Northwestern and Endeavor Health Develop AI Program to Diagnose Respiratory Distress Syndrome

Northwestern University researchers and Chicago-based Endeavor Health have created a computer program that automatically identifies Acute Respiratory Distress Syndrome (ARDS), a debilitating and often fatal lung condition affecting up to 190,000 Americans annually. The new algorithm addresses a critical diagnostic challenge in intensive care units by automatically analyzing disconnected medical information that might otherwise go unnoticed.

ARDS causes fluid accumulation in the lungs' alveoli, resulting in dangerously low blood oxygen levels. The condition typically follows lung injuries or infections, including COVID-19, and carries a mortality rate exceeding 40 percent. Despite its prevalence among critically ill patients, ARDS remains difficult to diagnose because physicians must synthesize multiple data sources including laboratory results, chest X-rays, clinical notes, and cardiac tests.

The program, developed by Endeavor Health pulmonologist Dr. Curtis Weiss alongside Northwestern engineering researchers Felix Morales and Luis Nunes Amaral, employs clinical guidelines used by ICU doctors to retrospectively identify ARDS cases in ventilated patients. Testing on medical data from an external hospital system demonstrated the algorithm's effectiveness, correctly diagnosing 93.5 percent of true ARDS cases with a false alarm rate of approximately 17 percent, representing an improvement over current clinical recognition rates.

"As an ICU doctor, you're busy taking care of patients, and it's hard to comb through all of the data required to make that diagnosis," said Dr. Curtis Weiss, an Endeavor Health pulmonologist and co-director of Critical Care Medicine, who co-authored the paper and is principal investigator on the grant that funded the work. "That's where AI and machine learning come in. We think this program could help fill that gap, creating an additional safeguard to help doctors and patients here in Chicagoland and well beyond."

"If ARDS isn't caught right away, patients may not receive the life-saving treatment they need as quickly," said Morales, a research specialist in NU's department of Engineering Sciences and Applied Mathematics and lead author on the paper. "An automatic tool like this could catch more cases, helping doctors give the right treatment sooner."

The algorithm will undergo pilot implementation across Endeavor Health's system, which formed through the merger of NorthShore University HealthSystem, Edward-Elmhurst Health, Swedish Hospital, and Northwest Community Healthcare. Professor Amaral emphasized the broader implications of this development for healthcare AI applications.

"Even for conditions other than ARDS, this is a good example of AI's potential as a care tool and how it might lead to better and faster treatment," Amaral said. "AI done carefully can give doctors superpowers, helping them spot critical conditions faster, more accurately and at a scale no human could manage alone."

Click here for the original news story.