Those who have suffered a common lung illness in the past may be more at risk of severe illness or even death should they contract the novel coronavirus, suggests a new study conducted by Havard researchers. 

Using artificial intelligence (AI) technology to analyze the electronic medical records from nearly 17,000 Massachusetts General Hospital (MGH) patients who were diagnosed with COVID-19 between March and November 2020, researchers concluded that a prior case of pneumonia increased a person’s risk of severe illness or death from COVID-19. 

In fact, a history of pneumonia was named as the second-greatest overall risk factor for death from the novel disease, according to the study published in NPJ Digital Medicine earlier this month. 

Age, meanwhile, was considered to be "by far the most important feature for predicting COVD-19 mortality," the researchers wrote. 

FIRST US CASES OF SOUTH AFRICAN CORONAVIRUS VARIANT IDENTIFIED IN SOUTH CAROLINA

In patients between the ages of 45 to 65, top predictors of mortality were histories of diabetes with complications, cancer, (namely breast and prostate). In those ages 65 to 85, interstitial lung disorders, chronic obstructive pulmonary disease (COPD), lung cancer, and a history of smoking were "strong predictors of poor outcomes," they found.

Irrespective of age, other comorbidities that contributed to a higher risk of death or severe illness included chronic kidney disease, heart failure, abdominal aortic aneurysm, hypertension and aortic valve disease, they said.

It’s important to note, however, that a single past case of pneumonia wouldn’t necessarily put someone at more risk for severe illness or death. Rather, the researchers said, prior cases could indicate an undiagnosed underlying condition that could put someone more at risk. 

"[Pneumonia’s] incorporation into the final prediction model was due to it not only being predictive, but likely less correlated with many other chronic diseases like HTN, hyperlipidemia, CAD, and age for predicting death. It is possible that the diagnostic label was a proxy for an underlying chronic lung disease," they wrote. "These findings suggest that future studies should investigate this correlation between a previous pneumonia diagnosis and increased risk of death with COVID-19."

CLICK HERE FOR COMPLETE CORONAVIRUS COVERAGE

The researchers said using AI technology to create models to forecast the most severe COVID-19 outcomes based on past medical records, potentially helping to further identify those who should be prioritized for the COVID-19 vaccines. 

"The ability to quickly utilize data that has already been collected across the country to compute individual-level risk scores is crucial for effectively allocating and distributing resources, including prioritizing vaccination among the general population," said Dr. Shawn Murphy, senior author and chief research informatics officer at Mass General Brigham, in a statement.