Frontiers in digital health最新文献

Background: Video-based education offers opportunities to enhance patients' medical literacy and to reduce anxiety and hesitation for patients undergoing diagnostic procedures such as lumbar puncture (LP). Multiple studies centered on LP education have demonstrated that video-based education can reduce anxiety regarding possible adverse events, while increasing literacy regarding the procedure itself for clinical purposes. Our study sought to assess the impact of video-based education on knowledge of and willingness to undergo an LP among older people with HIV (PWH).

Methods: We enrolled PWH age ≥ 50 years who regularly attend our Infectious Diseases clinic between March 3 and November 16, 2023. Participants watched a patient-centered educational video explaining the LP procedure and completed a questionnaire both pre- and post-video assessing demographics, general awareness and prior experience with an LP, specific knowledge, attitudes and perceptions toward an LP and willingness to undergo an LP.

Results: Our study included 99 PWH with mean (standard deviation, SD) age of 58.8 (5.7) years, one-third females and 60% African American/Black race. After watching the video, participants were significantly more likely to correctly identify technical details of the procedure (excluding those who had previously had an LP, 83.7% pre-video vs. 95.9% post-video) and common complications of an LP; agree that LPs can result in back pain (p < 0.001) and headaches (p < 0.001). There was no significant difference in participants' willingness to undergo an LP for diagnostic or research purposes. Only 5% said that they would never have an LP under any circumstance after watching the video.

Conclusions: Other educational interventions, such as in-person demonstrations or models, may help mitigate fears of LP. Our study provides important insight into the knowledge and perceptions of PWH when asked to undergo an LP and demonstrates that video-based education may not be sufficient to mitigate fears surrounding LP procedures, or a lack of interest or time for participating in an LP.

Background: Despite the effectiveness and potential of digital mental health interventions (DMHIs) in routine care, their uptake remains low. In Germany, digital mental health applications (DiGA), certified as low-risk medical devices, can be prescribed by healthcare professionals (HCPs) to support the treatment of mental health conditions. The objective of this proof-of-concept study was to evaluate the feasibility of using the Multiphase Optimization Strategy (MOST) framework when assessing implementation strategies.

Methods: We tested the feasibility of the MOST by employing a 2⁴ exploratory retrospective factorial design on existing data. We assessed the impact of the implementation strategies (calls, online meetings, arranged and walk-in on-site meetings) individually and in combination, on the number of DiGA activations in a non-randomized design. Data from N = 24,817 HCPs were analyzed using non-parametric tests.

Results: The results primarily demonstrated the feasibility of applying the MOST to a non-randomized setting. Furthermore, analyses indicated significant differences between the groups of HCPs receiving specific implementation strategies [χ² (15) = 1,665.2, p < .001, ɛ ² = 0.07]. Combinations of implementation strategies were associated with significantly more DiGA activations. For example, combinations of arranged and walk-in on-site meetings showed higher activation numbers (e.g., Z = 10.60, p < 0.001, χ²  = 1,665.24) compared to those receiving other strategies. We found a moderate positive correlation between the number of strategies used and activation numbers (r = 0.30, p < 0.001).

Discussion and limitations: These findings support the feasibility of using the MOST to evaluate implementation strategies in digital mental health care. It also gives an exploratory example on how to conduct factorial designs with information on implementation strategies. However, limitations such as non-random assignment, underpowered analysis, and varying approaches to HCPs affect the robustness and generalizability of the results. Despite these limitations, the results demonstrate that the MOST is a viable method for assessing implementation strategies, highlighting the importance of planning and optimizing strategies before their implementation. By addressing these limitations, healthcare providers and policymakers can enhance the adoption of digital health innovations, ultimately improving access to mental health care for a broader population.

This study aims to address the critical issue of emergency department (ED) overcrowding, which negatively affects patient outcomes, wait times, and resource efficiency. Accurate prediction of ED length of stay (LOS) can streamline operations and improve care delivery. We utilized the MIMIC IV-ED dataset, comprising over 400,000 patient records, to classify ED LOS into short (≤4.5 hours) and long (>4.5 hours) categories. Using machine learning models, including Gradient Boosting (GB), Random Forest (RF), Logistic Regression (LR), and Multilayer Perceptron (MLP), we identified GB as the best performing model outperforming the other models with an AUC of 0.730, accuracy of 69.93%, sensitivity of 88.20%, and specificity of 40.95% on the original dataset. In the balanced dataset, GB had an AUC of 0.729, accuracy of 68.86%, sensitivity of 75.39%, and specificity of 58.59%. To enhance interpretability, a novel rule extraction method for GB model was implemented using relevant important predictors, such as triage acuity, comorbidity scores, and arrival methods. By combining predictive analytics with interpretable rule-based methods, this research provides actionable insights for optimizing patient flow and resource allocation. The findings highlight the importance of transparency in machine learning applications for healthcare, paving the way for future improvements in model performance and clinical adoption.

The enigma of smartphone addiction (SA) has plagued academics for the last decade, now scholars believed this behaviour might affect physical and mental wellbeing. SA has become a complex problem, yet to date, there is limited research investigating the predictors of SA and its effect on "health-related quality of life (HRQoL)". This study aimed to address this gap. The data was gathered from a convenience sample of 440 young adults completed between July 2021 and February 2022 through online survey in Bangladesh. On Logistic regression, after controlling for socio-demographic variables; friend support, process, social and compulsive usage were determined as significant predictors of SA. Those who were smartphone addicted were more presumably to have a lower quality of life. This study has significant implications for designing prevention pro-grams and policy development in relation to predictors of SA and its effect on HRQoL.

Introduction: Digital mental health treatments (DMHTs) have begun to be implemented in some healthcare systems across the United States. These implementations are conducted as business arrangements. Thus, information on successful or unsuccessful implementations is not published or disseminated. This slows progress, as experiences and learnings are siloed within each organization, hindering or preventing learning across implementations and slowing the progress. To address this, the Society for Digital Mental Health established a DMHT Implementation Workgroup, with the goal of developing a DMHT Playbook that describes current best practices in DMHT implementation in American healthcare settings.

Methods: The workgroup was comprised of representatives from 7 healthcare systems and 10 DMHT companies that have conducted implementations, along with other stakeholders and technical experts. The workgroup met virtually to discuss implementation of effective DMHT implementation processes and inform the development of an interview guide, which was then administered to another 20 key opinion leaders with DMHT implementation experience. Concepts and thematic constructs were extracted by experts in qualitative data analysis. These findings were discussed and refined by the Workgroup based on the Workgroup's experience.

Results: The resulting playbook includes detailed methods, processes and procedures, representing practices that have been successful for implementing DMHTs in healthcare settings.

Discussion: The workgroup recognizes that DMHT implementation is a rapidly evolving field. The successful practices for DMHT implementation described in this playbook may be useful for improving the efficiency of future DMHT implementations in American healthcare systems. However, the authors caution that as the field rapidly evolves, successful implementation practices will likely evolve as well.

Post-traumatic stress disorder (PTSD) is a psychiatric condition producing considerable distress, dysfunction, and impairment in affected individuals. While various forms of psychotherapy are commonly utilized in PTSD treatment, the known neurological pathologies associated with PTSD are insufficiently addressed by these conventional approaches. Heart rate variability biofeedback (HRV-BFB) is a promising tool for correcting autonomic dysfunction in PTSD, with subsequent changes in clinically significant outcome measures. This paper outlines a systematic approach for the development, distribution, and implementation of a prescription at-home HRV-BFB digital therapeutic. We provide recommendations for evidence-generation strategies and propose appropriate regulatory pathways within existing frameworks. Widespread access to HRV-BFB could potentially reduce the distress, disability, and healthcare burden associated with PTSD. Promoting HRV-BFB as a primary intervention could also serve to reduce the stigma associated with "mental" illness and increase health literacy regarding the neuroimmune impacts of psychosocial factors. These processes might in turn improve treatment-seeking, adherence, and supported self-management of these conditions.

Introduction: The world's population is aging at a rapid rate. Nursing homes are needed to care for an increasing number of older adults. Palliative care can improve the quality of life of nursing home residents. Artificial Intelligence can be used to improve palliative care services. The aim of this scoping review is to synthesize research surrounding AI-based palliative care interventions in nursing homes.

Methods: A PRISMA-ScR scoping review was carried out using modified guidelines specifically designed for computer science research. A wide range of keywords are considered in searching six databases, including IEEE, ACM, and SpringerLink.

Results: We screened 3255 articles for inclusion after duplicate removal. 3175 articles were excluded during title and abstract screening. A further 61 articles were excluded during the full-text screening stage. We included 19 articles in our analysis. Studies either focus on intelligent physical systems or decision support systems. There is a clear divide between the two types of technologies. There are key issues to address in future research surrounding palliative definitions, data accessibility, and stakeholder involvement.

Discussion: This paper presents the first review to consolidate research on palliative care interventions in nursing homes. The findings of this review indicate that integrated intelligent physical systems and decision support systems have yet to be explored. A broad range of machine learning solutions remain unused within the context of nursing home palliative care. These findings are of relevance to both nurses and computer scientists, who may use this review to reflect on their own practices when developing such technology.

Objective: Our study aims to explore the health service issues of public concern through analyzing the basic characteristics of callers and information from the health hotline in Shanghai. The findings of this study will provide a reference to relevant government departments and assist the government in optimizing the allocation of health resources.

Methods: Our research utilized 16,962 original work orders from the 12,320 health hotline, collected since 2015. We applied natural language processing (NLP) to analyze the content of these work orders, facilitating effective text mining and information extraction. Initially, we performed data cleaning to remove irrelevant information and protect caller privacy by anonymizing personal details. This cleaned data was then organized into a structured database for further analysis. Using text mining, we examined various aspects of the calls, including duration, purpose, and topics discussed, to identify patterns and themes that emerged.

Results: The calls were categorized into four main groups: complaints, suggestions, inquiries, and requests for assistance. Complaints were the most frequent category, totaling 8,669 (51.11%), followed by help-seeking at 3,335 (19.66%), consultations at 2,727 (16.08%), and comments and suggestions at 1,484 (8.75%). The analysis revealed that men made 6,689 (56.88%), surpassing the 5,071 (43.12%) from women. Additionally, calls from parents numbered 2,126 (56.84%), slightly exceeding the 1,614 (43.16%) from children. The top 10 health service concerns identified in Shanghai included medical staff attitudes, medications, fees, registration, family planning, medical disputes, ambulance services, environmental health, illegal medical practices, and immunization.

Conclusions: This study not only identifies critical issues within the Shanghai health service system but also offers actionable insights to inform targeted policy interventions. The high volume of complaints regarding service attitudes and medical expenses underscores the need for stronger policies to improve patient-provider communication and ensure transparency and fairness in healthcare costs. Additionally, the data reveals considerable public concern about the availability and quality of medical services, suggesting that existing policies on resource allocation and service delivery may not adequately meet population needs. The methodologies employed here can be applied to other urban health contexts, providing a valuable framework for improving public health strategies globally.

Introduction: The increasing prevalence of dementia in aging populations necessitates effective and accessible cognitive screening tools. This study aimed to evaluate the feasibility and reliability of a newly developed mobile app for detecting and screening mild cognitive impairment (MCI).

Methods: The mobile app, developed by LifeQuest Co., Ltd. (Minato-ku, Tokyo), is an original tool inspired by the Japanese version of the Montreal Cognitive Assessment (MoCA-J). A prospective observational study was conducted with 20 participants, including healthy individuals, MCI patients, and those with mild to moderate-severe dementia. Participants completed both the mobile app and the MoCA-J in a randomized order within a two-week period, with a minimum one-day interval between tests.

Results and conclusion: The intraclass correlation coefficient (ICC) between the mobile app and the MoCA-J was 0.956 (95% CI: 0.89-0.983), demonstrating a very high level of correlation. All participants successfully completed the mobile app assessment, highlighting its feasibility across various cognitive levels. Although minor technical issues and usability challenges were identified, the results support the mobile app as a reliable and user-friendly alternative for cognitive screening. Further studies with larger sample sizes are necessary to validate these findings and refine the app for broader clinical use.