# Artificial Intelligence in Asthma and COPD: Current Status and Future Potential

## TL;DR

This paper reviews how artificial intelligence is being used to improve diagnosis and management of asthma and COPD, highlighting its potential and challenges in healthcare.

## Contribution

The paper provides a comprehensive review of AI applications in asthma and COPD, emphasizing their potential and implementation challenges.

## Key findings

- AI is being used to support diagnosis, phenotyping, and monitoring in asthma and COPD.
- AI tools require robust validation and transparency for safe clinical implementation.
- Digital health data and imaging are key sources for AI-based monitoring in respiratory diseases.

## Abstract

Interest in artificial intelligence (AI) is rapidly growing. In healthcare, especially through machine learning and deep learning, AI is emerging as a promising tool to support the diagnosis, management, and prevention of lung diseases and to advance personalized care, although it requires large, well-structured datasets. Clinicians must learn how to integrate AI into routine practice for conditions such as asthma and chronic obstructive pulmonary disease (COPD), while ensuring patient safety and building trust in these tools. Chronic respiratory diseases are major global causes of morbidity and mortality and place a substantial burden on healthcare systems; among them, asthma and COPD are chronic disorders characterized by airway obstruction and inflammation. This review highlights the rapid advancement of AI, and it aims to explore the literature’s evidence of its applicability in controlling chronic respiratory disorders, particularly in asthma and COPD. We conducted a narrative literature review by searching ScienceDirect, PubMed, and Google Scholar for English-language studies on artificial intelligence applications in asthma and COPD and by screening the references of relevant articles. The reviewed literature suggests that AI-based approaches are being applied across the asthma–COPD spectrum to support diagnosis and phenotyping, improve risk stratification and prediction of clinically relevant outcomes, and enable more continuous monitoring using heterogeneous data sources (e.g., clinical records, imaging, and digital health data). AI-based tools are poised to support clinicians in asthma and COPD across diagnosis, phenotyping, and monitoring; however, their safe implementation in routine care will require robust validation, transparency, and governance to ensure reliability and patient safety.