Frontiers in digital health最新文献

Introduction: The web application gp-multitool.de is based on the German clinical practice guideline "multimorbidity" and supports mutual prioritisation of treatments by GPs (general practitioners) and patients. The application facilitates sending hyperlinks to standardized assessments by email, which can be completed by patients on any suitable digital device. GPs can document clinical decisions. The tool also supports a structured medication review. Aims of this study were to consider needs and wants of the target groups in implementing the "multimorbidity" clinical practice guideline in a digital tool, and to examine themes of discussions in order to identify which aspects were considered most important for customising a digital tool.

Materials and methods: We conducted six focus groups with 32 GPs and six focus groups with 33 patients. Eight groups were conducted alongside the programming of the web application and four after finishing a prototype. GPs were recruited by mail and asked to invite up to six eligible patients from their practice to participate. Focus groups were based on semi-structured interview guides and discussed assessments, functionalities, usability and reliability of gp-multitool.de. Discussions were transcribed verbatim and analysed using content analysis.

Results: GPs wanted to avoid unnecessary and time-consuming functions and did not want to explore problems that they could not provide solutions for. For some assessments, GPs suggested simplifying scales or including residual categories. GPs and patients also addressed possible misunderstandings due to wording and discussed if some items might be too intimate or overtax patients intellectually. In most cases, participants confirmed usability, but they suggested changes in default settings and pointed out a few minor bugs that needed to be fixed. While some GPs considered data security an important topic, most patients were unconcerned with this issue and open to share their data.

Conclusion: Our study indicates that focus groups can be used to customize a digital tool according to the needs and wants of target groups and thus, improve content, functionality, usability, and reliability of digital tools. However, digital tools still need to be piloted and evaluated in everyday care. In our focus groups, study participants confirmed that gp-multitool.de can be a relevant approach for overcoming deficits in the information needed for mutual prioritisation of treatments by GPs and patients.

Background: The adoption of machine learning (ML) has been slow within the healthcare setting. We launched Pediatric Real-world Evaluative Data sciences for Clinical Transformation (PREDICT) at a pediatric hospital. Its goal was to develop, deploy, evaluate and maintain clinical ML models to improve pediatric patient outcomes using electronic health records data.

Objective: To provide examples from the PREDICT experience illustrating how common challenges with clinical ML deployment were addressed.

Materials and methods: We present common challenges in developing and deploying models in healthcare related to the following: identify clinical scenarios, establish data infrastructure and utilization, create machine learning operations and integrate into clinical workflows.

Results: We show examples of how these challenges were overcome and provide suggestions for pragmatic solutions while maintaining best practices.

Discussion: These approaches will require refinement over time as the number of deployments and experience increase.

Background: Only a minority of people with eating disorders receive evidence-based psychological treatment. This is especially true for those with recurrent binge eating because the shame that accompanies binge eating affects help seeking and there is a shortage of therapists to provide psychological treatments. Digital programme-led interventions have the potential to overcome both barriers.

Objective: This study examined the acceptability and effectiveness of a new digital programme-led intervention directly based on enhanced cognitive behaviour therapy (CBT-E), which is an empirically supported psychological treatment for eating disorders.

Methods: One hundred and ten adults with recurrent binge eating (self-reporting characteristics consistent with binge eating disorder, bulimia nervosa, and similar conditions) were recruited through an advertisement on the website of the UK's national eating disorder charity, Beat. The intervention, called Digital CBTe, comprised 12 sessions over 8-12 weeks delivered autonomously (i.e., without external support). Participants completed self-report outcome measures of eating disorder features and secondary impairment at baseline, post-intervention, and 6-month follow-up.

Results: Most participants identified as female, White, and were living in the United Kingdom. Most participants (85%) self-reported features that resembled binge eating disorder, and the rest self-reported features that resembled bulimia nervosa (8%) and atypical bulimia nervosa (7%). On average, participants reported that the onset of their eating disorder was more than twenty years ago. Sixty-three percent of the participants completed Digital CBTe (i.e., completed active treatment sessions). Those who completed all sessions and the post-intervention assessment (n = 55, 50%) reported significant decreases in binge eating, eating disorder psychopathology, and secondary impairment at post-intervention. These improvements were maintained at follow-up. Large effect sizes were observed for all these outcomes using a completer analysis and post-intervention data (d = 0.91-1.43). Significant improvements were also observed for all outcomes at post-intervention in the intent-to-treat analysis, with medium-to-large effect sizes.

Discussion: A substantial proportion of those who completed Digital CBTe and the post-intervention assessment experienced marked improvements. This provides promising data to support the conduct of a fully powered trial to test the clinical and cost-effectiveness of autonomous Digital CBTe.

Background: Fertility preferences refer to the number of children an individual would like to have, regardless of any obstacles that may stand in the way of fulfilling their aspirations. Despite the creation and application of numerous interventions, the overall fertility rate in West African nations, particularly Nigeria, is still high at 5.3% according to 2018 Nigeria Demographic and Health Survey data. Hence, this study aimed to predict the fertility preferences of reproductive age women in Nigeria using state-of-the-art machine learning techniques.

Methods: Secondary data analysis from the recent 2018 Nigeria Demographic and Health Survey dataset was employed using feature selection to identify predictors to build machine learning models. Data was thoroughly assessed for missingness and weighted to draw valid inferences. Six machine learning algorithms, namely, Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Decision Tree, Random Forest, and eXtreme Gradient Boosting, were employed on a total sample size of 37,581 in Python 3.9 version. Model performance was assessed using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). Permutation and Gini techniques were used to identify the feature's importance.

Results: Random Forest achieved the highest performance with an accuracy of 92%, precision of 94%, recall of 91%, F1-score of 92%, and AUROC of 92%. Factors influencing fertility preferences were number of children, age group, and ideal family size. Region, contraception intention, ethnicity, and spousal occupation had a moderate influence. The woman's occupation, education, and marital status had a lower impact.

Conclusion: This study highlights the potential of machine learning for analyzing complex demographic data, revealing hidden factors associated with fertility preferences among Nigerian women. In conclusion, these findings can inform more effective family planning interventions, promoting sustainable development across Nigeria.

Wearable augmented reality in neurosurgery offers significant advantages by enabling the visualization of navigation information directly on the patient, seamlessly integrating virtual data with the real surgical field. This ergonomic approach can facilitate a more intuitive understanding of spatial relationships and guidance cues, potentially reducing cognitive load and enhancing the accuracy of surgical gestures by aligning critical information with the actual anatomy in real-time. This study evaluates the benefits of a novel AR platform, VOSTARS, by comparing its targeting accuracy to that of the gold-standard electromagnetic (EM) navigation system, Medtronic StealthStation^® S7^®. Both systems were evaluated in phantom and human studies. In the phantom study, participants targeted 13 predefined landmarks using identical pointers to isolate system performance. In the human study, three facial landmarks were targeted in nine volunteers post-brain tumor surgery. The performance of the VOSTARS system was superior to that of the standard neuronavigator in both the phantom and human studies. In the phantom study, users achieved a median accuracy of 1.4 mm (IQR: 1.2 mm) with VOSTARS compared to 2.9 mm (IQR: 1.4 mm) with the standard neuronavigator. In the human study, the median targeting accuracy with VOSTARS was significantly better for selected landmarks in the outer eyebrow (3.7 mm vs. 6.6 mm, p = 0.05) and forehead (4.5 mm vs. 6.3 mm, p = 0.021). Although the difference for the pronasal point was not statistically significant (2.7 mm vs. 3.5 mm, p = 0.123), the trend towards improved accuracy with VOSTARS is clear. These findings suggest that the proposed AR technology has the potential to significantly improve surgical outcomes in neurosurgery.

Introduction: The digitalization of healthcare poses a risk of exacerbating health inequalities. Dutch public libraries offer freely accessible e-health courses given by trainers. However, there is limited knowledge on whether these libraries successfully reach and support those in need. This study aimed to explore trainers' perspectives on the challenges, successes, and potential improvements in digital health skill education in a library setting.

Materials and methods: Trainers of the e-health course were interviewed. Topics included: the role of the library in digital health skills education, the successes and challenges in reaching groups with a low socioeconomic position, the perceived impact of the digital health skills education, and strategies for future improvement in digital health skills education. A deductive analysis based upon the interview guide topics was performed. A second inductive analysis was applied to identify underlying patterns. Coding was done independently and cross-checked. Codebooks and themes were determined in discussion with authors.

Results: Three themes emerged. 1) Trainers' services, skills and expertise: Trainers identified older adults, youth, people with low (digital) literacy, the unemployed, and people from non-native cultural backgrounds as the groups most in need of support. Trainers felt equipped to address these groups' needs. 2) The libraries' reach: improving engagement, perceived accessibility, and clients' barriers: Despite trainers' efforts to adjust the course to the target groups' level of commitment, digital and literacy levels, and logistics, the digital health course predominantly engages older adults. Experienced barriers in reach: limited perceived accessibility of the public library and clients' personal barriers. 3) Collaborations with healthcare, welfare and community organizations: Trainers emphasized that collaborations could enhance the diversity and number of participants. Current partnerships provided: reach to target groups, teaching locations, and referral of clients.

Discussion: Trainers in public libraries recognize a various target groups that need support in digital health skill development. The study identified three challenges: accessibility of the digital health course, reach of the public library, and clients' personal barriers. Public libraries have potential to support their target groups but need strategies to improve their engagement and reach. Collaborations with healthcare, welfare, and community organizations are essential to improve their reach to those most in need of support.

Background: Current methods of measuring disease progression of neurodegenerative disorders, including Parkinson's disease (PD), largely rely on composite clinical rating scales, which are prone to subjective biases and lack the sensitivity to detect progression signals in a timely manner. Digital health technology (DHT)-derived measures offer potential solutions to provide objective, precise, and sensitive measures that address these limitations. However, the complexity of DHT datasets and the potential to derive numerous digital features that were not previously possible to measure pose challenges, including in selection of the most important digital features and construction of composite digital biomarkers.

Methods: We present a comprehensive machine learning based framework to construct composite digital biomarkers for progression tracking. This framework consists of a marginal (univariate) digital feature screening, a univariate association test, digital feature selection, and subsequent construction of composite (multivariate) digital disease progression biomarkers using Penalized Generalized Estimating Equations (PGEE). As an illustrative example, we applied this framework to data collected from a PD longitudinal observational study. The data consisted of Opal™ sensor-based movement measurements and MDS-UPDRS Part III scores collected at 3-month intervals for 2 years in 30 PD and 10 healthy control participants.

Results: In our illustrative example, 77 out of 235 digital features from the study passed univariate feature screening, with 11 features selected by PGEE to include in construction of the composite digital measure. Compared to MDS-UPDRS Part III, the composite digital measure exhibited a smoother and more significant increasing trend over time in PD groups with less variability, indicating improved ability for tracking disease progression. This composite digital measure also demonstrated the ability to classify between de novo PD and healthy control groups.

Conclusion: Measures from DHTs show promise in tracking neurodegenerative disease progression with increased sensitivity and reduced variability as compared to traditional clinical scores. Herein, we present a novel framework and methodology to construct composite digital measure of disease progression from high-dimensional DHT datasets, which may have utility in accelerating the development and application of composite digital biomarkers in drug development.

Smartphones and wearable sensors offer an unprecedented ability to collect peripheral psychophysiological signals across diverse timescales, settings, populations, and modalities. However, open-source software development has yet to keep pace with rapid advancements in hardware technology and availability, creating an analytical barrier that limits the scientific usefulness of acquired data. We propose a community-driven, open-source peripheral psychophysiological signal pre-processing and analysis software framework that could advance biobehavioral health by enabling more robust, transparent, and reproducible inferences involving autonomic nervous system data.

Introduction: Limb massive hemorrhage is the first cause of potentially preventable death in trauma. Its prompt and proper management is crucial to increase the survival rate. To handle a massive hemorrhage, it is important to train people without medical background, who might be the first responders in an emergency. Among the possible ways to train lay rescuers, healthcare simulation allows to practice in a safe and controlled environment. In particular, immersive technologies such as Virtual Reality (VR) and Augmented Reality (AR) give the possibility to provide real time feedback and present a realistic and engaging scenario, even though they often lack personalization.

Methods: This work aims to overcome the above-mentioned limitation, by presenting the design, development and usability test of an AR application to train non-experienced users on the use of antihemorrhagic devices. The application combines a Microsoft Hololens2 headset, with an AR application developed in Unity Game Engine. It includes a training scenario with a multimodal interactive system made of visual and audio cues, that would adapt to user's learning pace and feedback preference.

Results: Usability tests on 20 subjects demonstrated that the system is well tolerated in terms of discomfort and workload. Also, the system has been high rated for usability, user experience, immersion and sense of presence.

Discussion: These preliminary results suggest that the combination of AR with multimodal cues can be a promising tool to improve hemorrhage management training, particularly for unexperienced users. In the future, the proposed application might increase the number of people who know how to use an anti-hemorrhagic device.