DIGITAL HEALTH最新文献

Background: Maternal obesity increases risks of adverse pregnancy outcomes and long-term diseases for mothers and child. Digital lifestyle interventions show promise, but their effectiveness depends on meeting the specific needs of pregnant women with obesity and healthcare providers (HCPs).

Objectives: To explore perspectives and practices on healthy lifestyle and care for pregnant women with obesity, and to identify needs and preferences for digital lifestyle intervention development and implementation.

Methods: A qualitative study using focus groups and interviews was conducted with 13 HCPs and 13 pregnant women with obesity. Sessions were audio-recorded, transcribed and analysed thematically. Women viewed a healthy lifestyle as multidimensional, encompassing nutrition, physical activity, mental well-being, and rest, but faced barriers such as pregnancy discomfort, limited knowledge, and stigma. Both women and HCPs emphasized child health as a motivator and valued goal setting and practical advice. Existing care was seen as inconsistent and generic, with HCPs constrained by time and unclear roles. Participants preferred a personalized, user-friendly mobile app with modular, evidence-based content tailored to individual goals, pregnancy stage, and medical status. Features such as self-monitoring, goal setting, and a supportive, non-judgmental tone were important. Integration into routine obstetric care was considered key for engagement and effectiveness. If designed accordingly, such tools could provide accessible, tailored support between appointments, reinforce positive behaviour change, improve patient-provider communication, and reduce HCP time pressures.

Conclusions: Co-designing digital lifestyle tools with women and HCPs is vital. Personalized, feasible interventions integrated in obstetric care can support behaviour change and improve outcomes for mothers and children.

Trial registration number: not applicable.

Background: Nursing care in isolation environments requires strict infection control protocols, which increase nurses' physical and psychological burden. Frequent entry into isolation rooms for routine tasks, such as adjusting infusion pumps, exposes healthcare workers to infectious agents, increases consumption of personal protective equipment, and results in inefficient use of nursing resources.

Aims: This study aimed to develop and evaluate the usability of an Internet of Things (IoT) remote control system for infusion pumps (IRCSIP) to support infection prevention, improve nursing efficiency, and enable effective use of resources in isolation care.

Design: Simulation-based, single-group pre-post usability study.

Methods: IRCSIP developed using existing commercial IoT devices. Twelve registered nurses with experience in infusion pump operations and isolation nursing care completed two scenarios: (1) remote operation using the IRCSIP and (2) traditional infusion pump operation. The time required to complete infusion rate adjustment, operational success, and subjective usability were measured. Data were analyzed using paired t-tests and descriptive statistics.

Results: All participants successfully adjusted the infusion rate on their first attempt in both scenarios. Compared with traditional operation, the IRCSIP significantly reduced adjustment time, saving an average of 90.67 s. Usability ratings were positive across all domains: effectiveness "Very good" (58.33%) or "Good" (41.67%); efficiency "Very good" (91.67%); satisfaction "Very good" (66.67%) or "Good" (25.00%); safety "Very good" (41.67%) or "Good" (16.67%); and ease of use "Very good" (58.33%) or "Good" (33.33%).

Conclusion: IRCSIP demonstrated high usability and significantly improved workflow efficiency by reducing the time needed for infusion rate adjustments. This suggests that the system may help reduce nurse workload related to routine infusion pump management. A key strength of the IRCSIP is compatibility with existing infusion pumps, which allows for cost-effective and scalable implementation without the need for new medical equipment.

Objective: Men grappling with infertility often face emotional distress due to stigma and masculinity norms. Social support is vital in coping with infertility, and with the rise of digital health, much of it has shifted online. However, Dutch-speaking online infertility support groups (OISGs) remain unexplored, especially regarding male support inclusion. Existing research focuses on message content, offering limited insight into user demographics and usage patterns. Men's online support experiences are largely unexplored, and studies rarely examine online and offline networks together, despite their combined importance for support and wellbeing. This study addresses these gaps through three objectives: (1) explore the availability of Dutch- speaking OISGs and their inclusion of male-specific support; (2) map characteristics of male users and their usage of OISGs; and (3) understand how men experience online versus offline infertility support, and what factors shape their use.

Methods: A multistage mixed-method design was used in Flanders and the Netherlands, comprising three sequential components: (1) an environmental scan; (2) an online survey; and (3) online semi-structured interviews.

Results: Findings show that Dutch OISGs are scarce and male-specific support is not self-evident. Users are predominantly higher-SES, indicating selective access. Freya is the most used platform, with sustained but varied usage. Men's engagement is shaped by an interplay of digital and psychosocial factors, with perceived anonymity acting as a paradox. Online and offline infertility support are experienced as complementary, fulfilling different needs. The core distinction lies in the nature of relationships, peer versus intimate, rather than the medium. Support needs are dynamic across both settings.

Conclusion: These insights underscore the need for more, inclusive, and tailored support strategies that address the dynamic needs of men navigating infertility in both online and offline contexts.

Background: Remote photoplethysmography (rPPG) is a non-contact method for measuring physiological parameters using smartphone cameras. While the potential for scalable self-monitoring is promising, little is known about its usability and acceptability among patients with chronic cardiac and respiratory conditions.

Objective: This qualitative study explored the user experiences of a smartphone-based rPPG app (Vitacam) to assess its usability, acceptability, and perceived utility in real-world conditions.

Methods: Seven adults with chronic heart or respiratory conditions used the app at home over one week. Semi-structured interviews were conducted and explored using reflexive thematic analysis.

Results: Participants appreciated the app's simplicity, real-time guidance, and convenience. Key barriers included environmental sensitivity (e.g. lighting), technical limitations, vague error messaging, and lack of clinical integration. Users valued basic self-monitoring features but expressed concerns about accuracy and interpretation, especially for complex conditions like atrial fibrillation.

Conclusions: rPPG via smartphone is a promising, low-burden option for basic self-monitoring in chronic disease management. To increase adoption and utility, future iterations should improve feedback clarity, algorithm sensitivity, and integration with clinical systems. These developments could enhance user trust, accuracy, and long-term engagement.

The successful implementation of digital health and artificial intelligence (AI) innovations in the National Health Service (NHS) requires more than technical development. Navigating regulation, generating decision-grade evidence, and meeting clinical safety, information-governance, and interoperability standards are critical steps that frequently delay or prevent adoption. This article presents a practical, implementation-focused roadmap designed to help clinicians, innovators, and healthcare leaders translate policy requirements into real-world NHS deployment. Drawing on guidance from the Medicines and Healthcare products Regulatory Agency (MHRA), the National Institute for Health and Care Excellence (NICE), and NHS Digital, we outline an eight-step pathway covering medical-device classification, value-proposition development, intended-purpose definition, regulatory approval, evidence generation, algorithmic fairness and generalisability, interoperability and information governance, and post-market surveillance. Unlike high-level digital health frameworks, the roadmap specifies minimum artefacts, typical ownership and sign-off responsibilities, and decision points aligned with NHS procurement and clinical governance processes. The roadmap is illustrated through a detailed case study of a UK-deployed AI stroke imaging decision-support software. Its progression from academic development to multi-site NHS deployment demonstrates how early regulatory engagement, robust real-world evaluation, and sustained clinical collaboration can support safe scaling and measurable service improvements, including increased access to reperfusion therapies and reduced inter-hospital transfer times. By distilling complex regulatory and evidence requirements into executable steps, this guide offers a clear route from idea to adoption. It emphasises that aligning regulation, evidence generation, bias mitigation, and interoperability from the outset is essential to sustainable digital health integration within the NHS.

Objective: Stain color variations caused by differences in staining environments and scanning devices pose a major challenge for deep learning-based analysis of digital histopathological images. This study aims to develop a robust stain normalization framework that preserves structural information while enabling stable color-domain conversion across heterogeneous stain domains.

Methods: We propose a generative adversarial network (GAN)-based training and testing framework, termed I-GAN, which integrates StainGAN and Stain-to-Stain Translation (STST). The method incorporates identity loss within an RGB-grayscale training strategy and applies RGB images during testing to preserve original stain information. Performance was evaluated on the MITOS-ATYPIA 14 dataset using SSIM, PSNR, and DeltaE-ITP, and further assessed on downstream classification tasks using Camelyon17 and the ICIAR2018 BACH Challenge datasets.

Results: On MITOS-ATYPIA 14, I-GAN achieved an SSIM of 0.980, a PSNR of 29.579, and a DeltaE-ITP of 46.284, indicating superior structural preservation and color fidelity. For classification tasks, I-GAN obtained an average precision of 0.964 on Camelyon17 and an accuracy of 0.87, precision of 0.86, and recall of 0.87 on the ICIAR2018 BACH dataset.

Conclusions: The proposed I-GAN framework improves stain normalization for hematoxylin and eosin-stained digital histopathology images by preserving structural integrity and achieving accurate color-domain conversion. These results demonstrate the robustness and practical applicability of the proposed approach for medical image analysis.

Background: OpenAI developed ChatGPT as an advanced artificial intelligence (AI)-driven natural language processing system. ChatGPT is capable of generating responses through statistical pattern recognition established during pretraining.

Objective: To ascertain whether ChatGPT could respond to patients with breast cancer in a way that was consistent with evidence-based medical practices and a breast cancer clinical guideline. This guideline was a practical pocket book based on the latest evidence and took into account the national data, and to evaluate the ability of AI to provide accurate and up-to-date information to patients, potentially serving as a supplementary resource for medical professionals.

Methods: The research team designed a series of tests to assess the responses of ChatGPT to specific questions related to breast cancer diagnosis, treatment options, and post-treatment care. Thirty clinically validated breast cancer questions spanning diagnosis, prognosis, treatment, and pharmacotherapy were administered through three iterative trials to: (1) GPT-3.5/GPT-4.0 (5min interval between trials) and (2) three breast surgeons stratified by expertise (high/medium/low). Responses were scored dichotomously (1 = guideline-consistent; 0 = inconsistent) with total scores ranging 0 to 3 per question. For each consistent and inconsistent answer with the standard answer, 1 and 0 points were given, respectively. The sum of the answers obtained from the three experts resulted in a score of 0 to 3. Data analysis included mean score comparisons (analysis of variance with post hoc Tukey tests), subgroup analyses by question category, and inter-rater reliability assessment.

Results: Performance comparison between GPT-3.5 and GPT-4.0 across breast surgery subspecialties and question types revealed that GPT-4.0 generally outperformed GPT-3.5, despite the absence of significant difference in the mean scores for most items. We found that GPT-3.5 and have the same medical response ability as lower qualified breast surgeons, while GPT-4.0 have the same ability as higher qualified breast surgeons.

Background: Glucolipid metabolic disorders is a disorder characterized by derangement of glucose and lipid metabolism, which is involved in multiple factors. Since the emergence of accelerated technological evolution, it has progressively evolved into a significant concern in contemporary medicine. Therefore, early screening and diagnosis are crucial. This study aims to explore the possibility of early noninvasive diagnosis of glucolipid metabolic disorders using facial and tongue image indicators.

Method: In this study, we constructed a tongue-face segmentation model based on Deeplabv3 + for extracting tongue and facial indicators. The study collected information of 614 participants, including 296 patients with GLMD and 318 healthy controls. After baseline comparison, we respectively conducted intergroup comparison of laboratory biochemical indicators and correlation analysis of facial indicators and tongue image indicators for two groups. We also attempted to build machine learning diagnostic models for glycolipid metabolic diseases based on SVM, Random Forest, KNN, Naive Bayes, XGBoost, and AdaBoost by separately applying facial images and tongue images, and used Shapley to evaluate the contribution of each indicator in the model.

Result: The results show that there is a statistically significant difference in the facial and lip color indicators and tongue color indicators. The facial, lip and tongue brightness indicators have a higher correlation coefficient with LDL-C, TG, and CHO, among which F-L is most correlated with LDL-C. Then, six classical machine learning models for predicting GLMD were constructed based on facial and tongue image indicators, and XGBoost performed the best with an AUC of 0.946, accuracy of 0.861, among which the color indicators TB-Y, TB-S, and TB-G are the top three indicators in terms of contribution.

Conclusion: The GLMD diagnostic model combined with tongue-facial indicators can achieve disease classification, and through modern information-based TCM diagnosis technology, the accuracy of noninvasive diagnosis of glucose-lipid metabolism diseases can be further improved.

Objective: Engagement with self-monitoring is crucial for success in digital behavior change interventions for weight loss, but little is known about trajectories of engagement, nor valid predictors of these trajectories. This exploratory trajectory analysis identified engagement patterns based on multiple trajectories of engagement with self-monitoring of weight, diet, and activity in a website-based weight loss intervention over 12 months among adults with overweight/obesity (N = 363).

Methods: Latent class growth modeling with a mixture layer used self-monitoring data including number of days tracking weight, diet, and activity on the study website, summed across four 3-month intervals, to identify groups based on engagement trajectories. Regression models examined the association between engagement patterns, demographic variables, and percent weight loss at 12 months.

Results: Four engagement patterns emerged: never-engagers (23%), low/declining engagers (48%), early-engagers (13%), and sustained-engagers (16%). Trajectories of engagement were similar across self-monitoring behaviors within the same class. Age, race, and baseline body mass index were associated with likelihood of engagement class membership. Percent weight loss was clinically significant at 12 months for both sustained-engagers (-10.4%) and early-engagers (-5.1%), but not for low/declining (-1.3%) or never-engagers (-0.5%).

Conclusion: Promoting early self-monitoring engagement may be of equal or greater importance than promoting sustained engagement to achieve desired weight loss outcomes in a digital behavior change intervention for weight loss. Given the high proportion of low/declining engagers who did not achieve clinically significant weight losses, there is a need to characterize and identify these participants early on to promote engagement with self-monitoring.

Objective: To explore the perceived feasibility and potential applications of an augmented reality (AR) solution to address the challenges of managing pressure injuries in non-clinical settings.

Methods: This qualitative study utilized semi-structured interviews with caregivers and healthcare professionals. Conducted from January to June 2025 at Guangdong Provincial Hospital of Chinese Medicine, the study recruited 21 participants via purposive and snowball sampling until data saturation. Interview guides were grounded in the technology acceptance model. Data were analyzed using Braun and Clarke's six-phase thematic analysis via NVivo.

Results: Most participants (90.5%) reported prior experience with general digital health technologies such as telehealth platforms, while few had used immersive technologies (23.8%). All healthcare professionals were currently involved in pressure injury care (100.0%), and most caregivers were providing current care (83.3%), with the remaining caregivers reporting recent and relevant caregiving experience (16.7%). Thematic analysis revealed that participants' perceptions of the AR application were shaped by three main themes: perceived usefulness, perceived ease of use, and intention to use. Key external variables, such as computer anxiety and computer efficacy, also influenced these perceptions.

Conclusion: This study indicates that both healthcare professionals and caregivers perceive AR as a potentially useful tool for remote pressure injury management. Successful implementation depends on addressing key concerns related to user interface design, cost, and data privacy. These insights indicate that future development must prioritize intuitive usability and robust privacy measures to ensure successful implementation.