Frontiers in digital health最新文献

Introduction: Effective rehabilitation is essential to prevent physical and cognitive decline, but many stroke patients face challenges to maintain rehabilitation efforts after hospital discharge. Telerehabilitation, delivered via digital platforms, represents a promising approach for intensive continuation of stroke rehabilitation after discharge. The Swiss tele-assisted rehabilitation and training program (START), delivered through the Blended Clinic mobile application, seeks to support patients to start during inpatient rehabilitation, continue during the transition to the home environment, continue until outpatient rehabilitation starts and beyond. The study aims to evaluate feasibility, safety and performance of the START program on the Blended Clinic platform during inpatient, transition, and outpatient rehabilitation with patients in the early and late subacute phase after a stroke. Furthermore, patients' functional status, mobility and activity level, and health-related quality of life are monitored.

Methods: This single-center feasibility trial with three measurement sessions will include 40 patients, who will be introduced to START during their inpatient rehabilitation. Patients will continue for 12 weeks post-discharge. For the feasibility assessment, process-, training- and mHealth-related parameter will be evaluated, which include recruitment rate, process-evaluation, safety, adherence, drop-out rate, stability and maintenance of the system, usability, quality, satisfaction, user and program experience, and perceived change. Secondary outcomes will focus on motor function, mobility, quality of life, activity level, heart rate, blood pressure, and performance-based measures.

Discussion: The study's strengths include its foundation in previous usability analyses, which informed refinements to the START program. The study's design is based on the ISO 14155 standard, ensuring high standards for medical device research and supporting the future certification of the START program on the Blended Clinic platform. Potential challenges include patient self-reporting via the mobile application and barriers related to technology use among older adults and older mobile devices. Additionally, the availability of coaching is limited to business hours, which may affect adherence. Despite these challenges, the study's findings will provide insights into the feasibility of mobile-based telerehabilitation and guide the design of a future randomized controlled trial.

Clinical trial registration: The study is registered with the Swiss National Clinical Trial Portal (SNCTP000005943), EUDAMED (CIV-CH-24-05-046954), and clinicaltrils.gov (NCT06449612).

Background: Just-In-Time Adaptive Interventions (JITAIs) are interventions designed to deliver timely tailored support by adjusting to changes in users' internal states and external contexts. To accomplish this, JITAIs often apply complex analytic techniques, such as machine learning or Bayesian algorithms to real- or near-time data acquired from smartphones and other sensors. Given the idiosyncratic, dynamic, and context dependent nature of mental health symptoms, JITAIs hold promise for mental health. However, the development of JITAIs is still in the early stages and is complex due to the multifactorial nature of JITAIs. Considering this complexity, Nahum-Shani et al. developed a conceptual framework for developing and testing JITAIs for health-related problems. This review evaluates the current state of JITAIs in the field of mental health including their alignment with Nahum-Shani et al.'s framework.

Methods: Nine databases were systematically searched in August 2023. Protocol or empirical studies self-identifying their intervention as a "JITAI" targeting mental health were included in the qualitative synthesis if they were published in peer-reviewed journals and written in English.

Results: Of the 1,419 records initially screened, 9 papers reporting on 5 JITAIs were included (sample size range: 5 to an expected 264). Two JITAIs were for bulimia nervosa, one for depression, one for insomnia, and one for maternal prenatal stress. Although most core components of Nahum-Shani's et al.'s framework were incorporated in the JITAIs, essential elements (e.g., adaptivity and receptivity) within the core components were missing and the core components were only partly substantiated by empirical evidence (e.g., interventions were supported, but the decision rules and points were not). Complex analytical techniques such as data from passive monitoring of individuals' states and contexts were hardly used. Regarding the current state of studies, initial findings on usability, feasibility, and effectiveness appear positive.

Conclusions: JITAIs for mental health are still in their early stages of development, with opportunities for improvement in both development and testing. For future development, it is recommended that developers utilize complex analytical techniques that can handle real-or near-time data such as machine learning, passive monitoring, and conduct further research into empirical-based decision rules and points for optimization in terms of enhanced effectiveness and user-engagement.

Introduction: Artificial intelligence (AI) models trained on audio data may have the potential to rapidly perform clinical tasks, enhancing medical decision-making and potentially improving outcomes through early detection. Existing technologies depend on limited datasets collected with expensive recording equipment in high-income countries, which challenges deployment in resource-constrained, high-volume settings where audio data may have a profound impact on health equity.

Methods: This report introduces a novel protocol for audio data collection and a corresponding application that captures health information through guided questions.

Results: To demonstrate the potential of Voice EHR as a biomarker of health, initial experiments on data quality and multiple case studies are presented in this report. Large language models (LLMs) were used to compare transcribed Voice EHR data with data (from the same patients) collected through conventional techniques like multiple choice questions. Information contained in the Voice EHR samples was consistently rated as equally or more relevant to a health evaluation.

Discussion: The HEAR application facilitates the collection of an audio electronic health record ("Voice EHR") that may contain complex biomarkers of health from conventional voice/respiratory features, speech patterns, and spoken language with semantic meaning and longitudinal context-potentially compensating for the typical limitations of unimodal clinical datasets.

Background: Observational health data are collected in different formats and structures, making it challenging to analyze with common tools. The Observational Medical Outcome Partnership (OMOP) Common Data Model (CDM) is a standardized data model that can harmonize observational health data.

Objective: This paper demonstrates the use of the OMOP CDM to harmonize COVID-19 sero-surveillance data from the Nairobi Urban Health and Demographic Surveillance System (HDSS).

Methods: In this study, we extracted data from the Nairobi Urban HDSS COVID-19 sero-surveillance database and mapped it to the OMOP CDM. We used open-source Observational Health Data Sciences and Informatics (OHDSI) tools like WhiteRabbit, RabbitInAHat, and USAGI. The steps included data profiling (scanning), mapping the vocabularies using the offline USAGI and online ATHENA, and designing the extract, transform, and load (ETL) process using RabbitInAHat. The ETL process was implemented using Pentaho Data Integration community edition software and structured query language (SQL). The target OMOP CDM can now be used to analyze the prevalence of COVID-19 antibodies in the Nairobi Urban HDSS population.

Results: We successfully mapped the Nairobi Urban HDSS COVID-19 sero-surveillance data to the OMOP CDM. The standardized dataset included information on demographics, COVID-19 symptoms, vaccination, and COVID-19 antibody test results.

Conclusions: The OMOP CDM is a valuable tool for harmonizing observational health data. Using the OMOP CDM facilitates the sharing and analysis of observational health data, leading to a better understanding of disease conditions and trends and improving evidence-based population health strategies.

Background: The COVID-19 pandemic has catalysed the emergence of digital solutions in all areas of medicine. Our prior study on the digital health related experiences and opinions of Hungarian physicians highlights the crucial role of age in shaping attitudes towards digital health solutions among medical doctors. Our aim was to examine how under 35-year-old Hungarian physicians relate to digital technologies, the advantages and disadvantages they perceive, and how they would like to incorporate these technologies into their everyday medical practice.

Methods: As part of the "E-physicians and E-patients in Hungary" study, we conducted an online representative survey among medical practitioners in Hungary between July 2021 and May 2022 (n = 1,774). The main target group of our research were physicians under 35 years of age: n = 399 (25.3%). Besides descriptive statistical analyses, cluster analysis and binary logistic regression were applied to analyse the digital health related attitudes of the young age group.

Results: Our cluster analysis confirmed that younger doctors perceived more advantages (on average 7.07 items vs. 8.52 items) and disadvantages (on average 4.06 vs. 4.42) of digital health solutions. They also demonstrated greater familiarity with (8.27 vs. 9.79) and use of (1.94 vs. 2.66) a broader spectrum of technologies. Proficiency and active utilization of diverse technologies correlates with a more comprehensive understanding of both pros and cons, as well as a more realistic self-assessment of areas of further improvement. Doctors under 35 years express a notable demand for significantly increased incentives, both in terms of knowledge transfer/training and infrastructure incentives. Multivariate analyses revealed that young doctors, compared to their older counterparts, perceived enhanced patient adherence as one of the greatest benefits of digital health solutions. Additionally, young doctors expect that digital health solutions could reduce burnout.

Conclusion: Our results underscore the inevitable transformation of the 21st-century physician role: the success of digital health solutions hinges on active patient involvement and management, which requires proper patient education and professional support in navigating the digital space. Digital health solutions can be a bridge between different generations of doctors, where young people can help their older colleagues navigate the digital world.

Background: The growth of the use of artificial intelligence (AI) and robotic solutions in healthcare is accompanied by high expectations for improved efficiency and quality of services. However, the use of such technologies can be a source of anxiety for patients whose expectations and experiences with such technology differ from medical staff's. This study assessed attitudes toward AI and robots in delivering health services and performing various tasks in medicine and related fields in Polish society.

Methods: 50 semistructured in-depth interviews were conducted with participants of diversified socio-demographic profiles. The interviewees were initially recruited for the interviews in a convenience sample; then, the process was continued using the snowballing technique. The interviews were transcribed and analyzed using the MAXQDA Analytics Pro 2022 program (release 22.7.0). An interpretative approach to qualitative content analysis was applied to the responses to the research questions.

Results: The analysis of interviews yielded three main themes: positive and negative perceptions of the use of AI and robots in healthcare and ontological concerns about AI, which went beyond objections about the usefulness of the technology. Positive attitudes toward AI and robots were associated with overall higher trust in technology, the need to adequately respond to demographic challenges, and the conviction that AI and robots can lower the workload of medical personnel. Negative attitudes originated from convictions regarding unreliability and the lack of proper technological and political control over AI; an equally important topic was the inability of artificial entities to feel and express emotions. The third theme was that the potential interaction with machines equipped with human-like traits was a source of insecurity.

Conclusions: The study showed that patients' attitudes toward AI and robots in healthcare vary according to their trust in technology, their recognition of urgent problems in healthcare (staff workload, time of diagnosis), and their beliefs regarding the reliability and functioning of new technologies. Emotional concerns about contact with artificial entities looking or performing like humans are also important to respondents' attitudes.

Background: Ukrainians staying in Sweden under the EU mass refugee directive may face challenges due to traumas caused by the invasion that started on February 24, 2022. Part of an European Social Fund (ESF) project, our study showed that a brief trauma-focused group intervention onsite helped to increase health and mental-health literacy. The intervention has not yet been adapted online.

Methods: This pilot study during six months aimed to investigate the feasibility, acceptability and outcome in perceived trust, anxiety/stress, and perceived health after this brief trauma-focused group intervention online. A second aim was to observe perceived acceptability of the group intervention with different ways of online intervention. Local coaches, interpreters, the authors, and local experts participated. A mixed-methods design with participatory methodology and evaluation were used. Data was collected with a short questionnaire in Ukrainian. Additionally, at the end of each set, we orally asked about perceived trust and integrity. There were six sets of five group sessions per set, a total of 30 sessions. Each group met online five times for 2 h, a total of 10 h excluding pre- and post-assessment. Breathing exercises sought to reduce stress among the participants.

Results: The group intervention had both strengths and limitations. Baseline data were obtained from 136 participants, mostly females (75.7%). Answers to pre- and post-questionnaires showed that perceived anxiety/stress was significantly reduced (N = 91, chi-2 20.648, df = 6, p < .02). Perceived health significantly improved between pre- (mean 63.6) and post (77.2) (N = 77, t = -8.08, df = 66, p < .001). Older participants were vulnerable with higher stress and lower mean perceived health after the intervention. Four out of ten needed individual psychosocial support online.The participants' open questions were analyzed with qualitative content analysis, giving five general categories and 25 sub-categories and the theme "Strong efforts to cope with Swedish system".

Conclusion: Trust and reduced anxiety level changed after the intervention and a combination online of small, closed group meetings with the possibility of personal acquaintance, trust and individual follow-up psychosocial support for those in need to be paid attention to for future refugee support services, particular an online format.

Background: The Internet allows cancer patients to access information about their disease at any time. However, the quality of online information varies widely and is often inaccurate or does not provide all the details patients need to make informed decisions. Additionally, patients' often limited ability to find and evaluate cancer-related online information can lead to misinformation.

Objective: An interactive e-learning environment to promote digital health literacy will be developed and evaluated for effectiveness.

Primary hypothesis: Cancer patients who use the e-learning environment (IG1.1-IG1.3) or the content of the environment as a non-interactive PDF file (IG2) will show greater improvement in their digital health literacy from baseline to 8 weeks after baseline compared to patients who receive no such intervention, but are referred to a standard information brochure.

Methods: The hypothesis will be tested in a stratified randomized controlled superiority trial with five parallel groups and the primary endpoint of digital health literacy. In an e-learning environment, patients will learn strategies to use when searching for reliable cancer-related online information. During development, a prototype will be refined through focus groups and tested for usability by experts and patients. 660 cancer patients will be recruited using convenience sampling and randomly assigned in a 3:1:1 ratio to IG1.1-IG1.3 (three variants of the environment), IG2, or the control group. Two thirds of the 660 participants will be recruited through the German Cancer Information Service (CIS) and one third through non-CIS routes. Allocation will follow stratified randomization, accounting for recruitment route (CIS vs. non-CIS) and cancer type (breast cancer vs. other cancers), with variable block length. The primary outcome, digital health literacy, will be measured at baseline, 2 weeks, and 8 weeks after baseline.

Conclusion: If the results support the primary hypothesis, then the e-learning environment could empower patients to retrieve more reliable information about their disease. Concerns about the generalizability of the results, since a disproportionate number of inquiries to the CIS come from breast cancer patients, are addressed by a proportionally stratified randomization strategy and diversified recruitment routes.

Radiology departments are under increasing pressure to meet the demand for timely and accurate diagnostics, especially with chest x-rays, a key modality for pulmonary condition assessment. Producing comprehensive and accurate radiological reports is a time-consuming process prone to errors, particularly in high-volume clinical environments. Automated report generation plays a crucial role in alleviating radiologists' workload, improving diagnostic accuracy, and ensuring consistency. This paper introduces ChestX-Transcribe, a multimodal transformer model that combines the Swin Transformer for extracting high-resolution visual features with DistilGPT for generating clinically relevant, semantically rich medical reports. Trained on the Indiana University Chest x-ray dataset, ChestX-Transcribe demonstrates state-of-the-art performance across BLEU, ROUGE, and METEOR metrics, outperforming prior models in producing clinically meaningful reports. However, the reliance on the Indiana University dataset introduces potential limitations, including selection bias, as the dataset is collected from specific hospitals within the Indiana Network for Patient Care. This may result in underrepresentation of certain demographics or conditions not prevalent in those healthcare settings, potentially skewing model predictions when applied to more diverse populations or different clinical environments. Additionally, the ethical implications of handling sensitive medical data, including patient privacy and data security, are considered. Despite these challenges, ChestX-Transcribe shows promising potential for enhancing real-world radiology workflows by automating the creation of medical reports, reducing diagnostic errors, and improving efficiency. The findings highlight the transformative potential of multimodal transformers in healthcare, with future work focusing on improving model generalizability and optimizing clinical integration.