Atos and Erasmus Medical Center develop a model to predict intensive care capacity and disease progression of COVID-19
Atos and the Competence Center Business Intelligence (ccBI) of Erasmus MC have developed in just ten days a model that can predict the type and level of the care needed for COVID-19 patients. Based on lab and admission data, this model estimates the probability that a patient will be admitted to intensive care (ICU) and the probable period of time the patient will stay in ICU. Via an interactive dashboard in HiX, an electronic health record, care providers are supported in their day-to-day monitoring of patients. In addition, they can proactively scale up or down the ICU capacity based on occupancy. The Atos team of data-scientists participated in this project free of charge.
Atos and the ccBI teams are working closely together with the Clinical Chemistry department, the Emergency Room and the ICU. The model is currently being tested in a pilot study.
Daily monitoring of disease progression
The dashboard quickly shows various information about patients, such as the location where the patient was admitted, the ‘isolation’ label, and prognosis based on lab results. The dashboard is updated daily with new data in order to keep the data as accurate as possible and to display the patient's progress in near real-time. This enables the caregiver to make data-informed decisions regarding the patient's gravity of care. The underlying data for the model is anonymized historical lab and admission data from Erasmus MC's HiX healthcare system. The model was created and trained in Python and then visualized in Microsoft Power BI to give it a user-friendly interface. For optimal process integration, the dashboard has been implemented in the EPD HiX and has been made quickly accessible for care providers.
“During the lockdown, working together remotely can be challenging. However, the fast and clear communication between all relevant parties at Erasmus MC and Atos has led to a streamlined process. Through the combination of an expert data science team from Atos, data engineers from the ccBI, and the clinical and practical input of the stakeholders, an innovative solution has been realized in a very short timeframe which can form the basis of decision-making and capacity management", says Marit Jaspers, BI Consultant/Data Engineer of the Competence Center Business Intelligence (CCBI) Erasmus MC.
“We are extremely proud that our team was able to contribute to relieving the enormous pressure that healthcare providers in Erasmus MC and other hospitals are experiencing, and also to help reduce the risks for COVID-19 patients,” says Peter ‘t Jong, CEO of Atos Northern Europe. “Thanks to our close working relationship with the ccBI team, we were able to develop a predictive model in a very short time that supports healthcare providers in their daily monitoring of patients".
Atos is a global leader in digital transformation with 110,000 employees in 73 countries and annual revenue of € 12 billion. European number one in Cloud, Cybersecurity and High-Performance Computing, the Group provides end-to-end Orchestrated Hybrid Cloud, Big Data, Business Applications and Digital Workplace solutions. The Group is the Worldwide Information Technology Partner for the Olympic & Paralympic Games and operates under the brands Atos, Atos|Syntel, and Unify. Atos is a SE (Societas Europaea), listed on the CAC40 Paris stock index.
The purpose of Atos is to help design the future of the information space. Its expertise and services support the development of knowledge, education and research in a multicultural approach and contribute to the development of scientific and technological excellence. Across the world, the Group enables its customers and employees, and members of societies at large to live, work and develop sustainably, in a safe and secure information space.
Marianne Hewlett | firstname.lastname@example.org | +31882650621