The free AI tool Google NotebookLM, powered by the LLM Gemini 2.0 [
The Google NotebookLM interface.
Query questions were selected to match the essential requirements of eligible AI tools, such as reproducibility, the ability to develop a treatment plan, and the capacity to handle speculative ideas. They were designed by a pulmonologist with expertise in airway diseases and familiarity with these guidelines, and the appropriateness (focusing on accuracy and completeness) of AI responses was judged (Likert scale 1-5) by 3 pulmonologists independently. Airway diseases were selected as the pilot scenario to evaluate the feasibility of our system because standardized clinical guidelines are widely accepted, and they involve fewer complex and controversial data points than other conditions, such as oncological diseases.
The system was introduced to physicians and allied health care professionals in the emergency department (ED), where patients with airway diseases commonly present for treatment. Feedback was collected through a questionnaire, and the responses were analyzed to assess the system’s effectiveness within the clinical workflow.
The ED setting was chosen because clinicians frequently encounter diverse conditions and require rapid access to specialist knowledge. In this context, an expert system capable of answering clinical queries has the potential to reduce the time burden on patients, frontline clinicians, and the specialists consulted.
The complete workflow of the project is summarized in
Flowchart illustrating the process of constructing our artificial intelligence (AI)–based consultation tool for medical decision-making.
The system consistently generated accurate summaries and responses, each supported by appropriate and reliable references. When prompted to regenerate output from the same sources, this system produced slightly varied responses that retained identical meaning, resembling the variability typically observed in an AI chatbot interaction.
The asthma and chronic obstructive pulmonary disease (COPD) guidelines contained respective lists of differential diagnoses. When instructed to generate a consolidated table of differential diagnoses for airway diseases, including their distinguishing features and relevant diagnostic tests, the system successfully produced one, as shown in
Summary of the differential diagnoses for asthma, chronic obstructive pulmonary disease (COPD), and related conditions, including distinguishing symptoms, clinical features, and tests. Full version available in Multimedia Appendix 1.
| Condition | Primary differential for | Differentiating symptoms and features | Differentiating tests and findings |
| Inducible laryngeal obstruction or vocal cord dysfunction | Both asthma and COPD | Dyspnea and inspiratory wheezing (stridor), sometimes with cough and general wheeze | Functional laryngoscopy visualizing vocal cord movement; full flow-volume curve assessing upper airway obstruction |
| Obesity | Both asthma and COPD | Respiratory symptoms, such as dyspnea and wheeze, that can mimic asthma or COPD, often related to deconditioning or mechanical restriction | Objective measurement of variable expiratory airflow limitation to confirm asthma in obese patients |
| Tracheobronchomalacia | Both asthma and COPD | Wheeze | Bronchoscopy; high-resolution chest computed tomography scan |
| Lung cancer | Both asthma and COPD (more common in COPD) | Breathlessness, significant weight loss, hemoptysis, night sweats, and fever | Chest radiograph or computed tomography scan; reduced diffusing capacity for carbon monoxide may be present |
| Alpha-1 antitrypsin deficiency | Both asthma and COPD (more commonly associated with COPD) | Shortness of breath, with a family history of early-onset emphysema | Blood test confirming alpha-1 antitrypsin deficiency |
| Tuberculosis | Both asthma and COPD (especially in low- and middle-income countries) | Chronic cough, hemoptysis, dyspnea and/or fatigue, fever, night sweats, anorexia, and weight loss | Sputum induction (to confirm inflammatory phenotype); high-resolution computed tomography of the chest |
The system demonstrated the ability to recognize temporal updates. For instance, it correctly identified that the “ABCD assessment tool” for COPD was replaced by the “ABE assessment scheme” in the 2023 update of the GOLD COPD guideline [
A COPD patient with mMRC=2 and CAT=11, and a history of hospitalization once in the past 1 year. What is his/her treatment suggestion?
...
3. GOLD Group Classification:
Combining a high symptom burden (mMRC=2, CAT=11) with a high exacerbation risk (one hospitalization), this patient is classified as GOLD Group E [GOLD 2023, p. 40,
When the COPD guidelines from 2023 onward were deselected from the source input panel, the system could still respond to questions about “ABE assessment” using information retained from previous dialogues, provided those dialogues had not been deleted using the Refresh button (
What is the ABE assessment tool?
The provided 2021 and 2022 reports do not contain information about merging groups C and D into a single “E” group, nor do they refer to an “ABE” assessment tool. This suggests that the change to the ABE classification, if it occurred, was introduced in a subsequent GOLD report (e.g., the GOLD 2023 report as mentioned in our previous conversation).
Explain the ABE assessment tool for COPD.
The sources provided do not contain information on an “ABE assessment tool” for COPD. However, they extensively describe the “ABCD” assessment tool used in the Global Initiative for Chronic Obstructive Lung Disease (GOLD) guidelines for COPD management. It is possible that “ABE” in your query was a typographical error for “ABCD” or refers to a concept not detailed in these documents.
Explain the ABE assessment tool for COPD.
While the provided sources do not explicitly define or refer to an “ABE assessment tool” as a named entity for evaluating COPD, they do describe a framework for the initiation of pharmacological management that relies on assessing factors commonly associated with “A” (Symptoms), “B” (Blood Eosinophil Count), and “E” (Exacerbation Risk).
Leveraging Google’s multilingual capability, the system could accept a query in Chinese and respond in either English or Chinese. When asked to compare the 2022 Taiwan adult asthma clinical care guidelines, written entirely in Chinese, with the GINA guideline, the system managed to perform the task without difficulty. Language switching did not appear to affect system performance.
As illustrated in
I have a patient diagnosed of COPD adequately maintained with Pulmicort, 2 puffs bid. However, he suffered from more and more dyspnea while walking. What is the management suggestion?
Based on the information in the sources, here are some management suggestions for your patient with COPD who is experiencing increasing dyspnea on walking despite being maintained on Pulmicort (an inhaled corticosteroid - ICS):
Consider adding a long-acting bronchodilator...
Consider a combination inhaler containing ICS and LABA...
Optimize inhaled therapy. Ensure that the patient...
Consider pulmonary rehabilitation...
Reassess lung function and consider other diagnoses...
Review for modifiable risk factors...
Consider stepping up ICS dose (with caution)...
Assess for features of asthma-COPD overlap (ACO)...
Follow-up and reassess...
The system addressed a logical question regarding the unavailability of pulmonary function testing by providing a structured, entry-by-entry response. It explained the implications separately for COPD and asthma, as shown in
Is pulmonary function test necessary for diagnosis? What if there is no pulmonary function test accessible?
Here’s how pulmonary function tests relate to diagnosing airway diseases, and what to do if these tests aren’t accessible:
COPD Diagnosis: Spirometry is essential to confirm a COPD diagnosis...
Asthma Diagnosis: Asthma diagnosis relies on a combination of characteristic symptom patterns and evidence of variable expiratory airflow limitation...
Role of Lung Function Testing: Lung function testing is essential to confirm...
Spirometry: Forced spirometry is the most reproducible and objective measurement of airflow obstruction. It measures...
When Spirometry Isn’t Available for Asthma Diagnosis:
Peak expiratory flow (PEF) can be used, although it is less reliable...
Assess the patient for a characteristic pattern of respiratory symptoms.
Consider a therapeutic trial with SABA and low-dose ICS...
Confirm variable expiratory airflow limitation by PEF. A ≥20% improvement in PEF...
Improvement in symptoms and PEF after a 4-week therapeutic trial...
When Spirometry Isn’t Available for COPD Diagnosis: When routine spirometry is not available, home measurement of peak expiratory flow (PEF) combined with validated patient questionnaires could be used to support or refute a possible diagnosis of COPD...
The system generated a tailored rehabilitation plan and schedule that took into account an advanced age condition, as shown in
I have a female patient, age 95, with COPD and ischemic heart disease. Please make a rehabilitation plan and schedule for her.
For your 95-year-old female patient with COPD and ischemic heart disease, a highly individualized, comprehensive, and carefully supervised rehabilitation plan is crucial, taking into accounts her advanced age and multiple comorbidities. This plan draws primarily from the Taiwan Pulmonary Rehabilitation Practical Guideline and the Global Initiative for Chronic Obstructive Lung Disease (GOLD) reports.
I. Overall Approach and Guiding Principles
Personalized and Integrated Care:...
Specialist Supervision:...
Holistic Goals:...
II. Initial Comprehensive Assessment
Patient Goals and Preferences:...
Medical History and Physical Examination:...
...
III. Rehabilitation Setting and Schedule
Setting: For a 95-year-old patient with significant comorbidities, a supervised setting is highly recommended, such as...
Duration: Optimal benefits from pulmonary rehabilitation programs are typically achieved within 6 to 8 weeks...
Frequency: Supervised exercise training at least twice weekly is recommended.
IV. Components of the Rehabilitation Plan
Exercise Training:...
Education and Self-Management:...
...
V. Follow-up and Monitoring
Regular Review:...
Response Assessment:...
...
In this case, the system transformed the ambiguous concept of “prospect” into practical categories of “future challenges” and “research directions.” This approach provided a meaningful response, as illustrated in
What is the future prospect of airway diseases and their treatment?
The sources discuss future challenges and research directions for airway diseases such as asthma and Chronic Obstructive Pulmonary Disease (COPD).
Asthma:
Despite improvements in asthma care and effective medications, many patients worldwide do not benefit from these advances due to inadequate medical facilities and financial resources.
Future research should focus on clinical and physiological characteristics, biomarkers, outcomes, and underlying mechanisms in patients with respiratory symptoms or chronic airflow limitation...
COPD:
More research is needed to guide better recognition and safe, effective treatment of COPD.
There’s a need to study clinical and physiological characteristics, biomarkers, outcomes and underlying mechanisms in broad populations of patients with respiratory symptoms or with chronic airflow limitation.
Future studies should focus on defining phenotypes and mechanisms to ensure the safety of pharmacological treatments...
The system appropriately declined to answer questions that were beyond the scope of the available sources. It did not fabricate factitious responses, unlike many chatbots.
When asked to compare guideline versions across publication years, the system clearly outlined the differences between them. Additionally, when requested to analyze trends in pharmacological use for airway diseases over the past 5 years, it generated a comprehensive summary, as shown in
Find the trend in pharmacological use for COPD and asthma in the past 5 years.
In the past five years, pharmacological treatment for both Chronic Obstructive Pulmonary Disease (COPD) and asthma has seen a clear trend towards more individualized, exacerbation-focused, and strategically combined therapies, with a strong emphasis on proper inhaler use and minimizing oral corticosteroid exposure.
Overarching Trends for Both COPD and Asthma (Past 5 Years)
Individualized and Patient-Centered Care:...
Focus on Exacerbation Reduction:...
Emphasis on Inhaler Technique and Adherence:...
Minimizing Oral Corticosteroid (OCS) Use:...
Trends in COPD Pharmacological Treatment (Past 5 Years): The GOLD reports (2021, 2022, 2023, 2024, 2025) and the 2023 Taiwan COPD Clinical Care Guidelines emphasize these trends:
Long-Acting Bronchodilators (LABA and/or LAMA) as First-Line:...
Strategic Use of Inhaled Corticosteroids (ICS):...
Increasing Role of Triple Therapy (LABA+LAMA+ICS):...
...
Trends in Asthma Pharmacological Treatment (Past 5 Years): GINA reports (2021, 2022, 2023, 2024, 2025) and the 2022 Taiwan Adult Asthma Clinical Care Guidelines highlight significant shifts:
Shift Away from SABA Monotherapy:...
Introduction of Two Treatment Tracks (GINA):...
ICS as the Cornerstone of Controller Therapy:...
...
When asked to recommend additional readings on intractable asthma, the system searched both the source text and the reference lists it contained. However, it did not suggest any external articles or books. Notably, the system interpreted the term “intractable asthma” as both “severe asthma” and “difficult-to-treat asthma” to ensure comprehensive coverage, as shown in
Can you suggest any further readings about the treatment for intractable asthma?
For further readings about the treatment of intractable asthma, which is often referred to in the sources as severe asthma or difficult-to-treat asthma, you may find the following publications insightful. These sources provide detailed information on diagnosis, management, and treatment options for patients whose asthma remains uncontrolled despite standard therapies:
Comprehensive Guidelines and Reviews:
Global Strategy for Asthma Management and Prevention (GINA): The GINA reports are frequently referenced for their comprehensive guidance on asthma management. Specifically, the sections within these reports on “Difficult-to-treat and severe asthma” provide a roadmap for assessment and management. You can refer to the detailed sections in the provided GINA reports, such as:
GINA-2023-Report:...
GINA-2024-strategy-report:...
GINA-2025-Clean:...
...Pharmacological Interventions:
Biologic Therapies:
EAACI Biologicals Guidelines-Recommendations for severe asthma: Agache I et al. offer guidelines and recommendations for biologics in severe asthma.
Tezepelumab:...
...
Add-on treatments (nonbiologic):
Tiotropium:...
Azithromycin:...
Oral Corticosteroids (OCS):...
Diagnostic and Management Strategies:
Sputum-guided treatment...
Bronchial Thermoplasty:...
Importance of Adherence and Inhaler Technique:...
These readings should provide a comprehensive overview of the current understanding and treatment approaches for intractable asthma.
We designed a question regarding the interchangeability of questionnaires used for evaluating COPD and asthma. Our system provided a reasonable response, as shown in
Can we evaluate asthmatic patients with questionnaires designed for COPD? Can we evaluate COPD patients with questionnaires designed for asthma?
Asthma and COPD can be difficult to distinguish, especially in older patients and smokers, and these conditions may overlap. Some patients are assigned both diagnoses. While some questionnaires might capture general respiratory symptoms that could be present in both asthma and COPD, it is best to use disease-specific questionnaires to ensure the most appropriate and accurate assessment. There is no evidence that asthma questionnaires can be used for COPD patients, and vice versa.
We instructed the system to generate a simulated case with symptoms and pulmonary function values to test our diagnostic skills. During this exercise, we compared our reasoning and diagnosis with the system’s answer to strengthen diagnostic ability, as shown in
Please make a case with symptoms and pulmonary function values to test our diagnostic skills.
Simulated Patient: Mr David Lee
Patient Background: Mr David Lee is a 58-year-old male with a 25 pack-year smoking history, though he states he is currently trying to quit. He reports a chronic cough with some mucus production for the past 8 years. He also experiences intermittent shortness of breath on exertion, particularly when climbing stairs. Lately, he’s noticed that his breathing feels tighter in the mornings, and he occasionally hears a whistling sound (wheeze) when breathing out, especially after exposure to cold air. These wheezing episodes are variable in intensity, and he notes that his symptoms sometimes improve with a relative’s “asthma inhaler” (a short-acting beta2-agonist, SABA).
Symptoms:
Chronic cough with mucus production (8 years duration).
Intermittent dyspnea on exertion (eg, climbing stairs).
Morning chest tightness.
Occasional expiratory wheezing, variable in intensity, exacerbated by cold air.
Reports temporary improvement with SABA.
Significant smoking history (25 pack-years).
Pulmonary Function Values:
Pre-Bronchodilator Spirometry:
Forced Expiratory Volume in 1 second (FEV1): 60% of predicted
Forced Vital Capacity: 80% of predicted
FEV1/Forced Vital Capacity Ratio: 65% (indicating airflow limitation)
Post-Bronchodilator Spirometry (after administering 400 mcg of salbutamol, a SABA):...
-----------------------------------------------------------------------------------
Diagnosis, Reasons, and Treatment Suggestion for Mr David Lee
...
Most of the 3 pulmonologists’ ratings (56/84, 67%) regarding AI responses were above average (Likert scale 4-5), and only 5% (4/84) were below average (Likert scale 1-2). The interrater reliability was moderate for accuracy (intraclass correlation coefficient=0.612;
We collected responses from 20 participants, including 3 physicians, 3 nurse practitioners, 11 ED nurses, and 3 respiratory therapists. Among them, 80% (16/20) expressed interest in the system (Kolmogorov-Smirnov [K-S]
In total, 55% (11/20) of the participants believed that the system could reduce specialty consultation time (K-S