Detecting the most critical clinical variables of COVID-19 breakthrough infection in vaccinated persons using machine learning.

Background: COVID-19 vaccines offer different levels of immune protection but do not provide 100% protection. Vaccinated persons with pre-existing comorbidities may be at an increased risk of SARS-CoV-2 breakthrough infection or reinfection. The aim of this study is to identify the critical variables associated with a higher probability of SARS-CoV-2 breakthrough infection using machine learning. Methods: A dataset comprising symptoms and feedback from 257 persons, of whom 203 were vaccinated and 54 unvaccinated, was used for the investigation. Three machine learning algorithms - Deep Multilayer Perceptron (Deep MLP), XGBoost, and Logistic Regression - were trained with the original (imbalanced) dataset and the balanced dataset created by using the Random Oversampling Technique (ROT), and the Synthetic Minority Oversampling Technique (SMOTE). We compared the performance of the classification algorithms when the features highly correlated with breakthrough infection were used and when all features in the dataset were used. Result: The results show that when highly correlated features were considered as predictors, with Random Oversampling to address data imbalance, the XGBoost classifier has the best performance (F1 = 0.96; accuracy = 0.96; AUC = 0.98; G-Mean = 0.98; MCC = 0.88). The Deep MLP had the second best performance (F1 = 0.94; accuracy = 0.94; AUC = 0.92; G-Mean = 0.70; MCC = 0.42), while Logistic Regression had less accurate performance (F1 = 0.89; accuracy = 0.88; AUC = 0.89; G-Mean = 0.89; MCC = 0.68). We also used Shapley Additive Explanations (SHAP) to investigate the interpretability of the models. We found that body temperature, total cholesterol, glucose level, blood pressure, waist circumference, body weight, body mass index (BMI), haemoglobin level, and physical activity per week are the most critical variables indicating a higher risk of breakthrough infection. Conclusion: These results, evident from our unique data source derived from apparently healthy volunteers with cardiovascular risk factors, follow the expected pattern of positive or negative correlations previously reported in the literature. This information strengthens the body of knowledge currently applied in public health guidelines and may also be used by medical practitioners in the future to reduce the risk of SARS-CoV-2 breakthrough infection.

From Siloed Applications to National Digital Health Ecosystems: A Strategic Perspective for African Countries.

Substantial investment in digital solutions for improved health services has occurred in recent years in Africa. Digital Health provides for proven, beneficial applications in many different areas of health systems. It supports the transformation of healthcare delivery, and its potential is seemingly boundless. However, the deployed systems are in silos, and interoperability and integration are largely missing. There is no timely information for easy and quick decision making; there is no ability to track service levels across the whole health sector. What is missing is an integrated information system across all healthcare facilities nationwide. Such a Digital Health Ecosystem, the holistic application of information and communications technologies, services and applications, will support health systems and improve healthcare delivery, coordination and integration across providers. Based on global experience in resource-constraint contexts, core steps necessary to develop and implement such an ecosystem are explored, and four fundamental building blocks and their elements are developed. The results presented are succinctly integrated into six statements on lessons learned and recommendations.

Model-Driven Paediatric Cardiomyopathy Pathways - A Clinical Impact Assessment.

Intermediate results from an ongoing health technology assessment exercise of a simulation model of paediatric cardiomyopathy are reported. Comprehensive data on paediatric cardiomyopathy/heart failure, treatment options, incidence and prevalence, prognoses for different outcomes to be expected were collected. Based on this knowledge, a detailed clinical pathway model was developed and validated against the clinical workflow in a tertiary paediatric care hospital. It combines three disease stages and various treatment options with estimates of the probabilities of a child moving from one stage to another. To reflect the complexity of initial decision taking by clinicians, a three-stage Markov model was combined with a decision tree approach - a Markov decision process. A Markov Chain simulation tool was applied to compare estimates of transition probabilities and cost data of present standard of care treatment options for a cohort of children over ten years with expected improvements from using a clinical decision support tool based on the disease model under development. Early results indicate a slight increase of overall costs resulting from the extra cost of using such a tool in spite of some savings to be expected from improved care. However, the intangible benefits in life years saved of severely ill children and the improvement in QoL to be expected for moderately ill ones should more than compensate for this.

Analysis and Typology of Global eHealth Platforms - A Survey on Five Continents.

Driven by the diverse needs for exchanging patient, other healthcare and health system data with the aim to improve the overall quality and efficiency of healthcare provision, regions and countries globally have been developing electronic platforms to gather and exchange such data. Based on an initial sample of more than 50 potential cases, eight such platforms were analysed in detail. This covered issues like core public health policy goals pursued, and major patient and other healthcare data access and exchange characteristics driving the platforms surveyed. This allows for arriving at an initial, pragmatic typology of such platforms. It provides for a better understanding of the main objective(s) and the major thrust of the underlying national (or district-related) health policy to develop and implement such infrastructures.

Meeting the Semantic Challenge of the Globally Unique Identification of Medicinal Products - The openMedicine Approach.

To better enable cross-border healthcare delivery, particularly the exchange of ePrescriptions, this global undertaking advances the unique identification of medicinal products (MPs) and patient safety in cross-border settings. Major stakeholders harmonise their respective efforts to deliver • common data models for prescribed MPs • a common vocabulary for unambiguous definition, description, and identification of MPs • rules to harmonise practices of therapeutic and economic substitution • a global roadmap for post-project actions and implementations Based on earlier activities of standard development organisations (SDOs), use case scenarios are developed, where the identification of an MP is an issue, including pharmacological and pharmacokinetic attributes, clinical indications, and risks to be considered. Next, the univocal identification of MPs is addressed, for standard pre-packed ones as well as for special cases like MPs with multi-components, biologics, or special packaging. Impacts will be considerable for global healthcare services and systems as well as - through simplifying and speeding up the registration of new products and afterwards pharmacovigilance - for national and international regulatory agencies, the MPs industry, and, in particular, patients.

Patient-centric Care and Chronic Disease Management: A Stakeholder Perspective.

By taking a stakeholder perspective, the paper explores reasons why the political commitment to patient-centric integrated care, facilitated by eHealth applications, is so difficult to meet. In spite of hundreds of pilots, still today there is a dearth of evidence on how to indeed successfully organise such services. Outcomes from a variety of implementation projects supported by the European Union were analysed, focusing on benefits and costs for the diverse stakeholder groups involved or impacted. The re-engineering of the services may result in a considerable shift in these variables between groups. Rendering both positive clinical impacts and a positive (overall) socio-economic return is not sufficient to assure wide acceptance and long-term sustainability. However motivated stakeholders may be, few will operate against their economic interests. Successfully establishing modern eHealth facilitated services is not so much a technical, but a social, organisational, and business innovation. We need to better understand in detail the benefits and costs, or the new 'business models' that go with integrated care for each involved stakeholder group, and the likely impacts for each of them, with a focus on how to best assure a win-win situation for all. Health policy has to respond to this, and a promising approach would be to promote organisational integration with shared budgets and outcome targets.

Achieving the integrated and smart health and wellbeing paradigm: a call for policy research and action on governance and business models.

To assure sustainability of our health systems and improve quality, implementing integrated wellness, health and social care service models have been proposed. They will need the enabling power of Health ICT facilitated systems and applications. Such solutions support the efficient coordination of service provision across provider and jurisdictional boundaries, the sharing of data, information and knowledge, and the streamlining as well as individualisation of care. Achieving such change in health systems with limited resources requires refocusing the trend of medico-technical progress. Health ICT innovations must be scrutinised for their potential to indeed contribute not only to decreasing costs, but - at the same time - improving the quality of life and ability to cope with challenges like the increasing prevalence of certain chronic diseases or new expectations from healthy people and patients alike. This paper argues that decision-oriented governance models leading to focused policy interventions are needed at several levels: Governments should provide for comprehensive Health ICT infrastructures to enable provider market success. At the individual actor level, sustainable business models reflecting in their value propositions the expectations of their clients (patients and funders) need to be developed. Health policy should design intelligent reimbursement systems providing incentives to indeed optimise services. Smart health innovations should only be implemented where they help achieve the goal of increasing the productivity of health value chains and the quality of overall service delivery value systems. To assure allocational efficiency, regulatory impact analyses (RIA) can support evidence based policy making.

A vision and strategy for the virtual physiological human: 2012 update.

European funding under Framework 7 (FP7) for the virtual physiological human (VPH) project has been in place now for 5 years. The VPH Network of Excellence (NoE) has been set up to help develop common standards, open source software, freely accessible data and model repositories, and various training and dissemination activities for the project. It is also working to coordinate the many clinically targeted projects that have been funded under the FP7 calls. An initial vision for the VPH was defined by the FP6 STEP project in 2006. In 2010, we wrote an assessment of the accomplishments of the first two years of the VPH in which we considered the biomedical science, healthcare and information and communications technology challenges facing the project (Hunter et al. 2010 Phil. Trans. R. Soc. A 368, 2595-2614 (doi:10.1098/rsta.2010.0048)). We proposed that a not-for-profit professional umbrella organization, the VPH Institute, should be established as a means of sustaining the VPH vision beyond the time-frame of the NoE. Here, we update and extend this assessment and in particular address the following issues raised in response to Hunter et al.: (i) a vision for the VPH updated in the light of progress made so far, (ii) biomedical science and healthcare challenges that the VPH initiative can address while also providing innovation opportunities for the European industry, and (iii) external changes needed in regulatory policy and business models to realize the full potential that the VPH has to offer to industry, clinics and society generally.

Developing national eHealth infrastructures--results and lessons from Europe.

The European eHealth Strategies study analyzed policy development and strategy planning, implementation measures as well as progress achieved with respect to national and regional eHealth solutions in 34 European countries, with emphasis on barriers and enablers beyond technology. The focus was on infrastructure elements and selected solutions emphasized in the European Union eHealth Action Plan of 2004. At the governance level, issues around administrative responsibility and competence centers, stakeholder engagement, legal and regulatory facilitators, financing and reimbursement, and evaluation activities were surveyed. Solutions analyzed included patient summaries and electronic health records, ePrescription, telehealth, electronic identifiers, eCards as well standardization aspects. Results indicate that across Europe eHealth has matured from a policy debate to a very tangible, implementation oriented endeavor.

Assessing biocomputational modelling in transforming clinical guidelines for osteoporosis management.

Biocomputational modelling as developed by the European Virtual Physiological Human (VPH) Initiative is the area of ICT most likely to revolutionise in the longer term the practice of medicine. Using the example of osteoporosis management, a socio-economic assessment framework is presented that captures how the transformation of clinical guidelines through VPH models can be evaluated. Applied to the Osteoporotic Virtual Physiological Human Project, a consequent benefit-cost analysis delivers promising results, both methodologically and substantially.

Policy needs and options for a common transatlantic approach towards measuring adoption, usage and benefits of eHealth.

The European Union (EU) sponsored ARGOS project analysed current eHealth policy thinking in both the EU and the USA, compared strategic challenges and outcomes in selected fields, and drafted roadmaps towards developing advanced global approaches for these issues. This policy brief focuses on better understanding the benefits and costs of eHealth investments, assessing their overall socio-economic impact, identifying challenges and success factors, as well as measuring and globally benchmarking the concrete usage of eHealth solutions. These are by now key policy priorities not only of national governments and the European Commission, but also of international institutions like WHO or OECD. There is a strong felt transatlantic need for stocktaking, identifying lessons learned, sharing of experience, and working together to advance these issues for the benefit of health systems. A growing number of national and international activities can be taken advantage of. Recommendations on how to proceed with such transatlantic activities are proposed.

A proposed vision: the transatlantic observatory for meeting global health policy challenges through information and communications technology-enabled solutions (ARGOS).

In 2010 the ARGOS project was funded by the EC (DG RELEX) to contribute to the establishement of a "Transatlantic Observatory for meeting Global Health Policy Challenges through Information and Communication Technology-enabled solutions" to develop and promote common methods for responding to global eHealth challenges in the EU and the US. The European Institute for Health Records (EuroRec) was coordinating the project. The vision is that the Transatlantic Observatory will act as an international platform for dialogue and collaboration on health policy issues and will 1. build international consensus about how to improve the access, efficiency and quality of health services through ICT, 2. promote the importance of interoperability in eHealth, 3. help to define approaches to ensure that health data are easily available where it is needed, 4. identify optimal development paths.

Каким образом телездравоохранение может помочь в предоставлении интегрированной помощи?

Телездравоохранение, или оказание помощи на расстоянии, вне всякого сомнения, станет одной из ключевых составляющих в будущейинформационно-коммуникационной инфраструктуре, необходимой для организации интегрированной помощи. Лица, формирующие политику, уже сейчас возлагают на него большие надежды, рассматривая его как возможный способ решения обостряющихся проблем кадров. Для того,чтобы обеспечить интегрированность помощи, необходимо включить обособленные сегодня прикладные задачи, решаемые с помощьютелездравоохранения, в более комплексные стратегии электронного здравоохранения, в которых были бы предусмотрены полная координация протоколов ведения больных и процессов оказания услуг и безопасный обмен данными о пациентах. Несмотря на то, что пока в Европе и в других регионах имеется мало примеров применения телездравоохранения в порядке повседневнойпрактики (в противоположность огромному объему исследований в этой области), формируется база все более убедительных фактических данных, свидетельствующих о том, что телездравоохранение можно успешноиспользовать для того, чтобы помочь обеспечить более высокое качество интегрированной помощи, в частности, тем, кто страдает продолжительными хроническими заболеваниями.

How can telehealth help in the provision of integrated care?

Telehealth, the provision of care at a distance, is certain to be a key component in future ICT infrastructure for integrated care. It has already raised high hopes among policy-makers with regard to its potential for delivering solutions forgrowing capacity problems. For integrated care, today's segregated telehealth applications still require linking into more comprehensive eHealth strategies, in which clinical pathways and service delivery processes are fully coordinated andpatient data safely shared. Although few instances of routine application have yet emerged in Europe or elsewhere – in contrast with an enormous breadth of research activities – anincreasingly solid evidence base is emerging indicating that telehealth can be used effectively to help support better integrated care, in particular for those with long-term chronic conditions.

DebugIT: building a European distributed clinical data mining network to foster the fight against microbial diseases.

The expansion of clinical information systems and the reduction in computing costs have led to an explosion of patient data available for reuse. However, this data is rarely combined and analyzed in an integrated manner. The DebugIT project is a large-scale integrating project funded within the 7th EU Framework Programme (FP7). The main objectives of the project are to build IT tools that should have significant impacts for the monitoring and the control of infectious diseases and antimicrobial resistances in Europe; this will be realized by building a technical and semantic infrastructure able to a) share heterogeneous clinical data sets from different hospitals in different countries, with different languages and legislations; b) analyze large amounts of this clinical data with advanced multi-modal data mining; c) apply the obtained knowledge for clinical decisions and outcome monitoring. The concepts and architecture underlying this project are discussed.

Designing a socio-economic assessment method for integrative biomedical research: the Osteoporotic Virtual Physiological Human project.

In integrative biomedical research, methods assessing the clinical or even socio-economic impact of more complex technologies such as Information and Communication Technology (ICT)-based tools for modelling and simulation of human physiology have rarely been applied. The EU funded Osteoporotic Virtual Physiological Human (VPHOP) research project, part of the Virtual Physiological Human (VPH) European initiative, will create a patient-specific hypermodel to predict the absolute risk of bone fracture much more accurately than predictions based on current clinical practice. The project has developed an innovative, multilevel generic methodological framework to assess the clinical and socio-economic impact of biocomputational models. The assessment framework consists of three components: a socio-economic cost benefit analysis, health economic analysis of care pathways, and disease cost simulation models. Through its holistic perspective, the method provides a tool to appraise the overall value of biocomputational models for society.

Economic performance and sustainability of HealthGrids: evidence from two case studies.

Financial sustainability is not a driving force of HealthGrids today, as a previous desk research survey of 22 international HealthGrid projects has showed. The majority of applications are project based, which puts a time limit of funding, but also of goals and objectives. Given this situation, we analysed two initiatives, WISDOM and MammoGrid from an economic, cost-benefit perspective, and evaluated the potential for these initiatives to be brought to market as self-financing, sustainable services. We conclude that the topic of HealthGrids should be pursued further because of the substantial potential for net gains to society at large. The most significant hurdle to sustainability - the discrepancy between social benefits and private incentives - can be solved by sound business models.

An economic analysis of the national shared Emergency Care Summary in Scotland.

The Emergency Care Summary (ECS) in Scotland provides essential clinical and demographic information about patients needing unscheduled or emergency care. Information about patients' medications, adverse drug reactions and allergies is transferred twice every day from GP systems to the ECS. Access is then available to authorised health-care professionals at the national help line, at out-of-hours services and in accident and emergency departments. An economic analysis of the ECS implementation showed that annual benefits exceeded annual costs after about seven years. Approximately 77% of the benefits were non-financial and 23% from redeployed finance. No cash savings were planned and none were realised. As ECS utilisation increased from 2006, the net benefits became positive. This relationship between utilisation and net benefits is a common feature of successful e-health investment.

Availability and usage of ICT applications among European primary care physicians.

While differences in Information and Communication Technology (ICT) infrastructure in European general practices are decreasing more and more, actual use rates - in particular, for more advanced applications - are about as different as the languages spoken by GPs throughout the European Union. This is one finding of a representative survey among GPs in Europe carried out by empirica on behalf of the European Commission. The resulting patchwork pattern of eHealth use shows that there is still some distance to go before all the potential benefits of eHealth in general practice can be reaped by all the EU member states.

Tele-homecare for chronically ill persons: pilot trials, medical outcomes and future perspectives.

Socio-economic trends including the ageing of populations in the developed world have let to markedly increased interest in improving society's ability to deliver effective care to older and chronically ill patients at home. The paper reports progress from recent European research on three key fronts faced in the diffusion of tele-homecare: Pilot applications to explore the features of as yet untried care domains, full clinical trials to present hard evidence of desired medical outcomes, and R&D to expand the capability of tele-homecare systems to meet the needs of a yet wider variety of chronic illnesses and patient groups.