BIDMC researchers create tool for rapid insights into COVID-19 with international collaborators

Tool incorporates aggregate counts and statistics about patients with COVID-19 in five countries

Boston – As hospitals filled with patients with COVID-19 this spring, physicians quickly realized that electronic medical records (EMRs) had not lived up to their promise. Largely due to widespread decentralization of records and clinical systems that cannot “talk” to one another, EMRs weren’t streamlining clinical care and or guiding public health policy, as they were originally intended to do.

To circumvent these limitations, an international group including researchers from Beth Israel Deaconess Medical Center (BIDMC) has successfully created a platform for rapidly collecting aggregate counts and statistics about patients with COVID-19 from institutions' medical record systems and displaying the results as interactive visualizations. As described in Nature Digital Medicine by co-first authors Gabriel Brat, MD, and Griffin M. Weber, MD, PhD, both of BIDMC, the platform contains data from hospitals in five countries and has yielded intriguing, albeit preliminary, clinical clues about how COVID-19 presents, evolves and affects different organ systems across different categories of patients.

“Our work demonstrates that hospital systems can organize quickly to collaborate across borders, languages and different coding systems,” said Brat, who is a trauma surgeon at BIDMC and Assistant Professor of Surgery and member of the Department of Biomedical Informatics at Harvard Medical School (HMS). “I hope that our ongoing efforts to generate insights about COVID-19 and improve treatment will encourage others from around the world to join in and share data.”

The multi-institutional team, led by Harvard Medical School, analyzed data from 96 hospitals in the United States, France, Italy, Germany and Singapore, as part of the 4CE Consortium, an international research repository of electronic medical records used to inform studies of the COVID-19 pandemic.  The platform allowed researchers to track numbers of intensive care unit admissions and discharges, demographic breakdown of patients, weekly averages of new cases and daily death tolls, and more.

Early analysis of records from 27,584 patients and 187,802 lab tests collected in the early days of epidemic, from Jan. 1 to April 11, revealed some telltale patterns about the clinical presentation and course of severe COVID-19. For example, at initial presentation to the hospital, patients showed remarkable consistency in lab tests measuring cardiac, immune, blood-clotting and kidney and liver function, with test results progressively worsening in patients who went on to develop more severe disease or died.

For now, this initial observation—and many more—enabled by the data cannot be used to draw conclusions, the research team cautions.

“The platform currently represents more of a proof-of-concept than a fully evolved tool,” said Weber, who is Associate Professor of Medicine at BIDMC and an Associate Professor of Biomedical Informatics at HMS. “However, as more institutions contribute data, the trends these observations point to could provide a foundation for more focused and in-depth studies that will give us a better understanding of COVID-19 and how to manage it.”

Authors included co-corresponding senior authors Tianxi Cai, ScD, and Isaac S. Kohane, MD, PhD, both of the Department of Biomedical Informatics at Harvard Medical School. Please see the publication for a complete list of authors and relevant financial disclosures.

Adapted from a Harvard Medical School release written by Ekaterina Pesheva.