Periodic Reporting for period 2 - CrowdHEALTH (Collective wisdom driving public health policies)
Reporting period: 2018-09-01 to 2020-02-29
Capturing and linking this information with other data in EHRs would allow learning about outcomes of prevention strategies, health policies, etc. Records would become placeholders of all types of multi-information: data from multiple sources, incorporating multi-discipline knowledge, facilitating multi-stakeholder collaboration, capturing multi-morbidity cases.
CrowdHEALTH aims at delivering an integrated platform that provides decision support to public health authorities for policy creation / co-creation, through the exploitation of collective knowledge that emerges from multiple information sources. The latter will be realized through Holistic Health Records – HHRs that can include health, social and lifestyle data, data from medical devices, clinical data, diagnoses, medication, laboratory data, etc (see fig.1).
On top of big data management, CrowdHEALTH provides health analytics tools,(e.g. causal & risk stratification mechanisms, forecasting & simulation tools) towards the development of multi-modal targeted policies (see fig.2).
CrowdHEALTH will impact society providing policy makers with the means of processing large amount of healthcare information from a single entry point. The project’s platform will provide actionable insights on health-related implications of other policies (e.g. education or employment). It will facilitate the development of prevention strategies based on the evaluation and simulation of different scenarios. It will also provide means of assessing the impact of implementing strategies across specific patient groups and enable identifying successful KPIs.
• Analysis of specific state-of-the-art related to the project & future trends, at project start and at M16.
• Identification and description of the platform capabilities and core functionalities following the requirements elicitation and the state-of-the-art analysis.
• Compilation of CrowdHEALTH overall architecture with detailed example showing the information flow among the different components to ensure coherence.
• Definition of the HHR structure including + 200 entities / functionalities of the software components supporting HHRs.
• Design & implementation of tools to collect data from different data sources, aggregate and convert them into the common HHR format, assuring that datasets are clean and complete, convert them into HHR and FHIR formats.
• Design and implementation of the underlying big data management solution enabling storage, analysis and retrieval of data and analytics outcomes in an efficient way.
• Design and implementation of the overall security & privacy framework incorporating approaches for data anonymization, user and access management, trust profiling.
• Design and implementation of health analytics tools that act on the data, including risk stratification mechanisms, causal analysis and forecasting.
• Analysis of health policy models and definition of a public health policy model and structure including different KPIs.
• Design and implementation of an overall framework for policy modelling, namely the Policy Development Toolkit (PDT) as unique point for data visualization, health analytics mechanisms invocation, results analysis and policy development based on these results.
• Definition and analysis of several use case scenarios, going beyond EU use cases to include a scenario from Taiwan.
• Compilation of integration plan, driving integration activities that led to integrated prototypes according to the overall architecture.
• Early release of prototypes (M11) to demonstrate the added value of project outcomes and raise awareness, providing the ground for integrating prototypes towards the overall CrowdHEALTH platform.
• Creation of the public website, dissemination strategy & materials.
• Publication of scientific outcomes in conferences and journals, organization and participation in public events.
• Identification of the overall exploitation strategy and definition of initial exploitation plans from all partners.
• Interaction and feedback analysis with the ICB (Impact Creation Board).
• Collection of informed consent procedures to be adopted in the project for all use cases.
• Creation of a Board to monitor ethical concerns in the project and supervision of an Independent Ethics Advisor.
• Unified gateway, data aggregator and data converter enabling collection of heterogeneous data from diverse devices, aggregation of the data in health records and conversion to HHR structures by incorporating techniques for semantic and syntactic interoperability for the heterogeneous datasets.
• Data cleaning approaches to address cases of missing values in the datasets, of incorrect or incomplete information based on diverse rules being applicable to different scenarios / use cases and the corresponding datasets.
• Data anonymization techniques, trust and reputation modelling offering all the required mechanisms for enabling data anonymization, data protection and access control, while also ensuring that data sources / entities have the required profiles to account for their datasets.
• Big data management and analytics platform for storage & analysis of data emerging from different sources. Data models developed to allow storage of HHRs and interfaces enabling all components of the architecture to store and retrieve data from the underlying CrowdHEALTH big data framework.
• Health analytics tools developed and integrated in the overall CrowdHEALTH environment acting on the data to provide actionable insight to policy makers and healthcare professionals. These tools enable context analysis, clinical pathway mining, multimodal forecasting, causal analysis, risk stratification and profiling phenome-wide associations.
• Policies models reflecting a structural representation of policies including KPIs as parameters and outcomes that will be monitored, evaluated, adapted, etc.
• PDT serving as a unique point for policy makers to visualize existing data in an interactive way, trigger health analytics mechanisms on different datasets and obtain results, model and create policies.
• Data visualization environment integrated in the PDT offering adaptive and incremental visualization of the data to facilitate the analysis of the data by policy makers.