System Architecture of a European Platform for Health Policy Decision Making: MIDAS

Abstract

BackgroundHealthcare data is a rich yet underutilized resource due to its disconnected, heterogeneous nature. A means of connecting healthcare data and integrating it with additional open and social data in a secure way can support the monumental challenge policy-makers face in safely accessing all relevant data to assist in managing the health and wellbeing of all. The goal of this study was to develop a novel health data platform within the MIDAS (Meaningful Integration of Data Analytics and Services) project, that harnesses the potential of latent healthcare data in combination with open and social data to support evidence-based health policy decision-making in a privacy-preserving manner.MethodsThe MIDAS platform was developed in an iterative and collaborative way with close involvement of academia, industry, healthcare staff and policy-makers, to solve tasks including data storage, data harmonization, data analytics and visualizations, and open and social data analytics. The platform has been piloted and tested by health departments in four European countries, each focusing on different region-specific health challenges and related data sources.ResultsA novel health data platform solving the needs of Public Health decision-makers was successfully implemented within the four pilot regions connecting heterogeneous healthcare datasets and open datasets and turning large amounts of previously isolated data into actionable information allowing for evidence-based health policy-making and risk stratification through the application and visualization of advanced analytics.ConclusionsThe MIDAS platform delivers a secure, effective and integrated solution to deal with health data, providing support for health policy decision-making, planning of public health activities and the implementation of the Health in All Policies approach. The platform has proven transferable, sustainable and scalable across policies, data and regions.

Data Analytics to Support Policy Making for Noncommunicable Diseases: Scoping Review (Preprint)

“…The 7 tools reviewed are summarized in Table 2. Three integrated platforms (EVOTION, MIDAS, CrowdHEALTH) were designed to support public health policy decisions for a range of conditions and include a data analytics component supporting both descriptive and predictive analytics [22][23][24][25][26]. Users can create policy models, define the way in which data should be analyzed in order to produce the evidence useful for public health policymaking and obtain analytical results of how this evidence may support or contradict various policy actions.…”

“…All tools employed descriptive analytics. The first level was data ingestion, integration, cleaning and preprocessing such as removal of duplicates and errors, imputation of missing data, handling of outliers and standardization of data formats [21,22,23,27]. The next step was data exploration using basic descriptive statistics and inferential statistics such as identification of risk factors for a specific condition.…”

“…Methods included regression analysis and statistical modelling. Contemporary frameworks were also used for prediction and forecasting, including machine learning, deep learning and simulation modelling [22,26]. Other types of analyses that were used for predictive purposes is risk stratification analysis, causal analysis that models the behavior of the target valuable of interest and clinical pathway analysis, which models the process followed during treatment of a patient in respect to a particular condition [23,24].…”

“…Three out of 7 tools were decision support systems designed to make policy recommendations. Authors referred to the prescriptive capabilities of the tools and demonstrated the policy creation process [20,22,25]. However, none of them presented a related use case actually applying this type of analytics.…”

“…Interestingly, this use case was based on a real-life policy described in the Slovenian National Program on Nutrition and Physical Activity for Health 2015-2025[24]. MIDAS was piloted in 4 countries using Social Media, MEDLINE analytics and News Media data on a range of conditions[22].Ji et al (2017) used data on treatments and symptoms posted by patients on Social Media to evaluate the effectiveness of the Social InfoButtons platform [27]. PopHR was piloted with a randomly sampled, open cohort of 25% of the Montreal population in Canada [21].…”