DIGITAL HEALTH最新文献

Objective: The successful transition of a digital platform from a research institution to a government system in under-resourced environments necessitates effective cooperation among various stakeholders and a strong sense of responsibility from both the Malawi Ministry of Health (MoH) and all users. The article aims to describe the implementation and lessons learned in transitioning a maternal surveillance digital platform (MATSurvey) from a research-based to a government-owned system in Malawi.

Methods: The transition process involved active participation of the MoH leadership and close cooperation with healthcare workers and partners. The process comprised six stages, including stakeholder engagement, user feedback, system design, obtaining stakeholder input on the design, system development and testing, piloting and full implementation. The process emphasised stakeholder engagement, with technical teams from the MoH and Malawi Liverpool Wellcome Programme incorporating feedback during development.

Results: The successful transition of the MATSurvey platform from the Malawi Liverpool Wellcome Programme to the Digital Health Information System 2 tracker required strong leadership from the MoH, active engagement of partners and stakeholders, and a gradual, inclusive process. Challenges such as reliance on donor funding and delays in government support were notable, while ensuring clear data governance policies, system scalability, effective communication, and comprehensive training contributed to a smoother transition and successful adoption.

Conclusion: Transitioning of a digital health platform such as the MATSurvey platform requires strong leadership and supervision to ensure adoption, acceptance and ownership. The active involvement of MoH, partners and stakeholders accelerated transitioning of the platform despite challenges in funding, which ultimately resulted in delaying the process.

Background: Mandarin-speaking consumers requiring interpreter services face significant barriers to telehealth access in Australia, often due to systemic and cultural disconnects which widens healthcare access disparities. This qualitative cross-cultural cross-lingual study explored the perspectives of Mandarin-speaking individuals at a metropolitan hospital in Queensland to identify barriers, enablers, and solutions for equitable telehealth access.

Methods: Three Mandarin cross-lingual focus groups were conducted. Situated within the interpretive research paradigm and informed by intersectional critical inquiry, consumers described their perspectives on lived experiences interacting with the tertiary healthcare system while accessing telehealth and requiring interpreter services. Analysis was conducted by two researchers, starting with open coding, cross-checking and application of an intersectional lens.

Results: Eight Mandarin-speaking consumers and two carers attended three cross-lingual focus groups with qualified real-time interpreters. The analysis revealed six themes: 1) lack of telehealth awareness; 2) clinicians are gatekeepers of telehealth services; 3) the healthcare system is monolingual; 4) navigating the healthcare system is disempowering; 5) power is transferred to interpreters and carers; and 6) alternative solutions do not align with participants needs. Participants expressed openness to telehealth but emphasised the need for culturally sensitive and clearly communicated options.

Conclusion: This study reveals significant challenges accessing telehealth for Mandarin-speaking consumers needing interpreter services in metropolitan Queensland and highlights that clinician assumptions and the monolingual nature of healthcare services as major barriers. While video interpreting is often recommended, participants preferred simple, safe, and culturally appropriate communication strategies. Co-designing telehealth solutions with multicultural consumers can prevent the deepening of existing inequities and to foster inclusive healthcare practices.

Objective: To evaluate the level of quality, professionalism, and humanistic care in medical advice given by artificial intelligence (AI) and healthcare experts on social media platforms, with an emphasis on short video content and in-person question-and-answer (Q&A) sessions.

Methods: The mDISCERN, GQS, and VIQI scores were used to assess the quality and creator opinion trends of the short videos on AI-assisted diagnosis that were gathered from YouTube, TikTok, and Bilibili. Patient inquiries from Dingxiang Health, a significant Chinese online consultation platform, were selected across medical departments. Simulated answers were produced by Deep Seek R1 and Chat-GPT O3-mini-high, and Bedside Manner Rating were used to evaluate the humanistic and high-quality treatment.

Results: Across platforms, 60.8% of videos preferred AI's diagnosis powers above medical professionals (Bilibili: 74.29%, TikTok: 56.67%, YouTube: 53.75%). Bilibili videos, particularly those produced by professionals, scored highest in quality (p < 0.05). In simulated consultations, AI fared better than doctors in terms of quality and humanistic care (p < 0.05), especially in structured expression and emotional response.

Conclusions: Higher-quality medical content is available on Bilibili, and AI shows benefits in terms of humanistic care and diagnostic quality in text-based, simulated consultations. Future research should explore examine how doctors and AI might work together to enhance healthcare delivery, with doctors using digital communication while also exercising professional judgment in real-world clinical settings.

Objectives: Acute kidney injury (AKI) is marked by a rapid decline in renal function, often identified by elevated serum creatinine or reduced urine output. Although stress hyperglycemia ratio (SHR) has been linked to adverse outcomes in various conditions, its association with clinical prognosis in AKI patients remains unclear.

Methods: This cohort study analyzed data from critically ill patients with AKI extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV, version 3.1) database. The primary outcomes were 28-day and 365-day all-cause mortality, while the secondary outcomes included ICU mortality and in-hospital mortality. The association between SHR and all-cause mortality was explored by Cox proportional hazards regression. The discriminative performance of SHR was evaluated through the Boruta feature selection model, followed by the development of a prognostic prediction model utilizing advanced machine learning.

Results: The analysis encompassed 3640 patients with AKI. Multivariable Cox regression analysis demonstrated that elevated SHR significantly predicted increased 28-day mortality [adjusted hazard ratio (HR) 1.19, 95% confidence interval (CI): 1.11-1.29, P < .001, Model 3] and 365-day mortality (HR: 1.17, 95% CI: 1.08∼1.27, P < .001, Model 3). Upon categorizing SHR into quartiles, individuals in the highest quartile (Q4) faced a substantially elevated risk, with a 101% greater likelihood of 28-day death and a 34% elevated hazard of 365-day death relative to those in the lowest quartile (Q1). Boruta feature selection analysis identified SHR as a significant predictor. Among various predictive models evaluated, the CatBoost classifier exhibited the most robust discriminative performance for 28-day and 365-day mortality, achieving an area under the receiver operating characteristic curve of 0.83 and 0.82, respectively, showing comparable discriminative performance to the other models.

Conclusion: The SHR demonstrated a nonlinear association all-cause mortality among critically ill patients AKI, suggesting its potential utility as a reliable prognostic indicator for predicting unfavorable results in AKI patients.

Background: This study leverages machine learning and cytokine profiles to differentiate liver and renal function abnormalities in the aging population, aiming for advancements in early detection techniques.

Methods: The analysis involved data from 760 participants, employing logistic regression, random forest, lasso regression, extreme gradient boosting, and support vector machines to create diagnostic models. Cytokine levels were measured via ELISA, alongside liver and renal clinical function tests. The data were randomly split 3:1 into training and hold-out validation sets; Synthetic Minority Over-sampling Technique (SMOTE) was applied exclusively to the training set to mitigate class imbalance. Models were assessed on precision, recall, F1 score, specificity, and the area under the curve (AUC).

Results: Lasso regression was notably effective in identifying renal function abnormalities, delivering AUCs of 0.895 for males and 0.940 for females, pointing to its robustness in feature selection and model accuracy. For liver function, logistic regression was most accurate, with AUCs of 0.918 for males and 0.794 for females, identifying VCAM-1, REG4, Thrombomodulin, Notch-3 for males, and GDF-15, LDL R, CA125, PON1 for females as key discriminative cytokines. These results illustrate the models' capability in discerning critical biomarkers for early detection, with performance improved by SMOTE through correction of class imbalance in the training data.

Conclusion: Integrating machine learning with cytokine profiling emerges as a highly promising method for early detection of liver and renal abnormalities in the aging population, suggesting significant potential for improving preventive healthcare outcomes.

Background: Digital technologies offer the potential to promote mental health by improving older adults' digital and mental health literacy. Intergenerational support is a promising medium to promote the mental health of older adults. Nonetheless, the effects of interventions employing digital and mental health literacy training through intergenerational support on the mental health of older adults remain unclear.

Objectives: This study evaluated the effects of the Digital Buddy programme on the mental health of older adults.

Methods: This study used a multi-centre, cluster-randomised, two-parallel-group (1:1 allocation ratio), controlled trial design. People aged ≥60 years without diagnosed mental illnesses were eligible. In the intervention group, participants attended 14 training sessions conducted by young volunteers over 2 months, using materials on a website and a smartphone app. The content included digital skills and mental health knowledge. Volunteers continued tele-coaching participants for 6 months. The control group received usual care. Outcomes measured at baseline (T0) and 1-week post-intervention (T1) included mental well-being, depressive symptoms, health-related quality of life, self-efficacy, and perceived social support. Generalised estimating equations tested the hypotheses.

Results: A total of 310 participants from 15 clusters entered the study, with each group containing 155 participants. The WHO-5 (mean difference = 7.0, d = 0.32, p < .001) and Patient Health Questionnaire-9 scores (mean difference = 0.9, d = 0.24, p = .02) of the intervention group improved after the intervention with statistical significance, but not in the control group. Likewise, the interaction effects of group and time on the two outcomes were not statistically significant.

Discussion: There was a main effect of time in the intervention group over the outcomes of mental well-being and depressive symptoms. However, the interaction was non-significant and therefore the change over time did not differ between groups and therefore groups had similar change trajectories. However, future studies should devise measures to enhance its effects.

Trial registration: This trial has been registered at ClinicalTrials.gov (NCT05553730) on 23 September 2022, https://clinicaltrials.gov/ct2/show/NCT05553730.

Background: The internet of medical things (IoMT) is revolutionizing digital health through continuous monitoring, real-time diagnostics, and remote care capabilities. Nonetheless, research in this domain remains disjointed, with a restricted comprehension of its growth trajectories, principal contributors, and thematic emphasis. A comprehensive evaluation is thus required to inform forthcoming research, policy, and advancements in resilient healthcare technologies.

Methods: This study performed a bibliometric and literature-based analysis of IoMT research indexed in the Scopus database from 2016 to 2023. The dataset was optimized by keyword screening, resulting in 762 pertinent papers. Bibliometric indices, including as publication and citation trends, authorship and institutional output, and funding patterns, were analyzed. Thematic evolution was examined by keyword co-occurrence and cluster mapping utilizing VOSviewer, complemented by a synthesis of literature.

Results: A total of 762 publications on IOMT were identified, comprising 63.12% journal articles, 30.97% conference papers, and 5.91% review papers. The total publications rose from 1 in 2016 to 301 in 2023, indicating a 30,000% increase. Total citations reached 19,014, with an h-index of 171. The most prolific contributors were Mohsen M. Guizani, King Saud University, and India. Collaborations and funding, particularly from international agencies, were found to significantly drive research productivity. Keyword and cluster analyses revealed two dominant thematic areas: Smart Medical Diagnostics and Privacy-Driven Health Technologies. The literature further confirmed strong integration of machine learning, blockchain, sensor technologies, and cloud computing in IOMT applications.

Conclusion: This analysis consolidates fragmented IoMT research, providing a structured overview of its development, contributors, and thematic trajectories. The findings highlight the rapid growth, global collaborations, and integration of advanced technologies driving the field. By mapping benchmarks and research hotspots, the study offers valuable evidence to guide future investigations, interdisciplinary collaborations, and policy efforts aimed at strengthening secure and patient-centered digital health systems.

Background: Uterine contraction is a meaningful indicator for labor onset and appropriate hospital admission. Inaccurate self-assessment may lead to premature admission, unnecessary interventions, and higher healthcare resource use. Traditional monitoring devices have limited portability and comfort, restricting home-based use.

Objective: This study developed and validated a wearable system integrating flexible sensors, a data acquisition platform, and machine learning models to monitor uterine contractions and identify labor onset, focusing on late pregnancy and the pre-labor period.

Methods: A flexible sensor-based device was developed and validated against hospital toco. Contraction data from 82 participants (104 recordings) were preprocessed and segmented, and features were extracted for model training. Hospital admission was classified into recommended admission (RA), deferred admission (DA), and selective admission (SA). Several ML models were trained and evaluated via 10-fold stratified cross-validation using accuracy, precision, recall, F ₁-score, and area under the curve. Shapley Additive Explanations (SHAP) analysis interpreted feature contributions.

Results: A total of 82 participants were enrolled, and 104 uterine contraction recordings were collected, ranging from 10 to 70 min (mean 20.3). Two hundred and seventy-seven processed segments were obtained for analysis. Contraction signals were generally consistent with toco measurements (r = 0.85-0.95). XGBoost achieved accuracy of 0.87 for RA classification, and SHAP identified kurtosis, signal energy area, and standard deviation as key features.

Conclusion: The system enabled accurate monitoring of uterine contractions, improved estimation of hospital admission timing, reduced premature admission risk, and demonstrated high wearability, offering a feasible solution for home obstetric monitoring.

Objective: This study aims to systematically assess the content characteristics and information quality of knee arthroplasty-related videos on TikTok and Bilibili, in order to provide evidence to support the optimization of health science communication.

Methods: On February 13, 2025, we searched for "" (knee arthroplasty in Chinese) on TikTok and Bilibili, and initially collected 100 videos from each platform according to the default sorting order, which were then subjected to further screening. Videos containing irrelevant content, lacking audio, being non-original reposts, or intended for advertising and marketing purposes were excluded. The quality and reliability of the included videos were assessed by applying four validated instruments: the modified version of DISCERN (mDISCERN), the Global Quality Score (GQS), the Video Information and Quality Index (VIQI), and the Patient Education Materials Assessment Tool (PEMAT). Interplatform variations and correlations between quality and user interactions were analyzed via Mann‒Whitney U and chi-square tests.

Results: A total of 162 knee arthroplasty related videos were analyzed, including 88 from TikTok and 74 from Bilibili. TikTok videos demonstrated higher engagement and more certified uploaders, whereas Bilibili featured more diverse professional backgrounds. Bilibili emphasizing anatomy using PPT/class based, animation/ motion and television program/documentary styles. TikTok focusing on examination/diagnosis, and treatment delivered through solo narrative and Questions and Answers (Q&A). TikTok videos achieved higher scores across all quality assessment tools. Professionally generated content consistently outperformed nonprofessional content across most quality metrics, whereas no significant difference was observed for mDISCERN. Correlation analysis showed that engagement was strongly associated with VIQI on both platforms, with additional moderate associations for GQS and PEMAT only on TikTok, while mDISCERN showed no significant correlation.

Conclusions: TikTok favors high user engagement, whereas Bilibili provides more structured educational content. Professional involvement is essential to ensure information quality and effective medical communication.

Objective: To evaluate the design, implementation, and early impact of the Tasty Spoon™ - a hybrid digital-analogue, electrostimulation device intended to restore taste perception in people with dementia - and to identify the organisational and market conditions required for its routine use.

Methods: A ProcessOriented Holistic (PrOH) Modelling Methodology was applied across four phases:1. Userneeds assessment through three focus groups (n = 28), semistructured interviews with individuals living with dementia (n = 10), caregivers (n = 5) and healthcare professionals (n = 15).2. Iterative codesign and lab prototyping, informed by thematic analysis and smallscale electrogustometry studies (n = 15; people with dementia = 10, control = 5).3. Feasibility testing the prototype in care-home dining routines to explore practicality, user acceptance, and caregiver workload, documented through field notes, post use interviews and caregiver workload diaries.4. Regulatory and commercial pathway mapping (UKCA/CE precompliance review, 3i stakeholder analysis). Quantitative data were analysed descriptively; qualitative insights were integrated into the PrOH workflow to expose implementation pinchpoints.

Results: PrOH analysis identified three design features that underpinned acceptability - familiar spoon form, automatic activation on contact, and dishwashersafe construction - while highlighting outstanding challenges in cost control, training, and individual differences in taste sensitivity. Participants consistently reported that the Tasty Spoon™ made food 'taste stronger' and restored variety to meals they had previously found bland. Our research also highlighted the importance of co-developing ethical procedures in collaboration with people with dementia.

Conclusion: Early, smallscale evidence suggests that a sensoryfocused assistive device can complement existing cognitive and mobility technologies in dementia care by enhancing mealtime enjoyment and easing caregiver burden. Larger, rigorously controlled studies are needed to quantify nutritional and clinical outcomes and to refine personalised stimulation settings before widescale deployment.