Identifying essential symptoms to streamline asthma care in primary settings

Published online May 27, 2026

Bronchial asthma is a common lung disease that affects millions of people around the world. To confirm the diagnosis, guidelines recommend combining a patient’s symptoms with breathing tests. However, these test machines are often unavailable or too expensive in small primary clinics. To make matters worse, asthma symptoms look a lot like other lung conditions. Because of this, doctors with less specialized experience often struggle to know which symptoms they should look for first.

To solve this problem, Wang et al. created a simple, symptom-based diagnostic framework using a machine learning approach called a decision tree model. In a study published in The Journal of Allergy and Clinical Immunology: In Practice, Wang and colleagues studied 4,417 patients with asthma-like symptoms. They evaluated 16 common features—including cough, wheezing, seasonal pattern, and when symptoms happen. Their goal was to find which symptoms matter most and how they work together to spot asthma accurately. 

Statistical modeling identified 12 key clinical variables, establishing the overall "number of asthma-like symptoms" as the primary driver for diagnosis, followed by nighttime symptom worsening and seasonal variations. The symptom-based decision tree achieved an impressive overall classification accuracy of 93.9% in detecting true asthma cases. By translating complex clinical data into a simple visual algorithm, this tool offers a highly practical workflow to assist general practitioners with early asthma detection, particularly in healthcare environments where objective lung function tests are inaccessible.

The Journal of Allergy and Clinical Immunology: In Practice is an official journal of the AAAAI, focusing on practical information for the practicing clinician.

Full Article


First Author
Name: Tian-Yue Wang, B.Med. 
Department: China-Japan Friendship Institute of Clinical Medicine Research 

Corresponding Author
Name: Guo-Liang Liu, PhD 
Department: 1.Department of Pulmonary and Critical Care Medicine, National Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing 100029, People’s Republic of China 2. WHO Collaborating Centre for Tobacco Cessation and Respiratory Diseases Prevention, Beijing 100029, People’s Republic of China 3.Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, National Clinical Research Center for Respiratory Diseases, Beijing 100029, People’s Republic of China