Development of machine learning models to predict critical illness and mortality in COVID-19 patients

Mount Sinai researchers have developed machine learning models that predict the likelihood of critical events and mortality in COVID-19 patients within clinically relevant time windows. The new models outlined in the study, one of the first to use machine learning for risk prediction in COVID-19 patients among a large and diverse population, and published November 6 in Journal of Medical Internet Research—It could help clinical professionals on Mount Sinai and around the world in the care and management of COVID-19 patients.

“Since the initial outbreak of COVID-19 in New York City, we have seen that the presentation and course of COVID-19 disease are heterogeneous and we have built machine learning models using patient data to predict outcomes,” he said. Benjamin Glicksberg, Ph.D., assistant professor of genetics and genomic sciences at Mount Sinai Icahn School of Medicine, member of the Hasso Plattner Institute for Digital Health at Mount Sinai and Mount Sinai Clinical Intelligence Center (MSCIC) and one principal investigators of the study. “Now in the early stages of a second wave, we are much better prepared than before. We are currently evaluating how these models can help clinical professionals manage their patient care in practice.”

In the retrospective study using electronic health records of more than 4,000 adult patients admitted to five Mount Sinai Health System hospitals from March to May, MSCIC researchers and physicians analyzed the characteristics of COVID-19 patients, including past medical history, comorbidities, vital signs and laboratory test results upon admission, to predict critical events such as intubation and mortality within various clinically relevant time windows that can predict patients’ short- and medium-term risks during admission.

Researchers used the models to predict a critical event or mortality in time windows of 3, 5, 7 and 10 days after hospitalization. At the limit of one week, he performed better overall, correctly reporting the most critical events and returning the least number of false positives: acute kidney damage, rapid breathing, high blood sugar and elevated lactate dehydrogenase (LDH) indicating tissue damage or stronger driver diseases in the prediction of critical diseases. Older age, blood level imbalance, and C-reactive protein levels indicating inflammation were the strongest factors in predicting mortality.

“We have created high-performance predictive models using machine learning to improve the care of our patients on Mount Sinai,” said Girish Nadkarni, MD, Assistant Professor of Medicine (Nephrology) at Icahn School of Medicine, Clinical Director of the Hasso Plattner Institute for Digital Health at Mount Sinai and Co-Chair of MSCIC. “More importantly, we have created a method that identifies important health markers that guide probability estimates for acute care prognosis and can be used by healthcare institutions around the world to improve care decisions, both at the medical and hospital levels. , and manage patients with COVID-19 more effectively. ”