Search

Background Dengue is a common viral illness and severe disease results in life-threatening complications. Healthcare services in low- and middle-income countries treat the majority of dengue cases worldwide. However, the clinical decision-making processes which result in effective treatment are poorly characterised within this setting. In order to improve clinical care through interventions relating to digital clinical decision-support systems (CDSS), we set out to establish a framework for clinical decision-making in dengue management to inform implementation. Methods We utilised process mapping and task analysis methods to characterise existing dengue management at the Hospital for Tropical Diseases, Ho Chi Minh City, Vietnam. This is a tertiary referral hospital which manages approximately 30,000 patients with dengue each year, accepting referrals from Ho Chi Minh city and the surrounding catchment area. Initial findings were expanded through semi-structured interviews with clinicians in order to understand clinical reasoning and cognitive factors in detail. A grounded theory was used for coding and emergent themes were developed through iterative discussions with clinician-researchers. Results Key clinical decision-making points were identified: (i) at the initial patient evaluation for dengue diagnosis to decide on hospital admission and the provision of fluid/blood product therapy, (ii) in those patients who develop severe disease or other complications, (iii) at the point of recurrent shock in balancing the need for fluid therapy with complications of volume overload. From interviews the following themes were identified: prioritising clinical diagnosis and evaluation over existing diagnostics, the role of dengue guidelines published by the Ministry of Health, the impact of seasonality and caseload on decision-making strategies, and the potential role of digital decision-support and disease scoring tools. Conclusions The study highlights the contemporary priorities in delivering clinical care to patients with dengue in an endemic setting. Key decision-making processes and the sources of information that were of the greatest utility were identified. These findings serve as a foundation for future clinical interventions and improvements in healthcare. Understanding the decision-making process in greater detail also allows for development and implementation of CDSS which are suited to the local context.

Neonatal mortality remains disproportionately high in sub-Saharan Africa partly due to insufficient numbers of adequately trained and skilled front-line health workers. Opportunities for improving neonatal care may result from upskilling frontline health workers using innovative technological approaches. This practice paper describes the key steps involved in the design, development and implementation of an innovative smartphone-based training application using an agile, human-centred design approach. The Life-saving Instruction for Emergencies (LIFE) app is a three-dimension (3D) scenario-based mobile app for smartphones and is free to download. Two clinical modules are currently included with further scenarios planned. Whilst the focus of the practice paper is on the lessons learned during the design and development process, we also share key learning related to project management and sustainability plans, which we hope will help researchers working on similar projects.

In this paper, we describe techniques for predictive modeling of human-computer interaction (HCI) and discuss how they could be used in the development and evaluation of user interfaces for digital health systems such as electronic health record systems. Predictive HCI modeling has the potential to improve the generalizability of usability evaluations of digital health interventions beyond specific contexts, especially when integrated with models of distributed cognition and higher-level sociotechnical frameworks. Evidence generated from building and testing HCI models of the user interface (UI) components for different types of digital health interventions could be valuable for informing evidence-based UI design guidelines to support the development of safer and more effective UIs for digital health interventions.

Background Although smartphone-based emergency care training is more affordable than traditional avenues of training, it is still in its infancy, remains poorly implemented, and its current implementation modes tend to be invariant to the evolving learning needs of the intended users. In resource-limited settings, the use of such platforms coupled with gamified approaches remains largely unexplored, despite the lack of traditional training opportunities, and high mortality rates in these settings. Objective The primary aim of this randomized experiment is to determine the effectiveness of offering adaptive versus standard feedback, on the learning gains of clinicians, through the use of a smartphone-based game that assessed their management of a simulated medical emergency. A secondary aim is to examine the effects of learner characteristics and learning spacing with repeated use of the game on the secondary outcome of individualized normalized learning gain. Methods The experiment is aimed at clinicians who provide bedside neonatal care in low-income settings. Data were captured through an Android app installed on the study participants’ personal phones. The intervention, which was based on successful attempts at a learning task, included adaptive feedback provided within the app to the experimental arm, whereas the control arm received standardized feedback. The primary end point was completion of the second learning session. Of the 572 participants enrolled between February 2019 and July 2019, 247 (43.2%) reached the primary end point. The primary outcome was standardized relative change in learning gains between the study arms as measured by the Morris G effect size. The secondary outcomes were the participants individualized normalized learning gains. Results The effect of adaptive feedback on care providers’ learning gain was found to be g=0.09 (95% CI −0.31 to 0.46; P=.47). In exploratory analysis, using normalized learning gains, when subject-treatment interaction and differential time effect was controlled for, this effect increased significantly to 0.644 (95% CI 0.35 to 0.94; P Conclusions There is a considerable learning gain between the first two rounds of learning with both forms of feedback and a small added benefit of adaptive feedback after controlling for learner differences. We suggest that linking the adaptive feedback provided to care providers to how they space their repeat learning session(s) may yield higher learning gains. Future work might explore in more depth the feedback content, in particular whether or not explanatory feedback (why answers were wrong) enhances learning more than reflective feedback (information about what the right answers are). Trial Registration Pan African Clinical Trial Registry (PACTR) 201901783811130; https://pactr.samrc.ac.za/TrialDisplay.aspx?TrialID=5836 International Registered Report Identifier (IRRID) RR2-10.2196/13034

Summary Objective: The International Medical Informatics Association (IMIA) Open Source Working Group (OSWG) initiated a group discussion to discuss current privacy and security issues in the open data movement in the healthcare domain from the perspective of the OSWG membership. Methods: Working group members independently reviewed the recent academic and grey literature and sampled a number of current large-scale open data projects to inform the working group discussion. Results: This paper presents an overview of open data repositories and a series of short case reports to highlight relevant issues present in the recent literature concerning the adoption of open approaches to sharing healthcare datasets. Important themes that emerged included data standardisation, the inter-connected nature of the open source and open data movements, and how publishing open data can impact on the ethics, security, and privacy of informatics projects. Conclusions: The open data and open source movements in healthcare share many common philosophies and approaches including developing international collaborations across multiple organisations and domains of expertise. Both movements aim to reduce the costs of advancing scientific research and improving healthcare provision for people around the world by adopting open intellectual property licence agreements and codes of practice. Implications of the increased adoption of open data in healthcare include the need to balance the security and privacy challenges of opening data sources with the potential benefits of open data for improving research and healthcare delivery.

BackgroundTarget 3.2 of the United Nations Sustainable Development Goals (SDGs) is to reduce neonatal mortality. In low-income and middle-income countries (LMICs), the District Health Information Software, V.2 (DHIS2) is widely used to help improve indicator data reporting. There are few reports on its use for collecting neonatal hospital data that are of increasing importance as births within facilities increase. To address this gap, we investigated implementation experiences of DHIS2 in LMICs and mapped the information flow relevant for neonatal data reporting in Kenyan hospitals.MethodsA narrative review of published literature and policy documents from LMICs was conducted. Information gathered was used to identify the challenges around DHIS2 and to map information flows from healthcare facilities to the national level. Two use cases explore how newborn data collection and reporting happens in hospitals. The results were validated, adjusted and system challenges identified.ResultsLiterature and policy documents report that DHIS2 is a useful tool with strong technical capabilities, but significant challenges can emerge with the implementation. Visualisations of information flows highlight how a complex, people-based and paper-based subsystem for inpatient information capture precedes digitisation. Use cases point to major challenges in these subsystems in accurately identifying newborn deaths and appropriate data for the calculation of mortality even in hospitals.ConclusionsDHIS2 is a tool with potential to improve availability of health information that is key to health systems, but it critically depends on people-based and paper-based subsystems. In hospitals, the subsystems are subject to multiple micro level challenges. Work is needed to design and implement better standardised information processes, recording and reporting tools, and to strengthen the information system workforce. If the challenges are addressed and data quality improved, DHIS2 can support countries to track progress towards the SDG target of improving neonatal mortality.

There remains a lack of evidence on the implementation of Intelligent Tutoring Systems in low-resource settings, and in particular, of how adaptive instructional support can be implemented to support clinical training on smartphone devices. A core part of this challenge to determine an appropriate data and modelling approach to support adaptive instruction on mobile devices. Using data from a serious-gaming smartphone application for clinical training from Sub-Saharan Africa, this paper investigates models to support prediction of learner performance as a precursor to determining skill-mastery level. We explore Bayesian graph model configurations that predict unseen learner responses based on seen responses and investigate different combinations of these models that factor in time on task, and previous cumulative learning opportunities respectively. Our results show that a modelling approach that predicts learner performance while considering previous learning opportunities is more accurate than approaches that predicts learner performance based on time they spent on a learning task. Using time-on-task in combination with previous learning opportunities to augment prediction of learner performance produced no substantive increase on prediction accuracy compared to just using previous learning opportunities only. We discuss how our findings provide an avenue for introduction of adaptive scaffolding of feedback instruction, based on probabilistic performance thresholds informed by cumulative tries from previous attempts with the goal of helping the learner gain skill-mastery.

Background: Virtual and Augmented Reality (VR/AR) has been used in surgery for several decades. Over the past 5-10 years, however, new technological advances, including high-resolution screens, mobile graphical processing units (mGPUs) and position-sensing technologies, have been incorporated into relatively low-cost VR and AR devices. This review focuses on the current impact of the application of these “Phase 2” VR/AR technology in surgical training.Methods: A narrative literature review was undertaken using PubMed and Web of Science to identify comparative studies related to the impact of Phase 2 VR or AR tools on surgical training, defined in terms of the acquisition of technical surgical skills. Eleven studies on the effectiveness of VR/AR in surgical education were identified for full review. Further, the grey literature was searched for articles describing the current state of VR/AR in surgical education. A quality analysis using the Newcastle Ottawa scale showed a median score of 7 (out of a maximum achievable score of 9).Results: All studies showed a positive association between the use of VR/AR in surgical training and skill acquisition in terms of improving the speed of acquisition of surgical skills, the surgeon’s ability to multitask, the ability to perform a procedure accurately, hand-eye coordination and bimanual operation. The grey literature presented a common, positive theme of the benefits of VR/AR in surgical training.Conclusions: Based on the limited evidence available, VR/AR appears to have positive training benefits in improving the speed of acquisition of surgical skills. However, the significant heterogeneity in study methodology and the relative recency of wider VR/AR adoption in surgical training mean that only tentative conclusions can be drawn at this stage. Further research, ideally with large sample sizes, robust outcome measures and longer follow-up periods, is recommended.

Summary Objectives : Artificial Intelligence (AI) offers significant potential for improving healthcare. This paper discusses how an “open science” approach to AI tool development, data sharing, education, and research can support the clinical adoption of AI systems. Method : In response to the call for participation for the 2019 International Medical Informatics Association (IMIA) Yearbook theme issue on AI in healthcare, the IMIA Open Source Working Group conducted a rapid review of recent literature relating to open science and AI in healthcare and discussed how an open science approach could help overcome concerns about the adoption of new AI technology in healthcare settings. Results : The recent literature reveals that open science approaches to AI system development are well established. The ecosystem of software development, data sharing, education, and research in the AI community has, in general, adopted an open science ethos that has driven much of the recent innovation and adoption of new AI techniques. However, within the healthcare domain, adoption may be inhibited by the use of “black-box” AI systems, where only the inputs and outputs of those systems are understood, and clinical effectiveness and implementation studies are missing. Conclusions : As AI-based data analysis and clinical decision support systems begin to be implemented in healthcare systems around the world, further openness of clinical effectiveness and mechanisms of action may be required by safety-conscious healthcare policy-makers to ensure they are clinically effective in real world use.