A study conducted by researchers at several New York University institutions used over 5,000 Covid-19 patient chest X-ray samples to test their AI model

A chest X-ray example from the patient sample used in the NYU Langone study (Credit: NYU Langone)

A computer program has predicted which Covid-19 patients would develop life-threatening complications using chest X-ray images taken from a large sample of seriously ill patients.

Developed by researchers at NYU Grossman School of Medicine, the program used several hundred gigabytes of data gleaned from 5,224 chest X-ray samples taken from 2,943 Covid-19 patients – the algorithm predicted life-threatening complications within four days of hospital admission with 80% accuracy.

The authors of the study, publishing in the journal npj Digital Medicine online May 12, cited the “pressing need” for the ability to quickly predict which Covid-19 patients are likely to have lethal complications, so that treatment resources can best be matched to those at increased risk.

Study co-lead investigator Farah Shamout, PhD, an assistant professor in computer engineering at New York University’s campus in Abu Dhabi, said: “Emergency room physicians and radiologists need effective tools like our program to quickly identify those Covid-19 patients whose condition is most likely to deteriorate quickly, so that health care providers can monitor them more closely and intervene earlier.”

Yiqiu “Artie” Shen, MS, a doctoral student at the NYU Data Science Center added: “We believe that our Covid-19 classification test represents the largest application of artificial intelligence in radiology to address some of the most urgent needs of patients and caregivers during the pandemic.”

For reasons not yet fully understood, the health of some Covid-19 patients suddenly worsens, leading to them needing intensive care and increasing their chances of dying.

To address the need to make the course of the disease more predictable, the NYU Langone team fed X-ray information into their computer analysis, alongside patients’ age, race, and gender, as well as several vital signs and laboratory test results, including weight, body temperature, and blood immune cell levels.

Also factored into their mathematical models, which can learn from examples, were the need for a mechanical ventilator and whether each patient went on to survive (2,405) or die (538) from their infections.

Researchers then tested the predictive value of the software tool on 770 chest X-rays from 718 other patients admitted for Covid-19 through the emergency room at NYU Langone hospitals from March 3 to June 28, 2020.

The computer program accurately predicted four out of five infected patients who required intensive care and mechanical ventilation and/or died within four days of admission.

Study senior investigator Krzysztof Geras, PhD, an assistant professor in the Department of Radiology at NYU Langone, says a major advantage to machine-intelligence programs such as theirs is that its accuracy can be tracked, updated and improved with more data.

He says the team plans to add more patient information as it becomes available, and that the team is evaluating what additional clinical test results could be used to improve their test model.

Geras says he hopes, as part of further research, to soon deploy the NYU Covid-19 classification test to emergency physicians and radiologists.

In the interim, he is working with physicians to draft clinical guidelines for its use.