1 of 4
Ravell Call, Deseret News
Dr. David Barnes examines a patient at Intermountain Medical Center's emergency room in Murray, Monday, March 18, 2013.

MURRAY — Researchers at Intermountain Medical Center have developed what they say is the world’s first real-time tool for diagnosing pneumonia.

The study of the development and initial tests of the device were published Monday in the Journal of the American Medical Association.

The invention was designed to save crucial minutes during diagnosis in the emergency room. The technology enables medical equipment to simultaneously diagnose about 40 possible indicators of pneumonia while doctors attend to the patient’s most pressing symptoms.

“Aspects of pneumonia care are fairly sophisticated, and this helps us gather the data needed to support a more accurate and timely diagnosis," said Dr. Nathan Dean, the study’s primary author and a section chief of medicine at Intermountain Medical Center.

“The tool exceeds human ability to process information. ... Human beings can only handle about four variables at a time accurately. A doctor could go find all of this information eventually, but it would be extremely difficult for them to synthesize all 40 variables.”

Doctors at Intermountain Medical Center, LDS Hospital, Alta View Hospital and Riverton Hospital have been testing the sophisticated software for nearly two years. Dr. David Barnes, who regularly uses the real-time diagnosis, said getting published in one of the most prestigious medical journals in the United States is a landmark step in making the technology more widely available.

“This is a publication with a high standard, so to us this is an important step,” Barnes said. “Hopefully we’ll see it spread to other facilities throughout the country.”

The 40 variables that indicate a possibility of infection include oxygen levels, respiratory levels, chest X-rays, sodium levels, heart rate and white cell blood count. The factors were identified after Intermountain Medical Center conducted a study of more than 48,000 emergency room patients, nearly 2,500 of which were positively diagnosed with pneumonia.

“We hope that the decision support tool helps physicians make more consistent decisions about who should be admitted to the hospital versus being treated as an outpatient, and who requires admission to the ICU,” Dean said. “Ultimately, we hope the tool helps reduce the number of deaths caused by pneumonia.”

According the Center for Disease Control and Prevention, just over 1.1 million Americans per year are diagnosed with pneumonia and about 49,500 people die from the infection. However, pneumonia can prove to be a challenge for doctors to diagnose because of its similarities to a host of other conditions, including asthma, chronic obstructive pulmonary disease, appendicitis and lung cancer. 

"Pneumonia is not an easy diagnosis," Dean said. "Computer tools do a much better job of assembling the data and helping us get it right."

When the system determines a patient has at least a 40 percent chance of having pneumonia, a "P" pops up on an electronic tracking board in the middle of the treatment center to alert doctors.

According to Dr. Peter Haug, an associate researcher for the published study, the centralized alert system is in many ways as vital to the screening tool's success as the technology itself. He said the delivery itself is especially important in the fast-paced environment of an emergency room.     

"It can be smarter than anything we've made yet," Haug said. "But if it doesn’t fit into the workflow or is too intrusive into what the doctors are trying to do, we can guarantee it won’t be used."

In addition to pinpointing the correct diagnosis, the screening tool then suggests customized treatments according to the 40 data points gathered from the patients — allowing doctors to weigh the risks and benefits of the suggested treatment and make the final decision equipped with more rigorous data.

Going forward, the research team also plans to apply the technology to other similar diseases and study other symptoms for their relation to pneumonia and add those to the model.

"We’re always looking for further data concerning pneumonia," Haug said. "We’re looking for elements to include in the calculation to make it even more accurate."

E-mail: [email protected]

Twitter: @benlockhart89