Mass General Hospital researchers used medical histories of patients collected and stored in EHRs combined with artificial intelligence technology to predict patients' probability of dying from COVID-19.
The Boston-based hospital's analytics and medical team used COVID-19 data and medical records from more than 16,000 patients and applied a computer algorithm to identify 46 clinical conditions representing potential risk factors for death after a COVID-19 infection.
Potential risk factors for death in COVID-19 patients include age, history of pneumonia, gender, race and comorbidities like diabetes and cancer, according to the study, which was published in npj Digital Medicine.
"By combining computational methods and clinical expertise, we developed a set of models to forecast the most severe COVID-19 outcomes based on past medical records, and to help understand the differences in risk factors across age groups," said Hossein Estiri, PhD, co-lead author of the study and computer science lab investigator at MGH, according to a Feb. 4 news release.
Dr. Estiri said that while many prior studies have isolated small subsets of EHR data after the infection, MGH's study "is the first and largest to use entire historical medical records to try to untangle the role of age as the most important risk factor for COVID adverse outcomes."