Frontiers in digital health最新文献

Introduction: Self-management is the ability to control one's own responses to treatments, physical and psychological side effects, and lifestyle choices related to a chronic condition.

Purpose: To describe the development of a standard and practical user-centered design process for an interactive voice response system (IVRS) to improve self-management in kidney transplant (KT) recipients.

Methods: The IVRS was constructed utilizing the four phases of the Center for eHealth and Wellbeing Research (CeHRes) roadmap: the contextual inquiry, the value specification, the design phase, and evaluation. First, a literature review, background analysis, and needs assessment were used to identify the needs and problems and solutions related to self-management of KT recipients. Then, with the help of a team of experts and KT recipients, a logic model was created and evaluated. The IVRS was developed through iterative design development in response to these findings. Finally, fifteen end users (KT beneficiaries and health professionals) participated in a usability field test by completing a thinking -aloud test and a questionnaire based on the System Usability Scale (SUS).

Results: The review study indicates the necessary of self-management education and the potential outcomes and functionalities of information technology intervention. The situation analysis and needs assessment led to the final important requirements for the design of the intervention. All values were identified in three meetings with principal stakeholders, and a logic model was designed. The user test yielded an average SUS score of 81.2, and these results served as the basis for the usability requirements. Health Care Providers (HCPs) struggled with storing the profile of registered patients, setting up medication and personalizing adherence calls, and educational calls and follow-ups.

Conclusion: Following the CeHRes roadmap, an intervention based on IVRS was developed with considering the needs and preferences of KT recipients and HCPs. Designers and researchers could use the CeHRes roadmap as a reference when developing IT-based intervention systems. However, decisions must be made about the thoroughness of the execution of each phase, taking into account time constraints.

Introduction: Online formats provide promising and low-threshold options for mental health coaching. However, research on online mental health interventions compared to traditional face-to-face interventions remains scarce. In the present study, the established prevention tool "Teacher Group-coaching Program" (TGP) was applied in both the original face-to-face setting as well as online. TGP focuses on promoting mental health in teachers by strengthening relational skills using the Balint group technique. This technique roots back to a psychoanalytic approach to explore the emotional aspects of (stress inducing) professional relationships. The current study aimed at comparing the satisfaction with and effectiveness of TGP between both settings.

Method: The sample consisted of 104 teachers who voluntarily chose between face-to-face (n = 51) and online (n = 53) setting. In a pre-posttest design, participants completed questionnaires before and after the intervention. Additionally participant's satisfaction with the program was assessed during and after TGP.

Results: Intervention effects did not differ significantly in terms of mental health, general life satisfaction and emotional distancing between TGP online and face-to-face. In line with previous research, there was a pre-posttest improvement for mental distress and the ability to distance oneself for both groups, which did not differ significantly between face-to-face and online setting. Satisfaction with the program was rated high in both settings, suggesting similar acceptance.

Discussion: Although, the absence of an effect is not the evidence of equality of the groups, the present study highlights the potential of online admissions of mental health interventions as possible alternatives and additions to traditional face-to-face programs, especially when in-person meetings are not feasible. Specifically, it shows evidence that the Balint group technique can also be applied successfully by trained experts in the online setting.

Introduction: Externalization techniques are well established in psychotherapy approaches, including narrative therapy and cognitive behavioral therapy. These methods elicit internal experiences such as emotions and make them tangible through external representations. Recent advances in generative artificial intelligence (GenAI), specifically large language models (LLMs), present new possibilities for therapeutic interventions; however, their integration into core psychotherapy practices remains largely unexplored. This study aimed to examine the clinical, ethical, and theoretical implications of integrating GenAI into the therapeutic space through a proof-of-concept (POC) of AI-driven externalization techniques, while emphasizing the essential role of the human therapist.

Methods: To this end, we developed two customized GPTs agents: VIVI (visual externalization), which uses DALL-E 3 to create images reflecting patients' internal experiences (e.g., depression or hope), and DIVI (dialogic role-play-based externalization), which simulates conversations with aspects of patients' internal content. These tools were implemented and evaluated through a clinical case study under professional psychological guidance.

Results: The integration of VIVI and DIVI demonstrated that GenAI can serve as an "artificial third", creating a Winnicottian playful space that enhances, rather than supplants, the dyadic therapist-patient relationship. The tools successfully externalized complex internal dynamics, offering new therapeutic avenues, while also revealing challenges such as empathic failures and cultural biases.

Discussion: These findings highlight both the promise and the ethical complexities of AI-enhanced therapy, including concerns about data security, representation accuracy, and the balance of clinical authority. To address these challenges, we propose the SAFE-AI protocol, offering clinicians structured guidelines for responsible AI integration in therapy. Future research should systematically evaluate the generalizability, efficacy, and ethical implications of these tools across diverse populations and therapeutic contexts.

Remote Patient Monitoring (RPM) has driven significant advancements in Canadian healthcare, especially during the transformative period from 2018 to 2023. This perspective article explores the state of play and examines the current landscape of RPM platforms adopted across Canada, detailing their functionalities and measurable impacts on healthcare outcomes, particularly in chronic disease management and hospital readmission reduction. We explore the regulatory, technical, and operational challenges that RPM faces, including critical issues around data privacy, security, and interoperability, factors essential for sustainable integration. Additionally, this article provides a balanced analysis of RPM's potential for continued growth within Canadian healthcare, highlighting its strengths and limitations in the post-2023 context and offering strategic recommendations to guide its future development. Keywords: Remote Patient Monitoring, Digital Health, Virtual Care, Canadian Healthcare, Healthcare Technology, AI, Perspectives.

Introduction: Smoking, obesity, and insufficient physical activity are modifiable health risk behaviors. Self-regulation is one fundamental behavior change mechanism often incorporated within digital therapeutics as it varies momentarily across time and contexts and may play a causal role in improving these health behaviors. However, the role of momentary self-regulation in achieving behavior change has been infrequently examined. Using a novel momentary self-regulation scale, this study examined how targeting self-regulation through a digital therapeutic impacts adherence to the therapeutic and two different health risk behavioral outcomes.

Methods: This prospective interventional study included momentary data for 28 days from 50 participants with obesity and binge eating disorder and 50 participants who smoked regularly. An evidence-based digital therapeutic, called Laddr™, provided self-regulation behavior change tools. Participants reported on their momentary self-regulation via ecological momentary assessments and health risk behaviors were measured as steps taken from a physical activity tracker and breathalyzed carbon monoxide. Medical regimen adherence was assessed as daily Laddr usage. Bayesian dynamic mediation models were used to examine moment-to-moment mediation effects between momentary self-regulation subscales, medical regimen adherence, and behavioral outcomes.

Results: In the binge eating disorder sample, the perseverance [β ₁ = 0.17, 95% CI = (0.06, 0.45)] and emotion regulation [β ₁ = 0.12, 95% CI = (0.03, 0.27)] targets of momentary self-regulation positively predicted Laddr adherence on the following day, and higher Laddr adherence was subsequently a positive predictor of steps taken the same day for both perseverance [β ₂ = 0.335, 95% CI = (0.030, 0.717)] and emotion regulation [β ₂ = 0.389, 95% CI = (0.080, 0.738)]. In the smoking sample, the perseverance target of momentary self-regulation positively predicted Laddr adherence on the following day [β = 0.91, 95% CI = (0.60, 1.24)]. However, higher Laddr adherence was not a predictor of CO values on the same day [β ₂ = -0.09, 95% CI = (-0.24, 0.09)].

Conclusions: This study provides evidence that a digital therapeutic targeting self-regulation can modify the relationships between momentary self-regulation, medical regimen adherence, and behavioral health outcomes. Together, this work demonstrated the ability to digitally assess the transdiagnostic mediating effect of momentary self-regulation on medical regimen adherence and pro-health behavioral outcomes.

Clinical trial registration: ClinicalTrials.gov, identifier (NCT03774433).

Objectives: The present study aimed to analyze the effects of the use of a digital wellness device on improving sleep through reducing environmental noise.

Methods: Fifty-five self-reported light or moderate sleepers with difficulty falling or staying asleep due to environmental noise participated in the study. Objective sleep architecture data were collected via a wireless electroencephalogram (EEG) sleep monitor and subjective data were obtained through analysis of daily sleep diaries and responses to study-specific user experience surveys. Four primary outcomes specified a priori were analyzed for statistical significance: objectively measured sleep onset latency (SOL), wake after sleep onset (WASO), number of awakenings, and perceived SOL. Exploratory analysis through descriptive statistics was conducted for an additional 36 secondary outcomes.

Results: Use of the digital wellness device was associated with reduced SOL both objectively and subjectively. Perceived SOL was 32.5% reduced (p < 0.001, difference in means 7.5 min, 95% CI 22.3%-41.4% faster), and objectively measured SOL was 13.3% reduced (p = 0.030, difference in means 2.7 min, 95% CI = 1.4%-23.8% faster). No statistically significant differences were found for other primary outcomes. Among the subjective secondary outcomes, 100% of participants felt the device blocked environmental noise, 86% reported falling asleep more easily, 76% felt they stayed asleep longer, and 82% felt overall sleep quality was improved. No differences were observed among objectively measured secondary outcomes.

Conclusions: Participants fell asleep faster when using the wearable wellness device. Participants also perceived sleep quality improvements with the intervention, although no objective differences were measured. These findings show promise for using noise-masking digital wellness devices in noisy environments to improve sleep quality.

Background: Chronic Kidney Disease (CKD) is a global health concern and is frequently underdiagnosed due to its subtle initial symptoms, contributing to increasing morbidity and mortality. A comprehensive understanding of CKD comorbidities could lead to the identification of risk-groups, more effective treatment and improved patient outcomes. Our research presents a two-fold objective: developing an effective machine learning (ML) workflow for text classification and entity relation extraction and assembling a broad list of diseases influencing CKD development and progression.

Methods: We analysed 39,680 abstracts with CKD in the title from the Embase library. Abstracts about a disease affecting CKD development and/or progression were selected by multiple ML classifiers trained on a human-labelled sample. The best classifier was further trained with active learning. Disease names in question were extracted from the selected abstracts using a novel entity relation extraction methodology. The resulting disease list and their corresponding abstracts were manually checked and a final disease list was created.

Findings: The SVM model gave the best results and was chosen for further training with active learning. This optimised ML workflow enabled us to discern 68 comorbidities across 15 ICD-10 disease groups contributing to CKD progression or development. The reading of the ML-selected abstracts showed that some diseases have direct causal effect on CKD, while others, like schizophrenia, has indirect causal effect on CKD.

Interpretation: These findings have the potential to guide future CKD investigations, by facilitating the inclusion of a broader array of comorbidities in CKD prognostic models. Ultimately, our study enhances understanding of prognostic comorbidities and supports clinical practice by enabling improved patient monitoring, preventive strategies, and early detection for individuals at higher CKD development or progression risk.

Integrating advanced technologies like medical devices in healthcare is crucial for addressing critical challenges, but patient safety must remain the top priority. In modern clinical settings, medical devices, such as infusion devices used to administer fluids and drugs, carry risks from use errors, requiring a focus on usability and human factors engineering (HFE). Despite the significance of integrating HFE into technology selection processes, it is often overlooked. A review of five key articles demonstrates how applying HFE principles in procurement strategies can enhance device usability and patient safety. Although designed to reduce medication errors, infusion devices can still cause over-infusion or delays, indicating the need for improved safety features that must be considered in the context of sociotechnical systems. The reviewed studies suggest incorporating HFE in design, purchasing, and implementation to address these issues. The studies highlight various HFE methodologies, showing a wide variation in design, deployment, interpretation, and reporting. This comprehensive examination underscores the importance of standardised evaluations to ensure safer and more effective medical devices, emphasizing the essential role of HFE in advancing patient safety within healthcare settings.

Introduction: Artificial intelligence and machine learning are popular interconnected technologies. AI chatbots like ChatGPT and Gemini show considerable promise in medical inquiries. This scoping review aims to assess the accuracy and response length (in characters) of ChatGPT and Gemini in medical applications.

Methods: The eligible databases were searched to find studies published in English from January 1 to October 20, 2023. The inclusion criteria consisted of studies that focused on using AI in medicine and assessed outcomes based on the accuracy and character count (length) of ChatGPT and Gemini. Data collected from the studies included the first author's name, the country where the study was conducted, the type of study design, publication year, sample size, medical speciality, and the accuracy and response length.

Results: The initial search identified 64 papers, with 11 meeting the inclusion criteria, involving 1,177 samples. ChatGPT showed higher accuracy in radiology (87.43% vs. Gemini's 71%) and shorter responses (907 vs. 1,428 characters). Similar trends were noted in other specialties. However, Gemini outperformed ChatGPT in emergency scenarios (87% vs. 77%) and in renal diets with low potassium and high phosphorus (79% vs. 60% and 100% vs. 77%). Statistical analysis confirms that ChatGPT has greater accuracy and shorter responses than Gemini in medical studies, with a p-value of <.001 for both metrics.

Conclusion: This Scoping review suggests that ChatGPT may demonstrate higher accuracy and provide shorter responses than Gemini in medical studies.