Electronic medical record–based machine learning predicts the relapse of asthma exacerbation

The minimization of asthma exacerbation (AE) is a prioritized objective of asthma management given that repeated AE increases the future risk of fixed airway obstruction, adverse effects from corticosteroids and other medications, and even mortality. 1 Song WJ Lee JH Kang Y Joung WJ Chung KF. Future risks in patients with severe asthma. Allergy Asthma Immunol Res. 2019; 11: 763-778 Crossref PubMed Scopus (39) Google Scholar ,2 Sears MR. Can we predict exacerbations of asthma?. Am J Respir Crit Care Med. 2019; 199: 399-400 Crossref PubMed Scopus (8) Google Scholar Despite the development of novel biologics and supportive strategies proven to reduce AE, the prediction and prevention of exacerbation incidents remain a challenge. 3 Bloom CI Palmer T Feary J Quint JK Cullinan P. Exacerbation patterns in adults with asthma in England. A population-based study. Am J Respir Crit Care Med. 2019; 199: 446-453 Crossref PubMed Scopus (53) Google Scholar , 4 Martin A Bauer V Datta A Masi C Mosnaim G Solomonides A et al. Development and validation of an asthma exacerbation prediction model using electronic health record (EHR) data. J Asthma. 2020; 57: 1339-1346 Crossref PubMed Scopus (12) Google Scholar , 5 Jeffery MM Inselman JW Maddux JT Lam RW Shah ND Rank MA. Asthma patients who stop asthma biologics have a similar risk of asthma exacerbations as those who continue asthma biologics. J Allergy Clin Immunol Pract. 2021; 9 (e1): 2742-2750 Abstract Full Text Full Text PDF PubMed Scopus (8) Google Scholar Here, we present a machine-learning model that predicts AE recurrence using EMR in a single tertiary hospital in Korea.