Data lakehouse
Healthcare
Spain
The Servicio Madrileño de Salud (SERMAS) is the public entity responsible for managing the healthcare system in the Madrid Metropolitan Area. SERMAS manages the services and provision of healthcare in all centers of the region and healthcare assistance for more than six million inhabitants residing in the Community of Madrid.
Through the GENESIS initiative, the DG Information Systems and Digital Health is working on the digital transformation strategy for the Madrid healthcare service, with data as the central focus. The main objective of the General Directorate is to place the patient at the center of the system, achieve a unified health vision, advance toward better health outcomes, create service networks, and develop intelligence through data. The goal is to provide a self-service-based care model and, operationally, to streamline the range of services available to citizens and regional processes.
This initiative is part of a Digital Health plan that aims to transform healthcare in Madrid based on four pillars: accessibility, telemedicine, artificial intelligence (AI), and healthcare data management.
Data-driven strategy to improve patient experience
The healthcare sector is known for its complex organizational structures, and SERMAS, with its management of 37 hospitals, over 430 primary healthcare centers, and a workforce of 75,000 professionals, recognized the need to address this complexity by leveraging a unified and modern data architecture where data is at the center of its digital transformation.
In 2019, SERMAS started working with Cloudera technology to create a unified data space that would facilitate accessibility to information and foster research in the healthcare field through proper data governance. Starting from a very disseminated architecture with legacy applications that interoperated with each other, they transitioned from a legacy data warehouse architecture to Cloudera’s platform. This transition allowed them to establish a single repository model using a modern Data Lakehouse architecture, thanks to Cloudera's technology, with the aim of achieving self-service capabilities.
The collaboration with Cloudera and CGM Clinical España has allowed SERMAS to redefine the entire healthcare model, establishing one of the largest data lakehouses in Europe within the healthcare sector. The institution now possesses comprehensive healthcare information for citizens from start to finish, including all their clinical episodes, enabling them to harness the maximum potential from this data with a range of analytical capabilities to implement the four pillars with.
To ensure the quality, metadata, and security of the data, SERMAS has established a Data Governance Office. This office manages data normalization, standardization, and quality, ensuring accessibility to maximize their value. A layered model has been implemented, where data from various sources is ingested through different methods. A hybrid on-premises and cloud platform has been adopted, incorporating different components to guarantee persistence, virtualization, and application programming interfaces (APIs). This setup facilitates self-service and enables easier consumption of the data.
"Thanks to the technology provided by Cloudera, we have laid the foundations for a total and comprehensive transformation of healthcare in Madrid, aiming to improve the quality of life for all its users," explains Miguel López Valverde, General Director of Information Systems and Digital Health at the Servicio Madrileño de Salud.
Harnessing data to improve healthcare
The first phase of the project involved a considerable challenge: moving the information from the different data sources (more than 400 applications) into a single database. The volume of data in the health sector is extremely large due to the interactions of its users when using it and, after successfully completing this phase, has led to the creation of the largest data space in the health system at the national level. For example, the repository has more than 1.6 billion objects already stored.
Thus, professionals can have a complete view of the patient and their pathologies to improve care, as well as having access to an integrated medical imaging platform. This project has also laid the technological foundations for developing the remote medicine service.
In the second phase, the public entity is working to achieve a self-service model for its professionals using descriptive and prescriptive analytics and transforming its architecture with the latest technology towards the data lakehouse. This will allow them to go beyond storage and get the most out of their data.
For example, genomic data will be very important for early diagnosis of pathologies based on historical and demographic data. The enormous variety and complexity of data handled by the healthcare sector makes it essential to have the latest technology in data management.
Co-creation model to promote medical research
As a result of this transformation, SERMAS, with its centralized data lakehouse, has created the Digital Health Innovation Centre in 2022, located in the administrative building of the Hospital Zendal. This is a co-creation model in which a governed platform has been set up so that the healthcare sector can develop its own clinical trials based on anonymized and controlled data, as well as opening the way to collaboration with the pharmaceutical and technology industry.
This project will result in the creation of a federated and open data suite to create added value in the Madrid ecosystem together with other national and international organisations to promote data-driven healthcare models, where data is managed as an asset.
"Our focus is on delivering real value to citizens and patients through data. By collaborating with Cloudera, we provide clients with a single platform to address all data-based research requests," says Luis Javier Bonilla, General Manager of CGM Clinical Spain.
"Cloudera and CGM simplified project implementation, emphasizing the value of current data assets and advanced analytics. This enabled a transition from application-centric to a data-centric model," explains Miguel López Valverde, General Director of Information Systems and Digital Health of the Madrid Health Service.
