Skip to main content
Search
Audio Interview

Predicting asthma exacerbations using machine learning models

Published on April 30, 2025   19 min

A selection of talks on Methods

Please wait while the transcript is being prepared...
0:00
Interviewer: Dr. Nestor Molfino, thank you very much for joining us today. You and your colleagues recently published a paper describing the training of machine learning algorithms using electronic health record data in order to predict asthma exacerbations in real-world patients. Can you start by describing the gap that you identified regarding the prediction of asthma exacerbations? What guided your approach for addressing it? Dr. Molfino: Hi. Thanks for having me. Asthma is a chronic respiratory condition that affects millions of people worldwide, and there are different degrees of severity, from mild, moderate to severe, according to the amount of medication required to control the disease for a particular patient. Now, the factors triggered in asthma exacerbations, that we know so far, include respiratory infections, allergens, pollutants, and even emotional upsets. There may be other factors that are less well-known. In the case of asthma exacerbations in severe patients, the factors are pretty well-known because we have studied this patient population in randomized clinical trials, where we found that having had a prior exacerbation or having elevated biomarkers of inflammation, such as elevated levels of blood eosinophils or high levels of expired nitric oxide in the exhaled breath, called FeNO, those are factors that are predisposing to the next exacerbation.

Quiz available with full talk access. Request Free Trial or Login.

Show
Hide

Predicting asthma exacerbations using machine learning models

Embed in course/own notes