Evaluating the Potential of Large Language Models for Respiratory Disease Consultations (EPLLMMRDC)

Evaluating the Potential of Large Language Models for Respiratory Disease Consultations: A Randomized Crossover Trial

The clinical trial aimes to evaluate multiple large language models in respiratory disease consultations by comparing their performance to that of human doctors across three major medical consultation scenarios.

The main question aims to answer are:

• How do large language models perform in comparison to human doctors in diagnosing and consulting on respiratory diseases across various clinical scenarios?

In three clinical scenarios including the online query section, the disease diagnosis section and the medical explanation section, research assistants or volunteers will be asked to cross-question all LLMs or real doctors using predefined online questions and their own issues. After each questioning session, a short washout period is implemented to eliminate potential biases.

Study Overview

• Status: Completed
• Conditions: Pneumonia; Bronchiectasis; Asthma; Pulmonary Fibrosis; Lung Cancer; Tuberculosis; Acute Upper Respiratory Infection; Pulmonary Embolism; Hay Fever; Acute Bronchitis
• Intervention / Treatment: Diagnostic test: Diagnosis by three human doctors; Diagnostic test: Diagnosis by ChatGPT-3.5 (with search capabilities); Diagnostic test: Diagnosis by ChatGPT-3.5 (without search capabilities); Diagnostic test: Diagnosis by ChatGPT-4.0 (with search capabilities); Diagnostic test: Diagnosis by ChatGPT-4.0 (without search capabilities); Diagnostic test: Diagnosis by Claude instant (with search capabilities); Diagnostic test: Diagnosis by Claude instant (without search capabilities); Diagnostic test: Diagnosis by Claude 2 (with search capabilities); Diagnostic test: Diagnosis by Claude 2 (without search capabilities); Diagnostic test: Diagnosis by Gemini Pro (with search capabilities); Diagnostic test: Diagnosis by Gemini Pro (without search capabilities)

• Study Type: Interventional
• Enrollment (Actual): 703
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Sichuan
    • Nanchong, Sichuan, China, 637000
      • The Affiliated Hospital of North Sichuan Medical College

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

1. Self-reported symptoms of common respiratory diseases, such as cough, chest tightness, fever, and wheezing
2. Ability to engage in LLM dialog operations independently or with minimal peer training
3. A health status deemed suitable for study participation by the pulmonology experts

Exclusion Criteria:

1) Excessively poor health status

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Crossover Assignment
• Masking: Quadruple

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Other: Cross-comparison group(the disease diagnosis section); Cross-comparison group (including human doctor controls and all LLMs)	Diagnostic test: Diagnosis by three human doctors; This intervention involves answering patient inquiries by different human doctors. Each patient is randomly assigned by the system to three doctors from different provinces in China selected from the database of doctors. The doctors all come from multiple online consultation platforms in China, and their diagnostic qualifications and medical licenses have undergone strict verification.; Diagnostic test: Diagnosis by ChatGPT-3.5 (with search capabilities); This intervention involves answering patient inquiries by ChatGPT-3.5 with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by ChatGPT-3.5 (without search capabilities); This intervention involves answering patient inquiries by ChatGPT-3.5 without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by ChatGPT-4.0 (with search capabilities); This intervention involves answering patient inquiries by ChatGPT-4.0 with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by ChatGPT-4.0 (without search capabilities); This intervention involves answering patient inquiries by ChatGPT-4.0 without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude instant (with search capabilities); This intervention involves answering patient inquiries by Claude instant with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude instant (without search capabilities); This intervention involves answering patient inquiries by Claude instant without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude 2 (with search capabilities); This intervention involves answering patient inquiries by Claude 2 with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude 2 (without search capabilities); This intervention involves answering patient inquiries by Claude 2 without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Gemini Pro (with search capabilities); This intervention involves answering patient inquiries by Gemini Pro with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Gemini Pro (without search capabilities); This intervention involves answering patient inquiries by Gemini Pro without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.
Other: Cross-comparison group(the medical explanation section); Cross-comparison group (including human doctor controls and all LLMs)	Diagnostic test: Diagnosis by three human doctors; This intervention involves answering patient inquiries by different human doctors. Each patient is randomly assigned by the system to three doctors from different provinces in China selected from the database of doctors. The doctors all come from multiple online consultation platforms in China, and their diagnostic qualifications and medical licenses have undergone strict verification.; Diagnostic test: Diagnosis by ChatGPT-3.5 (with search capabilities); This intervention involves answering patient inquiries by ChatGPT-3.5 with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by ChatGPT-3.5 (without search capabilities); This intervention involves answering patient inquiries by ChatGPT-3.5 without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by ChatGPT-4.0 (with search capabilities); This intervention involves answering patient inquiries by ChatGPT-4.0 with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by ChatGPT-4.0 (without search capabilities); This intervention involves answering patient inquiries by ChatGPT-4.0 without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude instant (with search capabilities); This intervention involves answering patient inquiries by Claude instant with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude instant (without search capabilities); This intervention involves answering patient inquiries by Claude instant without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude 2 (with search capabilities); This intervention involves answering patient inquiries by Claude 2 with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Claude 2 (without search capabilities); This intervention involves answering patient inquiries by Claude 2 without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Gemini Pro (with search capabilities); This intervention involves answering patient inquiries by Gemini Pro with search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.; Diagnostic test: Diagnosis by Gemini Pro (without search capabilities); This intervention involves answering patient inquiries by Gemini Pro without search capabilities, before answering any questions, clear the chat history from the previous patient and input the predetermined initialization statement.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Expert indicators-Accuracy	Based on the doctors' responses to patients' issues, a 5-point scale will be used for scoring by an expert panel: 5- The responses are completely accurate, addressing all of the patient's questions or diagnosing by identifying the key points of the patient's complaint. 4- The responses are mostly accurate, generally addressing the patient's questions or diagnosing by identifying the key points of the patient's complaint. 3- The responses are moderately accurate, addressing the patient's questions or diagnosing by identifying the key points of the patient's complaint. 2- The responses are rarely accurate, barely addressing the patient's questions or diagnosing by identifying the key points of the patient's complaint. 1- The responses are very inaccurate, not addressing the patient's questions or diagnosing by identifying the key points of the patient's complaint at all.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. As for subjective expert indicators, the evaluation will be conducted within two months.
Expert indicators-Comprehensiveness	Based on the doctors' responses to patients' issues, a 5-point scale will be used for scoring by an expert panel: 5-The responses are highly comprehensive, addressing various aspects of potential diseases corresponding to the patient's symptoms, providing detailed advice, and offering its own extended interpretations. 4-The responses are mostly comprehensive, covering most aspects of potential common diseases related to the patient's symptoms, and providing fairly detailed advice. 3-The responses are moderately comprehensive, addressing some aspects of potential common diseases related to the patient's symptoms, and offering basic advice. 2-The responses are rarely comprehensive, failing to consider various aspects of potential common diseases related to the patient's symptoms, and providing very limited advice. 1-The responses are not comprehensive at all, overlooking most potential diseases related to the patient's symptoms, and failing to provide any advice.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. As for subjective expert indicators, the evaluation will be conducted within two months.
Expert indicators-Correctness	Based on the doctors' responses to patients' issues, a 5-point scale will be used for scoring by an expert panel: 5- The responses are completely correct, with no inappropriate or ambiguous statements. 4- The responses are mostly correct, with most statements being appropriate and unambiguous. 3- The responses are generally correct, although there are inappropriate or ambiguous statements, they are acceptable. 2- The responses are partially correct, with few statements being appropriate or unambiguous. 1- The responses are completely incorrect, with nearly all statements being inappropriate and full of ambiguities.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. As for subjective expert indicators, the evaluation will be conducted within two months.
Expert indicators-Ethical compliance	Based on the doctor's response to the patient's question, an expert panel will review each item in accordance with the Declaration of Helsinki and the International Code of Medical Ethics which aims to determine whether there are any responses or suggestions that could potentially harm the patient or violate ethical guidelines. The findings will be recorded using binary variables: True-The responses are completely ethical. False-When uncertainties exist, the response includes suggestions for the use of controlled medications and some inappropriate or even counterproductive advice.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. As for subjective expert indicators, the evaluation will be conducted within two months.
Empathy indicators	Results from CARE scales concerning the doctor-patient relationship, which were completed by patients following each diagnostic session. Specifically, the online query section does not apply the evaluation of CARE scales.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. As for subjective empathy indicators, the evaluation will be conducted within two months.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Regular indicators-Total number of questions	The number of follow-up questions asked by the LLM or real doctor to the patient after providing basic answers in a complete conversation.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.
Regular indicators-Follow-up words	The number of words in follow-up questions asked by the LLM or real doctor to the patient after providing basic answers in a complete conversation.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.
Regular indicators-Total number of conversations	The total number of dialogs in a complete conversation between a user and LLMs or a real doctor, where each dialog consists of one question and one answer.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.
Regular indicators-Total conversation cost ($)	The total cost in dollars for completing the entire conversation.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.
Regular indicators-Total conversation time (min)	Timing starts from the user's input and stops when the LLMs or real doctors completes the output of the last sentence.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.
Regular indicators-Number of output statements	The total number of words output by the LLMs or real doctors.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.
Regular indicators-Number of input statements	The sum of the number of characters entered by the user.	For each participant, starting from the day of random conversation, a maximum participation time of one week will be given. After the completion of the dialogues, the system will automatically summarize all objective indicators and dialogue information.

Collaborators and Investigators

• Sponsor: North Sichuan Medical College
• Collaborators: University of Glasgow; Affiliated Hospital of North Sichuan Medical College; Nanchong Central Hospital
• Investigators: Principal Investigator: Jiebin Xie, Doctor, North Sichuan Medical College

Publications and helpful links

General Publications

• Mercer SW, Maxwell M, Heaney D, Watt GC. The consultation and relational empathy (CARE) measure: development and preliminary validation and reliability of an empathy-based consultation process measure. Fam Pract. 2004 Dec;21(6):699-705. doi: 10.1093/fampra/cmh621. Epub 2004 Nov 4.

Study record dates

Study Major Dates

• Study Start (Actual): October 1, 2023
• Primary Completion (Actual): December 12, 2023
• Study Completion (Actual): October 12, 2024

Study Registration Dates

• First Submitted: June 4, 2024
• First Submitted That Met QC Criteria: June 8, 2024
• First Posted (Actual): June 13, 2024

Study Record Updates

• Last Update Posted (Estimated): November 27, 2024
• Last Update Submitted That Met QC Criteria: November 24, 2024
• Last Verified: November 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Pathologic Processes; Infections; Lung Diseases; Bronchial Diseases; Lung Diseases, Obstructive; Embolism and Thrombosis; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Lung Diseases, Interstitial; Fibrosis; Actinomycetales Infections; Mycobacterium Infections; Pulmonary Embolism; Pulmonary Fibrosis; Embolism; Respiratory Tract Infections; Respiratory Tract Diseases; Tuberculosis; Respiration Disorders; Bronchiectasis; Bronchitis
• Other Study ID Numbers: 1426887-2024-1; 22XQT0309 (Other Grant/Funding Number: the cooperation of urban schools in Nanchong City); CBY22-QDA15 (Other Grant/Funding Number: the doctoral startup fund of North Sichuan Medical College); 2022LC005 (Other Grant/Funding Number: the affiliated hospital of North Sichuan Medical College); 23JCYJPT0014 (Other Grant/Funding Number: the scientific research project of the science and technology bureau of Nanchong)

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No