Machine Learning Models Forecast Likelihood of COVID-19 Mortality
The study is one of the first to use machine learning to predict COVID-19 mortality among a large and diverse patient population.
Source: Getty Images
By Jessica Kent
- Machine learning models can predict the likelihood of critical illness or mortality in COVID-19 patients, which could help clinicians better care for and manage individuals infected with the virus, according to a study published in JMIR.
For more coronavirus updates, visit our resource page, updated twice daily by Xtelligent Healthcare Media.
Patients with COVID-19 present with varying symptomatology, which can make effective patient triaging difficult, researchers noted. While some patients are asymptomatic, others experience severe acute respiratory distress syndrome, multiorgan failure, or death.
Identifying the patient characteristics that drive the course of disease across large patient cohorts is important, because it could help providers and hospitals predict disease trajectory and allocate essential resources.
Previous efforts to develop machine learning models for this purpose have been limited by small sample sizes, lack of generalization to diverse populations, disparities in feature missingness, and potential for bias.
Researchers from Mount Sinai set out to create machine learning algorithms using data from large and diverse patient populations. The team analyzed EHRs from more than 4,000 adult patients admitted to five Mount Sinai Health System hospitals from March to May.
The group examined characteristics of COVID-19 patients, including past medical history, comorbidities, vital signs, and laboratory test results at admission, to predict critical events such as intubation and mortality within various clinically relevant time windows that can forecast short- and medium-term risks of patients over the hospitalization.
Researchers used the machine learning models to predict a critical event or mortality at time windows of three, five, seven, and ten days from admission. The models performed best at the one-week mark, when they were able to correctly flag the most critical events while returning the fewest false positives.
At this point in the study, acute kidney injury, fast breathing, high blood sugar, and elevated lactate dehydrogenase (LDH) indicating tissue damage were the strongest drivers in predicting critical illness.
Older age, blood level imbalance, and C-reactive protein levels indicating inflammation were the strongest drivers in predicting mortality.
The results show not only the potential for machine learning to forecast patient outcomes, but also the progress the healthcare sector has made in developing these technologies to fit the current pandemic.
“From the initial outburst of COVID-19 in New York City, we saw that COVID-19 presentation and disease course are heterogeneous and we have built machine learning models using patient data to predict outcomes,” said Benjamin Glicksberg, PhD, Assistant Professor of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai, member of the Hasso Plattner Institute for Digital Health at Mount Sinai and Mount Sinai Clinical Intelligence Center.
“Now in the early stages of a second wave, we are much better prepared than before. We are currently assessing how these models can aid clinical practitioners in managing care of their patients in practice.”
As the healthcare crisis continues, researchers and provider organizations will work to further refine analytics tools that will help hospitals triage patients and manage care.
“We have created high-performing predictive models using machine learning to improve the care of our patients at Mount Sinai,” said Girish Nadkarni, MD, Assistant Professor of Medicine (Nephrology) at the 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 drive likelihood estimates for acute care prognosis and can be used by health institutions across the world to improve care decisions, at both the physician and hospital level, and more effectively manage patients with COVID-19.”
