strong>Published articles in the field feature multidisciplinary authorships from multiple scholars in the domains of health and technology. Network analysis revealed the most prominent stakeholders and keyword clusters related to mHealth technology features and applications in healthcare. The papers predominantly focused on the development of mHealth technology, usability, and affordances and less on the physiologic and sociologic attributes of technology use. mHealth technologies in low and middle-income countries are mostly smartphone-based, static, and include features for home care settings with fall detection accuracy of 86%-99.62%. Mixed reality-based mobile applications have not yet been explored.</p><p><strong>Conclusion: </strong>Overall, key findings and information from the articles highlight a gradually advancing research domain. Outcomes reinforce the need to expand the focus of mHealth investigations to include emerging technologies, update current technology models, create a more human-centered technology design, test mHealth technologies in the clinical setting, and encourage continued cooperation between and among researchers from various fields and environments.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1559570"},"PeriodicalIF":3.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11985854/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144042465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate.","authors":"Myranda Uselton Shirk, Catherine Dang, Jaewoo Cho, Hanlin Chen, Lily Hofstetter, Jack Bijur, Claiborne Lucas, Andrew James, Ricardo-Torres Guzman, Andrea Hiller, Noah Alter, Amy Stone, Maria Powell, Matthew E Pontell","doi":"10.3389/fdgth.2025.1552746","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1552746","url":null,"abstract":"<p><strong>Background: </strong>Hypernasality, a hallmark of velopharyngeal insufficiency (VPI), is a speech disorder with significant psychosocial and functional implications. Conventional diagnostic methods rely heavily on specialized expertise and equipment, posing challenges in resource-limited settings. This study explores the application of OpenAI's Whisper model for automated hypernasality detection, offering a scalable and efficient alternative to traditional approaches.</p><p><strong>Methods: </strong>The Whisper model was adapted for binary classification by replacing its sequence-to-sequence decoder with a custom classification head. A dataset of 184 audio recordings, including 96 hypernasal (cases) and 88 non-hypernasal samples (controls), was used for training and evaluation. The Whisper model's performance was compared to traditional machine learning approaches, including support vector machines (SVM) and random forest (RF) classifiers.</p><p><strong>Results: </strong>The Whisper-based model effectively detected hypernasality in speech, achieving a test accuracy of 97% and an F1-score of 0.97. It significantly outperformed SVM and RF classifiers, which achieved accuracies of 88.1% and 85.7%, respectively. Whisper demonstrated robust performance across diverse recording conditions and required minimal training data, showcasing its scalability and efficiency for hypernasality detection.</p><p><strong>Conclusion: </strong>This study demonstrates the effectiveness of the Whisper-based model for hypernasality detection. By providing a reliable pretest probability, the Whisper model can serve as a triaging mechanism to prioritize patients for further evaluation, reducing diagnostic delays and optimizing resource allocation.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1552746"},"PeriodicalIF":3.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11986712/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144013632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A call to action for adverse drug event (ADE) detection and prevention.","authors":"John McCue, C David Butler, Raymond C Love, Shelly Spiro, Roy Guharoy","doi":"10.3389/fdgth.2025.1507967","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1507967","url":null,"abstract":"<p><p>Injury from medication use, known as an adverse drug event (ADE) accounts for millions of emergency department visits globally and thousands of hospitalizations annually within the United States. Efforts to prevent and detect ADEs within healthcare systems are complicated by data quality, lack of data standardization, and actionable clinical decision support systems. United States Pharmacopeia (USP) proposes the use of an ADE value set, a standardized grouping of medical terms, to improve the identification, documentation, and use of ADE information in EHRs. Artificial Intelligence and Machine Learning capabilities would be further strengthened through the standardization of ADE data and information.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1507967"},"PeriodicalIF":3.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11986632/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning and artificial intelligence in type 2 diabetes prediction: a comprehensive 33-year bibliometric and literature analysis.","authors":"Mahreen Kiran, Ying Xie, Nasreen Anjum, Graham Ball, Barbara Pierscionek, Duncan Russell","doi":"10.3389/fdgth.2025.1557467","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1557467","url":null,"abstract":"<p><strong>Background: </strong>Type 2 Diabetes Mellitus (T2DM) remains a critical global health challenge, necessitating robust predictive models to enable early detection and personalized interventions. This study presents a comprehensive bibliometric and systematic review of 33 years (1991-2024) of research on machine learning (ML) and artificial intelligence (AI) applications in T2DM prediction. It highlights the growing complexity of the field and identifies key trends, methodologies, and research gaps.</p><p><strong>Methods: </strong>A systematic methodology guided the literature selection process, starting with keyword identification using Term Frequency-Inverse Document Frequency (TF-IDF) and expert input. Based on these refined keywords, literature was systematically selected using PRISMA guidelines, resulting in a dataset of 2,351 articles from Web of Science and Scopus databases. Bibliometric analysis was performed on the entire selected dataset using tools such as VOSviewer and Bibliometrix, enabling thematic clustering, co-citation analysis, and network visualization. To assess the most impactful literature, a dual-criteria methodology combining relevance and impact scores was applied. Articles were qualitatively assessed on their alignment with T2DM prediction using a four-point relevance scale and quantitatively evaluated based on citation metrics normalized within subject, journal, and publication year. Articles scoring above a predefined threshold were selected for detailed review. The selected literature spans four time periods: 1991-2000, 2001-2010, 2011-2020, and 2021-2024.</p><p><strong>Results: </strong>The bibliometric findings reveal exponential growth in publications since 2010, with the USA and UK leading contributions, followed by emerging players like Singapore and India. Key thematic clusters include foundational ML techniques, epidemiological forecasting, predictive modelling, and clinical applications. Ensemble methods (e.g., Random Forest, Gradient Boosting) and deep learning models (e.g., Convolutional Neural Networks) dominate recent advancements. Literature analysis reveals that, early studies primarily used demographic and clinical variables, while recent efforts integrate genetic, lifestyle, and environmental predictors. Additionally, literature analysis highlights advances in integrating real-world datasets, emerging trends like federated learning, and explainability tools such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations).</p><p><strong>Conclusion: </strong>Future work should address gaps in generalizability, interdisciplinary T2DM prediction research, and psychosocial integration, while also focusing on clinically actionable solutions and real-world applicability to combat the growing diabetes epidemic effectively.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1557467"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983615/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144042744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The gaps and challenges in digital health technology use as perceived by patients: a scoping review and narrative meta-synthesis.","authors":"Georgia Livieri, Eleni Mangina, Evangelos D Protopapadakis, Andrie G Panayiotou","doi":"10.3389/fdgth.2025.1474956","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1474956","url":null,"abstract":"<p><strong>Introduction: </strong>Digital health has revolutionized the landscape of healthcare through personalized care, moving away from the traditional approach of treating symptoms and conditions. Digital devices provide diagnostic accuracy and treatment effectiveness while equipping patients with control over their health and well-being. Although the growth of technology provides unprecedented opportunities, there are also certain issues arising from the use of such technology. This scoping review aimed to explore perceived gaps and challenges in the use of digital technology by patients and meta-synthesize them. Identifying such gaps and challenges will encourage new insights and understanding, leading to evidence-informed policies and practices.</p><p><strong>Methods: </strong>Three electronic databases were searched (Cinahl EBSCO, Pubmed, and Web of Science) for papers published in English between January 2010 and December 2023. A narrative meta-synthesis was performed. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) 2009 checklist.</p><p><strong>Results: </strong>A total of 345 papers were retrieved and screened, with a noticeable increase in publication numbers after 2015. After the final selection, a total of 28 papers were included in the final meta-synthesis; these were published between 2015 and 2023. A total of 99 individual reports were included in the synthesis of these papers, comprising 25 identified gaps and 74 challenges.</p><p><strong>Discussion: </strong>Our meta-synthesis revealed several gaps and challenges related to patients' use of digital technology in health, including generational differences in digital propensity and deficiencies in the work process. In terms of ethics, the lack of trust in technology and data ownership was highlighted, with the meta-synthesis identifying issues in the realm of disruption of human rights. We, therefore, propose building a model for ethically aligned technology development and acceptance that considers human rights a crucial parameter in the digital healthcare ecosystem.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1474956"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983460/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144025209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical performance of Hedia Diabetes Assistant bolus calculator for diabetes management: a real-world retrospective cohort study.","authors":"Kenney Fehrenkamp Pedersen, Anne Østerskov, Sabrina Mai Nielsen, Gkikas Karagkounis, Astrid Karnøe Knudsen","doi":"10.3389/fdgth.2025.1430744","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1430744","url":null,"abstract":"<p><strong>Introduction: </strong>Individuals living with type 1 diabetes are at risk of long-term complications related to chronic hyperglycemia. Tight glycemic control is recommended but can increase the risk of iatrogenic hypoglycemia. Hedia Diabetes Assistant (HDA) is a bolus calculator that provides users with bolus insulin recommendations based on personalized settings. We aimed to investigate the effects of HDA on a known risk index of hypoglycemia.</p><p><strong>Methods: </strong>New users from 2019 to 2021 were included if they fulfilled the following criteria: age ≥18 years, ≥5 logs/1st week of use, and ≥1 log for glucose, carbohydrate, and insulin. User data was extracted from the HDA database. The prespecified primary endpoint was change in the Low Blood Glucose Index (LBGI) after 12 weeks of use. Secondary endpoints were changes in the High Blood Glucose Index (HBGI) and eA1c. An exploratory endpoint was to maintain potential improvements in LBGI after 25 weeks. A repeated-measures mixed model with a log-transformation was used.</p><p><strong>Results: </strong>A total of 1,342 users were included. The mean age was 43.4 years (SD 14.7) with 52.3% being female. After 12 weeks, LBGI significantly improved from 0.73 to 0.61 (17% decrease, <i>P</i> < 0.001) with no significant changes in HBGI, and eA1c. From week 12 to 25, LBGI decreased from 0.61 to 0.55 (10%, <i>P</i> = 0.107).</p><p><strong>Conclusions: </strong>Users of HDA experienced statistically significant improvement in LBGI after 12 weeks with no changes in HBGI and eA1c, which was successfully maintained after 25 weeks. These results suggest a decreased risk of hypoglycemia when using HDA.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1430744"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144054649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the accuracy of Garmin PPG sensors on differing skin types based on the Fitzpatrick scale: cross-sectional comparison study.","authors":"Annie Icenhower, Claire Murphy, Amber K Brooks, Megan Irby, Kindia N'dah, Justin Robison, Jason Fanning","doi":"10.3389/fdgth.2025.1553565","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1553565","url":null,"abstract":"<p><strong>Background: </strong>Commercial wearable devices, which are often capable of estimating heart rate via photoplethysmography (PPG), are increasingly used in health promotion. In recent years, researchers have investigated whether the accuracy of PPG-measured heart rate varies based on skin pigmentation, focusing particularly on the accuracy of such devices among users with darker skin tones. As such, manufacturers of wearable devices have implemented strategies to improve accuracy. Given the ever-changing nature of the wearable device industry and the important health implications of providing accurate heart rate estimates for all individuals no matter their skin color, studies exploring the impact of pigmentation on PPG accuracy must be regularly replicated.</p><p><strong>Objective: </strong>We aimed to contrast heart rate readings collected via PPG using the Garmin Forerunner 45 in comparison with an electrocardiogram (ECG) during various levels of physical activity across a diverse group of participants representing a range of skin tones.</p><p><strong>Methods: </strong>Heart rate data were collected from adult participants (18-64 years of age) at a single study session using the Garmin Forerunner 45 PPG-equipped smartwatch and the Polar H10 ECG chest strap. Skin tone was self-reported via the Fitzpatrick scale. Each participant completed two 10 min bouts of moderate-intensity walking or jogging separated by a 10 min bout of light walking.</p><p><strong>Results: </strong>A series of mixed ANOVAs indicated no significant interaction between Fitzpatrick score and phase of the activity bout (i.e., rest at the start, first intensity ramp-up phase, first steady-state phase, active rest, second ramp-up phase, and second steady-state phase). Similarly, there was no significant main effect for the Fitzpatrick score, although there was a significant main effect for phase, which was driven by greater ECG-recorded heart rate relative to PPG during the first ramp-up phase.</p><p><strong>Conclusion: </strong>Our findings support prior research demonstrating no significant impact of skin tone on PPG-measured heart rate, with significant differences between PPG- and ECG-measured heart rate emerging during dynamic changes in activity intensity. As commercial heart rate monitoring technology and software continue to evolve, it will be vital to replicate studies investigating the impact of skin tone due to the rapidity with which widely used wearable technologies advance.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1553565"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983641/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144047612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal patterns of multiple long-term conditions in individuals with intellectual disability living in Wales: an unsupervised clustering approach to disease trajectories.","authors":"Rania Kousovista, Georgina Cosma, Emeka Abakasanga, Ashley Akbari, Francesco Zaccardi, Gyuchan Thomas Jun, Reza Kiani, Satheesh Gangadharan","doi":"10.3389/fdgth.2025.1528882","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1528882","url":null,"abstract":"<p><strong>Introduction: </strong>Identifying and understanding the co-occurrence of multiple long-term conditions (MLTCs) in individuals with intellectual disability (ID) is crucial for effective healthcare management. Individuals with ID often experience earlier onset and higher prevalence of MLTCs compared to the general population, however, the specific patterns of co-occurrence and temporal progression of these conditions remain largely unexplored. This study presents an innovative unsupervised approach for examining and characterising clusters of MLTC in individuals with ID, based on their shared disease trajectories.</p><p><strong>Methods: </strong>Using a dataset of electronic health records (EHRs) from 13,069 individuals with ID, encompassing primary and secondary care data in Wales from 2000 to 2021, this study analysed the time sequences of disease diagnoses. Significant pairwise disease associations were identified, and their temporal directionality assessed. Subsequently, an unsupervised clustering algorithm-spectral clustering-was applied to the shared disease trajectories, grouping them based on common temporal patterns.</p><p><strong>Results: </strong>The study population comprised 52.3% males and 47.7% females, with a mean of 4.5 <math><mo>±</mo></math> 3 long-term conditions (LTCs) per patient. Distinct MLTC clusters were identified in both males and females, stratified by age groups (<45 and <math><mo>≥</mo></math> 45 years). For males under 45, a single cluster dominated by neurological conditions (32.4%), while three clusters were identified for older males, with the largest characterised by circulatory (51.8%). In females under 45, one cluster was found with digestive system conditions (24.6%) being most prevalent. For females <math><mo>≥</mo></math> 45 years, two clusters were identified: the first cluster was predominantly defined by circulatory (34.1%), while the second cluster by digestive (25.9%) and musculoskeletal (21.9%) system conditions. Mental illness, epilepsy, and reflux disorders were prevalent across all groups.</p><p><strong>Discussion: </strong>This study reveals complex multimorbidity patterns in individuals with ID, highlighting age and sex differences. The identified clusters provide new insights into disease progression and co-occurrence in this population. These findings can inform the development of targeted interventions and risk stratification strategies, potentially improving personalised healthcare for individuals with ID and MLTCs with the aim of improving health outcome for this vulnerable group of patients i.e. reducing frequency and length of hospital admissions and premature mortality.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1528882"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983499/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144063443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effect of WhatsApp-based reminders on enhancing knowledge and adherence to weekly iron-folic acid supplementation among adolescent girls in Maluku, Indonesia.","authors":"Mega Clarita Laurence, Christiana Rialine Titaley, Ritha Tahitu, Elpira Asmin, Nathalie Elischeva Kailola, Sean Semuel Istia, Yudhie Djuhastidar Tando, Lershito Antonio Pasamba, Liyani Sartika Sara","doi":"10.3389/fdgth.2025.1542006","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1542006","url":null,"abstract":"<p><strong>Introduction: </strong>Anemia continues to be a problem among adolescent girls, including in Indonesia. Although the Weekly Iron-Folic Acid Supplementation (WIFAS) program was introduced in 2014, adherence remains a challenge. The study aimed to evaluate the effectiveness of WhatsApp (WA) reminder messages in improving knowledge and adherence to WIFAS among adolescent girls in the Salahutu Sub-District, Maluku Province.</p><p><strong>Methods: </strong>A quasi-experimental design was employed in 2024, utilizing a pretest-posttest control group framework across two senior high schools in Salahutu Sub-District. The intervention school (<i>n</i> = 49) received WA-based reminder messages for four weeks, while the control school (<i>n</i> = 42) continued to receive routine services. We used Mann-Whitney, Fisher Exact and chi-square tests in this analysis.</p><p><strong>Results: </strong>The WA-based intervention led to a significant improvement in knowledge scores among adolescent girls from the intervention school (<i>p</i> <i><</i> <i>0.001</i>). These students were also more likely to have taken WIFAS in the week preceding the endline survey (<i>p</i> <i><</i> <i>0.001</i>) and to have consumed at least 75% of the distributed WIFAS (<i>p</i> <i>=</i> <i>0.015</i>) compared to the control school. Furthermore, the mean hemoglobin levels were significantly higher in the intervention compared to the control school (<i>p</i> <i>=</i> <i>0.001</i>).</p><p><strong>Conclusions: </strong>The WA-based reminder messages were effective in enhancing knowledge and adherence to WIFAS. Expanding this approach to a broader population is recommended before scaling up implementation across Maluku and other regions in Indonesia.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1542006"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983285/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144051621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DATA 5.0-Data Acquisition, Translation & Analysis-a prospective urooncological data warehouse for the 21st century.","authors":"Viktoria Schütz, Christine Geisler, Mathias Rath, Sarah Böning, Thomas Treber, Albrecht Stenzinger, Alexander Brobeil, Oliver Reinhard, Anette Duensing, Stefan Duensing, Markus Hohenfellner, Magdalena Görtz","doi":"10.3389/fdgth.2025.1530321","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1530321","url":null,"abstract":"<p><strong>Background: </strong>Prospective data registration is the basis of clinical oncological research. Commonly, case documentation is restricted to studies investigating a defined hypothesis. Only few institutions prospectively register all oncological patients with a reliable, sustainable and continuous follow-up infrastructure. The Department of Urology of the Heidelberg University Hospital started its prospective tumor data base in 1992. Since then, the clinical course of all oncological in-patients is continuously registered within a life-long follow-up (success rate: 93%). Associated tumor tissue is stored in the Heidelberg Biobank. In 2005, the transfer of this invaluable registry from the initial InterSystemsCache®/KRAZTUR system to a modern data warehouse was initiated. However, the transfer of existing data into a new environment proved to be technically challenging.</p><p><strong>Objective: </strong>To migrate the existing data into a modern data warehouse (DATA 5.0) while maintaining data extraction functions. Additional requirements included FHIR connectivity, big data analyses and AI applications.</p><p><strong>Methods: </strong>Together with SAP SE, DATA 5.0 was developed. Based on SAP HANA® (High Performance Analytic Appliance) it allows data registration and analysis with third party analytical tools. The project was supported by members of the SAP SE executive board and funded by the Dietmar Hopp Foundation.</p><p><strong>Results: </strong>Data Acquisition, Translation & Analysis 5.0 (DATA 5.0), a web-based tool for data registration, preservation and analysis of treatment and follow-up data, was developed to proof-of-concept stage. DATA 5.0 was then implemented into clinical practice replacing the previous system. As of today, 15,345 oncological patients and 6.7 Mio. data points are registered.</p><p><strong>Conclusion: </strong>Prospective long-term data was successfully migrated into DATA 5.0, allowing data preservation, flexibility and capabilities for future data sources. DATA 5.0, together with associated tumor tissue, is a lighthouse platform for oncological research, with capability for third party analytical tools, big data analysis and AI applications including training of digital twin models.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1530321"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983565/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}