ѻýҕl

Using AI to Predict Exacerbations in Uncontrolled COPD

<ѻýҕl class="mpt-content-deck">— This is the "wave of the future," says Reynold Panettieri
MedpageToday

Artificial intelligence (AI) and natural language processing tools can build an algorithm that identifies patients with chronic obstructive pulmonary disease (COPD) at risk for exacerbations, according to at the CHEST annual meeting hosted by the American College of Chest Physicians.

In this exclusive ѻýҕl video, investigator , of the Rutgers Institute for Translational Medicine and Science in New Brunswick, New Jersey, discusses the goal and design of the study.

Following is a transcript of his remarks:

What I would like to share with you is an exciting work that was presented at the CHEST 2023 meeting where we used artificial intelligence, machine learning, and natural language processing to search structured and unstructured data in the EMR [electronic medical record].

Now, our goal was to identify patients who have uncontrolled COPD. So in effect, taking the concept of a COPD assessment tool, which we use to determine severity of illness, but to actually mine EHR [electronic health record] to predict exacerbations.

Long and short is in a study where we looked at a denominator that was over two million patients, and specifically in about 3,500 patients, we were able to identify comorbidities that were associated with a prediction of COPD exacerbations.

We believe this approach of using artificial intelligence, natural language processing, and machine learning to alert providers in their EHR for the likelihood of an exacerbation will have a profound effect in the management of COPD. We think this is the wave of the future for those providers who are in large health systems that are using EHR platforms to manage the patient's disease. Thank you.

  • author['full_name']

    Greg Laub is the Senior Director of Video and currently leads the video and podcast production teams.