Frontiers in digital health最新文献

Objective: Artificial intelligence (AI) is revolutionizing healthcare, but less is known about how it may facilitate methodological innovations in research settings. In this manuscript, we describe a novel use of AI in summarizing and reporting qualitative data generated from an expert panel discussion about the role of electronic health records (EHRs) in implementation science.

Materials and methods: 15 implementation scientists participated in an hour-long expert panel discussion addressing how EHRs can support implementation strategies, measure implementation outcomes, and influence implementation science. Notes from the discussion were synthesized by ChatGPT (a large language model-LLM) to generate a manuscript summarizing the discussion, which was later revised by participants. We also surveyed participants on their experience with the process.

Results: Panelists identified implementation strategies and outcome measures that can be readily supported by EHRs and noted that implementation science will need to evolve to assess future EHR advancements. The ChatGPT-generated summary of the panel discussion was generally regarded as an efficient means to offer a high-level overview of the discussion, although participants felt it lacked nuance and context. Extensive editing was required to contextualize the LLM-generated text and situate it in relevant literature.

Discussion and conclusions: Our qualitative findings highlight the central role EHRs can play in supporting implementation science, which may require additional informatics and implementation expertise and a different way to think about the combined fields. Our experience using ChatGPT as a research methods innovation was mixed and underscores the need for close supervision and attentive human involvement.

Background: Remote care usefulness and climate change co-benefits should be addressed simultaneously to incentivize political action.

Objectives: To assess the changes in healthcare consumption, lung function and greenhouse gas (GHG) emissions during the COVID-19 pandemic in Dutch cystic fibrosis (CF) care.

Design: Retrospective multicentre observational study in five Dutch CF centres.

Methods: Eighty-one participants were included. Healthcare consumption was described alongside the COVID-19 Stringency Index (2019-2022). Travel related GHG emissions were calculated for every clinic visit. Changes in percentage predicted Forced Expiratory Volume in one second (ppFEV1) were assessed using a paired-samples T-test.

Results: Healthcare consumption patterns followed COVID-19 public health measure stringency but returned back to the "old normal". Emission of 5.450, 3 kg of carbon dioxide equivalents were avoided while quality of care was relatively preserved. ppFEV1 declined as expected (ΔMeans 3.69%, 95%CI 2.11-5.28).

Conclusion: Remote monitoring of lung function and symptoms and teleconsultations in CF can reduce GHG emissions while maintaining quality of care. As health sectors constitute a large share of national climate change footprints, digital health can partly alleviate this burden by reducing private travel.

Background: Facial palsy after vestibular schwannoma surgery is temporary in many cases but can significantly affect patients' quality of life. Physical training-initially guided and subsequently performed by the patient-is of paramount importance for recovery of facial nerve function. The introduction of medical application software (apps) might improve therapy by maintaining motivation for daily home-based training and surveilling patients' rehabilitation progress.

Methods: We developed a mobile app, "FACEsemper", for home-based facial nerve rehabilitation. This app guides patients through a daily training program comprising six variable exercises, each performed in three repetitions. The app allows the user to customize the exercise intensity for different facial areas and includes a reminder function for daily training. Additional features include photo documentation, a calendar function, training report generation, and the possibility of direct communication with the attending physician. The app's usability was prospectively investigated with 27 subjects, including 8 physicians, 9 patients with facial palsy and 10 healthy subjects, over a two-week period. Usability was assessed using various self-rating questionnaires (i.e., mHealth App Usability Questionnaire, MAUQ; System Usability Scale, SUS; Visual Aesthetics of Apps Inventory, VisAAI) and scores were compared across the groups.

Results: The participants reported an average smartphone use of 12.19 years and completed a mean number of 290 ± 163 facial exercises during the study period. Patients used the app significantly more frequently than the other two groups (p = 0.017). The average total scores of the questionnaires were: MAUQ 5.67/7, SUS 89.6/100, VisAAI 5.88/7 and specific rating 6.13/7. In particular, the simplicity of use and craftsmanship of the app were rated very highly. Usability scores did not significantly differ between groups. A primary limitation identified was malfunction of the daily reminder feature in some Android versions.

Conclusion: This usability study demonstrated a positive user experience and excellent usability of the FACEsemper app. However, some limitations and areas for improvement were identified. As a next step, the app should be evaluated in a large patient cohort with facial palsy to determine its potential medical benefits for facial rehabilitation compared to traditional training methods.

Digital health research often relies on case vignettes (descriptions of fictitious or real patients) to navigate ethical and practical challenges. Despite their utility, the quality and lack of standardization of these vignettes has often been criticized, especially in studies on symptom-assessment applications (SAAs) and self-triage decision-making. To address this, our paper introduces a method to refine an existing set of vignettes, drawing on principles from classical test theory. First, we removed any vignette with an item difficulty of zero and an item-total correlation below zero. Second, we stratified the remaining vignettes to reflect the natural base rates of symptoms that SAAs are typically approached with, selecting those vignettes with the highest item-total correlation in each quota. Although this two-step procedure reduced the size of the original vignette set by 40%, comparing self-triage performance on the reduced and the original vignette sets, we found a strong correlation (r = 0.747 to r = 0.997, p < .001). This indicates that using our refinement method helps identifying vignettes with high predictive power of an agent's self-triage performance while simultaneously increasing cost-efficiency of vignette-based evaluation studies. This might ultimately lead to higher research quality and more reliable results.

Background: The use of online information and communication is globally increasing in the healthcare sector. In addition to known benefits in other medical fields, possible specific potentials of eHealth lie in the monitoring of oncological patients undergoing outpatient therapy. Specifically, the treatment with immune checkpoint inhibitors (ICI) requires intensive monitoring due to various possible negative side effects. The present study explores cancer patients' perspectives on eHealth and demonstrates how eHealth applications, from the patients' point of view, can contribute to further improving outpatient immunotherapy.

Methods and findings: Our multicenter study was executed at the university hospitals in Bonn and Aachen. A structured questionnaire was distributed to patients receiving outpatient immunotherapy. Contents addressed were (1) the patients' attitude towards eHealth applications, (2) the use of modern information and communications technologies (ICT) in (2a) everyday life and (2b) health-related information search including eHealth literacy, (3) the use of internet-enabled devices as well as (4) socio-demographic data. 164 patients were included in the study, of whom 39.0% were female and 61.0% male and the average age was 62.8 years. Overall, there was a high distribution of internet-enabled devices for everyday use and a great interest in integrating eHealth applications into outpatient immunotherapy. The assessment of eHealth potentials significantly depended on age. The younger participants demonstrated a broader use of modern ICT and a higher affinity for its use in outpatient immunotherapy. In some aspects, level of education and gender were also relevant factors influencing the patients' view on eHealth.

Conclusion: This study demonstrates the potential for further integration of eHealth applications into outpatient immunotherapy from the patients' perspective. It indicates a dependency on age and educational level for the further integration of eHealth into patient care in oncology. Due to particular patient needs regarding age, level of education, gender and other subgroups, specific education and training as well as target-group specific digital health interventions are necessary to fully utilize the potentials of eHealth for outpatient immunotherapy. Future studies are required to specifically address target-group specific usability of eHealth applications and eHealth literacy, as well as to address information security and data protection.

In the past decade, the progress of traditional bioprocess optimization technique has lagged far behind the rapid development of synthetic biology, which has hindered the industrialization process of synthetic biology achievements. Recently, more and more advanced equipment and sensors have been applied for bioprocess online inspection to improve the understanding and optimization efficiency of the process. This has resulted in large amounts of process data from various sources with different communication protocols and data formats, requiring the development of techniques for integration and fusion of these heterogeneous data. Here we describe a multi-source fusion platform (Biofuser) that is designed to collect and process multi-source heterogeneous data. Biofuser integrates various data to a unique format that facilitates data visualization, further analysis, model construction, and automatic process control. Moreover, Biofuser also provides additional APIs that support machine learning or deep learning using the integrated data. We illustrate the application of Biofuser with a case study on riboflavin fermentation process development, demonstrating its ability in device faulty identification, critical process factor identification, and bioprocess prediction. Biofuser has the potential to significantly enhance the development of fermentation optimization techniques and is expected to become an important infrastructure for artificial intelligent integration into bioprocess optimization, thereby promoting the development of intelligent biomanufacturing.

This article explores the intersection of healthcare accessibility and digitalisation from a rights perspective. Drawing from two illustrative cases presented to a filariasis management clinic in Puducherry, where the authors are affiliated, the article argues that despite the multiple benefits that digital health poses, there are individuals and sections of society that experience marginalisation in healthcare owing to digitalisation. Collating the data generated through the observations of the authors and the narratives of the patients, the article illustrates that such marginalisation can originate even from a relatively simple ICT adaptation like text message-based appointments, inducing health inequities. The impact of such digital marginalisation disproportionately affects vulnerable sections like older adults and the rural population in an intersectional pattern where disadvantages compound to produce larger health inequities for the affected. The study advocates for bridging the digital divide through efforts including digital literacy-when possible-and alternative solutions like dedicated helpdesks, training healthcare staff and involving NGOs and voluntary organisations to ensure health equity for the digitally marginalised.

Introduction: Extraction of Doppler-based measurements from feto-placental Doppler images is crucial in identifying vulnerable new-borns prenatally. However, this process is time-consuming, operator dependent, and prone to errors.

Methods: To address this, our study introduces an artificial intelligence (AI) enabled workflow for automating feto-placental Doppler measurements from four sites (i.e., Umbilical Artery (UA), Middle Cerebral Artery (MCA), Aortic Isthmus (AoI) and Left Ventricular Inflow and Outflow (LVIO)), involving classification and waveform delineation tasks. Derived from data from a low- and middle-income country, our approach's versatility was tested and validated using a dataset from a high-income country, showcasing its potential for standardized and accurate analysis across varied healthcare settings.

Results: The classification of Doppler views was approached through three distinct blocks: (i) a Doppler velocity amplitude-based model with an accuracy of 94%, (ii) two Convolutional Neural Networks (CNN) with accuracies of 89.2% and 67.3%, and (iii) Doppler view- and dataset-dependent confidence models to detect misclassifications with an accuracy higher than 85%. The extraction of Doppler indices utilized Doppler-view dependent CNNs coupled with post-processing techniques. Results yielded a mean absolute percentage error of 6.1 ± 4.9% (n = 682), 1.8 ± 1.5% (n = 1,480), 4.7 ± 4.0% (n = 717), 3.5 ± 3.1% (n = 1,318) for the magnitude location of the systolic peak in LVIO, UA, AoI and MCA views, respectively.

Conclusions: The developed models proved to be highly accurate in classifying Doppler views and extracting essential measurements from Doppler images. The integration of this AI-enabled workflow holds significant promise in reducing the manual workload and enhancing the efficiency of feto-placental Doppler image analysis, even for non-trained readers.

For successful health technology innovation and implementation it is key to, in an early phase, understand the problem and whether a proposed innovation is the best way to solve the problem. This review performed an initial exploration of published tools that support innovators in academic research and early stage development with awareness and guidance along the end-to-end process of development, evaluation and implementation of health technology innovations. Tools were identified from scientific literature as well as in grey literature by non-systematic searches in public research databases and search engines, and based on expert referral. A total number of 14 tools were included. Tools were classified as either readiness level tool (n = 6), questionnaire/checklist tool (n = 5) or guidance tool (n = 3). A qualitative analysis of the tools identified 5 key domains, 5 innovation phases and 3 implementation principles. All tools were mapped for (partially) addressing the identified domains, phases, and principles. The present review provides awareness of available tools and of important aspects of health technology innovation and implementation (vs. non-technological or non-health related technological innovations). Considerations for tool selection include for example the purpose of use (awareness or guidance) and the type of health technology innovation. Considerations for novel tool development include the specific challenges in academic and early stage development settings, the translation of implementation to early innovation phases, and the importance of multi-disciplinary strategic decision-making. A remaining attention point for future studies is the validation and effectiveness of (self-assessment) tools, especially in the context of support preferences and available support alternatives.