Related Experiment Video
Updated: May 12, 2025

Murine Model of Allergen Induced Asthma
Published on: May 14, 2012
Artificial Intelligence-Generated Answers to Patients' Questions on Asthma: The Artificial Intelligence Responses on
Mattia Nigro1, Andrea Aliverti2, Alessandra Angelucci2
1Department of Biomedical Sciences, Humanitas University, Milan, Italy; Respiratory Unit, IRCCS Humanitas Research Hospital, Milan, Italy.
Generative artificial intelligence (AI) chatbots can answer asthma questions, but reliability varies. ChatGPT performed best overall, while Bard excelled in understandability, highlighting the need for caution with AI in asthma management.
Area of Science:
- Digital Health and Artificial Intelligence
- Respiratory Medicine and Asthma Management
Background:
- Asthma is a common chronic respiratory condition requiring continuous patient education and personalized care.
- Growing use of generative artificial intelligence (AI) for health queries raises concerns about information accuracy and reliability for asthma patients.
Purpose of the Study:
- To systematically assess the reliability, accuracy, comprehensiveness, and understandability of AI chatbot responses for asthma-related questions.
- To compare the performance of ChatGPT, Bard, and Copilot in addressing common asthma management queries.
Main Methods:
- A cross-sectional study involving 15 patient-generated asthma management questions categorized by difficulty.
- Responses from ChatGPT, Bard, and Copilot were evaluated by international experts (accuracy, comprehensiveness) and patient representatives (understandability).
- Reliability was tested via consistency checks across devices in a blinded evaluation.
Main Results:
- ChatGPT showed the highest reliability (15/15), accuracy (median 9.0), and comprehensiveness (median 8.0) compared to Bard and Copilot (P < .0001).
- Bard scored highest in understandability (median 9.0; P < .0001).
- Performance differences remained consistent across varying question difficulty levels.
Conclusions:
- AI chatbots offer generally accurate and understandable information for asthma-related queries.
- Variability in AI chatbot reliability and accuracy necessitates caution in clinical applications.
- AI tools can supplement, but not substitute, professional medical guidance for asthma care.
Related Concept Videos
Asthma-IV: Diagnostic and Management
Clinical Assessment for Asthma:
This is the first step in diagnosing and managing asthma. It includes:
Asthma-IV: Nursing Management
First, in...
Asthma-I: Introduction
Asthma-II: Pathophysiology and Classification
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
Asthma-III: Symptoms and Complications
Classification of Asthma
Asthma: Pathogenesis and Management
Asthma is classified as allergic and non-allergic. Allergens such as dust mites, pollen, and pet dander trigger allergic asthma, while factors like cold air, intense emotions, or exercise can induce non-allergic asthma.

