Frontiers in digital health最新文献

{"title":"Acceptance of a mental health app (JoyPop^TM) for postsecondary students: a prospective evaluation using the UTAUT2.","authors":"Ishaq Malik, Aislin R Mushquash","doi":"10.3389/fdgth.2025.1503428","DOIUrl":"10.3389/fdgth.2025.1503428","url":null,"abstract":"<p><strong>Introduction: </strong>Mental health (MH) smartphone applications (MH apps) can support the increasing MH needs of postsecondary students and mitigate barriers to accessing support. Evaluating MH app acceptance using technology acceptance models is recommended to improve student engagement with MH apps. The JoyPop^TM app was designed to improve youth resilience and emotion regulation. The JoyPop^TM app is associated with improved student MH, but its acceptance has yet to be evaluated quantitatively. The present study used the Unified Theory of Acceptance and Use of Technology (UTAUT2) to evaluate and examine constructs and moderators influencing the acceptance (i.e., behavioural intention) and use of the JoyPop^TM app.</p><p><strong>Method: </strong>Participants were 183 postsecondary students attending a Canadian University who used the app for one week and completed measures before and after using the app. Relationships posited by the UTAUT2 were tested using partial least squares structural equation modelling (PLS-SEM).</p><p><strong>Results: </strong>Most participants accepted the JoyPop^TM app. The UTAUT2 model explained substantial variance in behavioural intention and app use. Performance expectancy, hedonic motivation, and facilitating conditions predicted behavioural intention, and behavioural intention and facilitating conditions predicted app use. Age moderated the association between facilitating conditions and behavioural intention. Experience moderated the relationship between performance expectancy, hedonic motivation, and social influence on behavioural intention.</p><p><strong>Discussion: </strong>Results provide insight into factors influencing the acceptance of the JoyPop^TM app and its ability to engage students. Results also provide valuable insights for evaluating and optimally designing MH apps.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1503428"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876143/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560349","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":"Virtual reality for training emergency medicine residents in emergency scenarios: usefulness of a tutorial to enhance the simulation experience.","authors":"A Vittadello, S Savino, S Bressan, M Costa, A Boscolo, N Sella, T Pettenuzzo, F Zarantonello, A De Cassai, T Chang, P Navalesi, G Mormando","doi":"10.3389/fdgth.2025.1466866","DOIUrl":"10.3389/fdgth.2025.1466866","url":null,"abstract":"<p><strong>Introduction: </strong>Critical events in healthcare require a rapid and coordinated approach: simulation has been demonstrated a valid technique for training in emergency. Virtual Reality (VR) is an innovative technology that has revolutionized simulation training and healthcare professional development. A key phase of a simulation session with manikin consists in a familiarization with setting and equipment. The primary objective of this study is to investigate whether familiarization with a VR tutorial can change the perception of cases.</p><p><strong>Methods: </strong>Emergency medicine residents were randomly assigned to the Intervention group (n = 21) who undergone familiarization tutorial prior to the clinical scenario to a Control group (<i>n</i> = 21) where no familiarization tutorial was provided before the clinical scenario.</p><p><strong>Results: </strong>No significant differences were found between the two groups regarding perceived ease of use, but the Intervention group found VR familiarization useful and the Control group found it necessary to implement a VR tutorial. VR training was generally perceived by learners as a useful technology for training as confirmed by the literature.</p><p><strong>Discussion: </strong>Familiarization seems to be an important phase of simulation-based training for trainees, even when running a VR-based simulation for an emergency scenario; it should be incorporated into the clinical VR sessions for simulation in healthcare settings.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1466866"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876424/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143558433","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":"Assessing accuracy of BiliPredics algorithm in predicting individual bilirubin progression in neonates-results from a prospective multi-center study.","authors":"Britta Steffens, Gilbert Koch, Corinna Engel, Axel R Franz, Marc Pfister, Sven Wellmann","doi":"10.3389/fdgth.2025.1497165","DOIUrl":"10.3389/fdgth.2025.1497165","url":null,"abstract":"<p><strong>Background: </strong>Neonatal jaundice affects more than half of neonates. As bilirubin values usually peak few days after hospital discharge, jaundice remains a leading cause of rehospitalization. The recently developed BiliPredics algorithm, integrated in the first CE-approved bilirubin prediction tool, predicts individual bilirubin progression for up to 60 h into the future. Goal of the prospective study was to assess accuracy of this algorithm in predicting individual bilirubin prior to hospital discharge in neonates.</p><p><strong>Methods: </strong>A prospective multi-center study was conducted in 2021 at the University Children's Hospitals in Tübingen and Regensburg, Germany. Various scenarios differing in type and number of bilirubin measurements and in prediction horizon were tested. Primary objective was prediction accuracy of the BiliPredics algorithm based on total serum bilirubin (TSB) measurements or based on transcutaneous bilirubin (TcB) measurements alone. Secondary objective was prediction accuracy based on combinations of TSB and TcB measurements. For assessment of accuracy, two validation metrics, absolute prediction error <math><mo>(</mo> <mrow><mi>a</mi> <mi>P</mi> <mi>E</mi></mrow> <mo>)</mo></math> and relative prediction error <math><mo>(</mo> <mrow><mi>r</mi> <mi>P</mi> <mi>E</mi></mrow> <mo>)</mo></math> , and two clinical acceptance conditions, margin of error of the 95%-confidence interval (95%-CI) and percentage of clinically relevant mis-predictions defined as <math><mi>a</mi> <mi>P</mi> <mi>E</mi> <mo>></mo> <mn>85</mn> <mspace></mspace> <mspace></mspace> <mi>μ</mi> <mrow><mi>mol</mi> <mo>/</mo> <mi>L</mi></mrow> </math> , were investigated.</p><p><strong>Results: </strong>Out of 455 enrolled neonates, 276 neonates met bilirubin inclusion criteria and were included in the analyses. Irrespective from tested prediction horizons, median <math><mi>r</mi> <mi>P</mi> <mi>E</mi></math> was small (8.5% to 9.5%) utilizing TSB measurements for up to 30 and 60 h and slightly higher (13.8%) utilizing TcB measurements for up to 48 h. The same applied for median <math><mi>a</mi> <mi>P</mi> <mi>E</mi></math> . Both clinical acceptance conditions were fulfilled across tested scenarios. Results for combined TSB-TcB scenarios up to a prediction horizon of 48 h without adjustment for type of measurement were comparable to TSB and TcB scenarios fulfilling both clinical acceptance conditions.</p><p><strong>Conclusion: </strong>Results from this prospective study in neonates confirm that the BiliPredics algorithm accurately predicts bilirubin progression up to 60 h with TSB measurements and up to 48 h with TcB or combined TSB-TcB measurements. As such, prediction tools utilizing this algorithm are expected to facilitate and safely optimize jaundice risk assessment at hospital discharge with the potential to reduce jaundice-related rehospitalizations.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1497165"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11878101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560352","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 impact of Internet-based healthcare derived from the COVID-19 pandemic on outpatients in a cardiology department.","authors":"Jie Liu, Yunhan Fei, Ying Gao, Yu Meng, Dongxue Huang, Wenjuan Zhao, Keliang Xie","doi":"10.3389/fdgth.2025.1475422","DOIUrl":"10.3389/fdgth.2025.1475422","url":null,"abstract":"<p><strong>Objective: </strong>This study examines the impact of a COVID-19 pandemic-derived online medical service on cardiovascular patient visits and assesses whether these services can ease the strain on medical resources.</p><p><strong>Method: </strong>This study investigated the impact of the COVID-19 pandemic on cardiology services and hospital operations. We analyzed key primary medical indicators in cardiology, including outpatient visits, inpatient improvement rates, cure rates, and mortality rates, over three years from 2019 to 2021. Furthermore, the study assessed the influence of the development of Internet-based medical services on the treatment of cardiovascular disease. Specifically, we compared the changes in the number of outpatient visits in four categories of offline outpatient clinics in the Department of Cardiology during two phases: Phase I (1 February 2019 to 28 February 2020) and Phase II (1 March 2020 to 28 February 2021).</p><p><strong>Results: </strong>Compared to the period before online services (T1), the second stage (T2) saw a significant decrease in total offline and general clinic visits. After the establishment of the online clinic, the third period (P3) showed a significant reduction in total offline, general, and senior clinic visits compared to the first period (P1), while vice-senior and VIP/international clinic visits increased. The number of online clinic visits and VIP/international clinic visits continued to rise. Online consultations had the highest proportion (55.9%), while prescriptions and examinations had the lowest (3.3%), although they showed a gradually increasing trend. After the implementation of the online clinic, the improvement rate of patients' conditions increased and the mortality rate decreased.</p><p><strong>Conclusion: </strong>Since the advent of online medical services, cardiovascular patients have increasingly opted for online diagnosis and treatment. Since March 2021, the online outpatient service has driven the overall growth in hospital outpatient numbers while maintaining medical quality. The primary use of the online medical service is for consultations, which shortens medical time and reduces implicit costs for patients.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1475422"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876138/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560361","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":"Developing and testing tele-support psychotherapy using mobile phones for depression among youth in Kampala district, Uganda: study protocol for a pilot randomized controlled trial.","authors":"Etheldreda Nakimuli-Mpungu, Jeremiah Mutinye Kwesiga, John Mark Bwanika, Davis Musinguzi, Caroline Nakanyike, Jane Iya, Sabrina Bakeera Kitaka, Benedict Akimana, Charlotte Hawkins, Patricia Cavazos, Jean B Nachega, Edward J Mills, Musisi Seggane","doi":"10.3389/fdgth.2025.1515193","DOIUrl":"10.3389/fdgth.2025.1515193","url":null,"abstract":"<p><strong>Introduction: </strong>In the post-COVID-19 era, depressive disorders among youth have risen significantly, creating an urgent need for accessible, cost-effective mental health interventions. This study adapts Group Support Psychotherapy into Tele-Support Psychotherapy (TSP) via mobile phones. It aims to evaluate its feasibility, acceptability, effectiveness, and cost-efficiency in addressing mild to moderate depression among youth in central Uganda.</p><p><strong>Methods and analysis: </strong>This study will use a mixed-methods approach, starting with a qualitative phase to adapt Group Support Psychotherapy into Tele-Support Psychotherapy (TSP) via mobile phones. Guided by ecological theories and the Unified Theory of Acceptance and Use of Technology (UTAUT), focus group discussions and interviews with youth, mental health professionals, and stakeholders will inform the development of a youth-tailored call platform integrated into Rocket Health Africa's telehealth services. Data will be analyzed using grounded theory and MAXQDA Analytics Pro 2022 to guide intervention adaptation. An open-label randomized controlled trial will enroll 300 youth (15-30 years) with mild to moderate depression from Kampala, Uganda, to evaluate Tele-Support Psychotherapy (TSP). Participants will be randomized to TSP with standard mental health services (SMHS) or SMHS alone. Primary outcomes include feasibility and acceptability, with secondary outcomes assessing cost-effectiveness, depressive symptom changes, and social support. Intention-to-treat analysis using structural equation modeling will evaluate treatment effects, complemented by qualitative insights into implementation barriers and facilitators.</p><p><strong>Discussion: </strong>This study protocol develops and evaluates Tele-Support Psychotherapy (TSP) for youth depression in resource-limited settings, addressing mental health gaps exacerbated by COVID-19. Using user-centered design and mixed methods, it explores TSP's feasibility, adaptability, and cost-effectiveness while addressing barriers like technology literacy, laying the groundwork for accessible digital mental health solutions.</p><p><strong>Trial registration: </strong>PACTR202201684613316.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1515193"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560360","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":"Adaptation of a digital health intervention for rural adults: application of the Framework for Reporting Adaptations and Modifications-Enhanced.","authors":"Maura M Kepper, Callie Walsh-Bailey, Loni Parrish, Ainsley Mackenzie, Lisa M Klesges, Peg Allen, Kia L Davis, Randi Foraker, Ross C Brownson","doi":"10.3389/fdgth.2025.1493814","DOIUrl":"10.3389/fdgth.2025.1493814","url":null,"abstract":"<p><strong>Introduction: </strong>Adaptation is a key aspect of implementation science; interventions frequently need adaptation to better fit their delivery contexts and intended users and recipients. As digital health interventions are rapidly developed and expanded, it is important to understand how such interventions are modified. This paper details the process of engaging end-users in adapting the PREVENT digital health intervention for rural adults and systematically reporting adaptations using the Framework for Reporting Adaptations and Modifications-Enhanced (FRAME). The secondary objective was to tailor FRAME for digital health interventions and to document potential implications for equity.</p><p><strong>Methods: </strong>PREVENT's adaptations were informed by two pilot feasibility trials and a planning grant which included advisory boards, direct clinic observations, and qualitative interviews with patients, caregivers, and healthcare team members. Adaptations were catalogued in an Excel tracker, including a brief description of the change. Pilot coding was conducted on a subset of adaptations to revise the FRAME codebook and generate consensus. We used a directed content analysis approach and conducted a secondary data analysis to apply the revised FRAME to all adaptations made to PREVENT (<i>n</i> = 20).</p><p><strong>Results: </strong>All but one adaptation was planned, most were reactive (versus proactive), and all adaptations preserved fidelity to PREVENT. Adaptations were made to content and features of the PREVENT tool and may have positive implications for equity that will be tested in future trials.</p><p><strong>Conclusion: </strong>Engaging rural partners to adapt our digital health tool prior to implementation with rural adults was critical to meet the unique needs of rural, low-income adult patients, fit the rural clinical care settings, and increase the likelihood of generating the intended impact among this patient population. The digital health expansion of FRAME can be applied prospectively or retrospectively by researchers and practitioners to plan, understand, and characterize digital health adaptations. This can aid intervention design, scale up, and evaluation in the rapidly expanding area of digital health.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1493814"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876167/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560351","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":"Bridging language barriers in healthcare: a patient-centric mobile app for multilingual health record access and sharing.","authors":"Theodoros Solomou, Stelios Mappouras, Efthyvoulos Kyriacou, Ioannis Constantinou, Zinonas Antoniou, Ionut Cristian Canciu, Marios Neophytou, Zoltan Lantos, Christos N Schizas, Constantinos S Pattichis","doi":"10.3389/fdgth.2025.1542485","DOIUrl":"10.3389/fdgth.2025.1542485","url":null,"abstract":"<p><strong>Introduction: </strong>Access to health data for patients is hindered by a fragmented healthcare system and the absence of unified, patient-centric solutions. Additionally, there are no mechanics for easy sharing of medical records with healthcare providers, risking incomplete diagnoses. To further intensify the problem, when patients seek care abroad, language barriers may prevent foreign doctors from understanding their health data, further complicating treatment.</p><p><strong>Methods: </strong>Our study presents the development and evaluation of a mobile application designed to enable users to access and share their health records directly from their device, in multiple languages, ensuring ease of use and convenience. The solution utilizes OpenNCP for translating patient summaries into multiple languages and the FHIR Smart Health Links Protocol for secure sharing. We conducted a user acceptance study with 45 participants to evaluate our mobile app's interface and functionality.</p><p><strong>Results: </strong>The feedback was positive, highlighting the app's user-friendliness and usefulness. The participants felt it would enhance communication between physicians and patients and the features of sharing and translating are going to give more control of their medical data to the patients.</p><p><strong>Discussion: </strong>Based on the results and participants feedback, our mobile solution significantly enhances healthcare accessibility and efficiency by enabling easy access and sharing of health records in multiple languages, using relevant protocols and standards, reducing medical errors and ensuring personalized care.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1542485"},"PeriodicalIF":3.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876183/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560353","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":"Evaluating working memory in young individuals with normal hearing through tele-assessment and traditional assessment: a comparative study.","authors":"Kavassery Venkateswaran Nisha, N Devi, B Vandana, E Rashmi, Shraddha A Shende, Raksha A Mudar","doi":"10.3389/fdgth.2025.1499737","DOIUrl":"10.3389/fdgth.2025.1499737","url":null,"abstract":"<p><strong>Aim: </strong>This pilot study examined the feasibility of tele-assessment of working memory (WM) compared to conventional face-to-face assessment.</p><p><strong>Methods: </strong>In total, 15 young adults aged between 18 and 30 years who were native speakers of Kannada with normal hearing completed three WM tests in Indian English: forward digit span, backward digit span, and n-back task through tele-assessment and in-person/face-to-face assessment. The National Aeronautics and Space Administration (NASA) task load index, which assesses subjective workload, was used to determine the difficulties across the two modes of assessment.</p><p><strong>Results: </strong>Paired comparison <i>t</i>-tests showed no significant differences in performance in the forward digit span (<i>p</i> = 0.29), backward digit span (<i>p</i> = 0.71), and n-back (<i>p</i> = 0.66) tasks across the two assessment conditions. Furthermore, the NASA task load index did not differ across the two assessment conditions for forward digit span (<i>p</i> = 0.29), backward digit span (<i>p</i> = 0.71), and n-back (<i>p</i> = 0.66). The Wilcoxon signed-rank test showed that the backward digit span task was the most difficult among the working memory tasks in both modes of assessment. The findings of our pilot study suggest that both modes can be used successfully to assess working memory, and tele-assessment yields similar results to face-to-face WM assessment in young normal-hearing adults. These results support the feasibility of conducting WM tests via tele-assessment, which has implications for use in clinical populations.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1499737"},"PeriodicalIF":3.2,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11873067/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143544743","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":"Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning.","authors":"Emeka Abakasanga, Rania Kousovista, Georgina Cosma, Ashley Akbari, Francesco Zaccardi, Navjot Kaur, Danielle Fitt, Gyuchan Thomas Jun, Reza Kiani, Satheesh Gangadharan","doi":"10.3389/fdgth.2025.1538793","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1538793","url":null,"abstract":"<p><strong>Purpose: </strong>Individuals with learning disabilities (LD) often face higher rates of premature mortality and prolonged hospital stays compared to the general population. Predicting the length of stay (LOS) for patients with LD and multiple long-term conditions (MLTCs) is critical for improving patient care and optimising medical resource allocation. However, there is limited research on the application of machine learning (ML) models to this population. Furthermore, approaches designed for the general population often lack generalisability and fairness, particularly when applied across sensitive groups within their cohort.</p><p><strong>Method: </strong>This study analyses hospitalisations of 9,618 patients with LD in Wales using electronic health records (EHR) from the SAIL Databank. A Random Forest (RF) ML model was developed to predict hospital LOS, incorporating demographics, medication history, lifestyle factors, and 39 long-term conditions. To address fairness concerns, two bias mitigation techniques were applied: a post-processing threshold optimiser and an in-processing reductions method using an exponentiated gradient. These methods aimed to minimise performance discrepancies across ethnic groups while ensuring robust model performance.</p><p><strong>Results: </strong>The RF model outperformed other state-of-the-art models, achieving an area under the curve of 0.759 for males and 0.756 for females, a false negative rate of 0.224 for males and 0.229 for females, and a balanced accuracy of 0.690 for males and 0.689 for females. Bias mitigation algorithms reduced disparities in prediction performance across ethnic groups, with the threshold optimiser yielding the most notable improvements. Performance metrics, including false positive rate and balanced accuracy, showed significant enhancements in fairness for the male cohort.</p><p><strong>Conclusion: </strong>This study demonstrates the feasibility of applying ML models to predict LOS for patients with LD and MLTCs, while addressing fairness through bias mitigation techniques. The findings highlight the potential for equitable healthcare predictions using EHR data, paving the way for improved clinical decision-making and resource management.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1538793"},"PeriodicalIF":3.2,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11868268/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143544777","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":"What social media analyses can tell us about Ghanaian women's concerns during pregnancy.","authors":"Martina Anto-Ocrah, Tori Valachovic, Joseph W Lanning, Ali Ghanem, Claire Couturier, Celestin Hakizimana, Celestin Niyomugabo, Nabeeha Jabir Affan, Hemika Vempalli, Ruth Sally Kodam","doi":"10.3389/fdgth.2025.1479392","DOIUrl":"10.3389/fdgth.2025.1479392","url":null,"abstract":"<p><strong>Introduction: </strong>Social media platforms are used by over 4.9 billion people for networking and community building, as well as for healthcare information seeking and decision-making. Most studies investigating the utilization of social media during pregnancy have focused on high-income countries, despite the surge in social media utilization globally. In this study, we analyzed how pregnant women in Ghana, West Africa, utilize Facebook to inform decision-making on their most salient pregnancy concerns.</p><p><strong>Methods: </strong>We utilized machine learning techniques (Web Scraping and Latent Dirichlet Allocation) to mine and analyze posts from the Ghana-based MidWife Sally Pregnancy School Facebook group between August 16, 2020 and April 29, 2023. Posts were extracted, cleaned, and analyzed using Gensim python library. Topics were generated based on their probabilities and relevance to the study goal.</p><p><strong>Results: </strong>A total of 3,328 posts were extracted and 3,322 were analyzed after removing 6 empty posts. Seven major topics with listed subtopics were identified: Pregnant (693 posts): personal physiological changes, exercise during pregnancy, medication (e.g., anti-malarials, pain killers) Delivery (367): emergency delivery, vaginal/caesarean birthing, breastmilk production, exercise during pregnancy Pain (350): location of pain and pain relief modalities (e.g., exercise, medication, sleep) Breastfeeding (248): delivery, emergency service, milk production Water (174): cold water consumption, infant feeding (e.g., gripe water, constipation, formula) Sleeping (165): discomfort, sleeping positions, exercise to induce sleep, sleep as a natural analgesic Antenatal (124): fetal growth, progress, hospital selection Of note, content from \"Pregnant\", \"Delivery\" and \"Sleeping\" included mentions of depression, while \"Breastfeeding\" highlighted cultural approaches to increasing milk production. The sentiment analysis showed that 43.4% of the responses were neutral and primarily focused on seeking information. Negative sentiments, which were more distressing, comprised 46.4% of the responses, while positive sentiments, had a celebratory tone and represented 10.2% of the data.</p><p><strong>Conclusion: </strong>Social media analysis, previously employed in high income settings, can provide impactful, granular snapshots of pregnant people's concerns in the African region, which could be used to inform social media interventions aimed at filling educational gaps in antenatal care for those without adequate healthcare access.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1479392"},"PeriodicalIF":3.2,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11865226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143525479","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}