Vignette Based InterventionNCT07250516
The Diagnostic and Triage Capacity of Laypeople-large Language Model Collaboration in China
A study testing AI-assisted health information seeking and Conventional internet search for health information in people with Vignette Based Intervention and LLM-based AI Dialogue Bot, run by Huazhong University of Science and Technology at 1 site in China.
Trial summary
The goal of this randomized controlled trial is to evaluate the role of large language models in enhancing laypeople's ability to self-diagnose and triage common diseases. The main questions it aims to answer are: Does using an LLM help participants make more accurate self-diagnoses and care decisions for common… Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Vignette Based Intervention, LLM-based AI Dialogue Bot
- What is being tested?
- AI-assisted health information seeking and Conventional internet search for health information
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 6,360 participants
- Where
- 1 siteChina
- Study dates
- 27 Apr 2025to 1 Jul 2025
- Phase
- Interventional
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Age 18 years or older
- Current resident of mainland China
- History of high-quality participation in online surveys on Credamo platform (historical survey acceptance rate ≥ 80% and personal credit score ≥ 70)
Who cannot join
- Incomplete survey responses
- Failure on embedded quality-check items
- Implausibly short completion time (<180 seconds for search engine group; <360 seconds for LLM group)
- Provision of non-diagnostic or irrelevant responses (e.g., "unknown", "don't know")
- Consistent pattern of identical responses across all items
Trial locations and contacts
1 site in 1 country.
China1 site
Tongji Medical College of Huazhong University of Science & Technology School of Medicine and Health Management
Wuhan, Hubei
About this study
Official title: The Diagnostic and Triage Capacity of Laypeople-large Language Model Collaboration: a National Pretest-posttest Randomized Controlled Experiment in China
The goal of this randomized controlled trial is to evaluate the role of large language models in enhancing laypeople's ability to self-diagnose and triage common diseases. The main questions it aims to answer are:
- Does using an LLM help participants make more accurate self-diagnoses and care decisions for common illnesses, compared to their first guess without any help?
- How much better is it when people work together with an LLM, compared to using a regular search engine, using the LLM alone, or how doctors would decide? Researchers will compare participants who were randomly assigned to either the LLM group (using DeepSeek) or the search engine group to see if the LLM-assisted approach leads to better clinical judgments.
Read more
Participants will:
- Read one of 48 short, realistic health vignettes;
- Make an initial guess about what might be wrong by listing up to three possible causes, ranked from most to least likely, and choose a care level: seek immediate care, see a doctor within one day, see a doctor within one week, or manage at home without medical care.
- Use their assigned tool (either DeepSeek or a standard search engine) to look up information and update their guess and care decision;
- Submit their final diagnosis and care choice after using the tool. In addition, the study team evaluated the performance of four other AI models (GPT-4o, GPT-o1, DeepSeek-v3, and DeepSeek-r1) and 33 experienced general physicians on the same vignettes.
- Being tested
- AI-assisted health information seeking, Conventional internet search for health information
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-assisted health information seekingBehavioural
Participants in this group used a large language model (DeepSeek) to search for medical information related to a clinical vignette after providing initial diagnostic and triage decisions. They were instructed to interact freely with the model to gather insights and then update their diagnoses and triage recommendations. The intervention simulates real-world use of AI tools for personal health decision-making
Conventional internet search for health informationBehavioural
Participants in this group used mainstream internet search engines (e.g., Baidu, Google, Bing) to look up information about the clinical vignette after making initial diagnostic and triage decisions. They were allowed to search freely but were not permitted to use any named AI chatbot or large language model platform. This group represents typical self-directed online health information seeking behavior.
| Study group | Role | What they receive |
|---|---|---|
| layperson-LLM integrated group | Experimental | After initially answering a clinical diagnosis and triage question without the aid of tools, the participants were asked to use a large language model (Deepseek v3 or r1) to retrieve health information and then answer the same question again Receives: Behavioral: AI-assisted health information seeking |
| layperson-search engine group | Active comparator | After initially answering a clinical diagnosis and triage question without the use of tools, the participants were required to use a search engine to retrieve health information and then answer the same question again Receives: Behavioral: Conventional internet search for health information |
What is being measured
The primary outcome is the main question the study is designed to answer.
Top-3 Diagnostic Accuracy
The primary diagnostic outcome was defined as the proportion of participants who included the correct diagnosis in their top three differential diagnoses after using the assigned tool (LLM or search engine). Accuracy was assessed for each of the 48 clinical vignettes and aggregated across all participants in each group.
Measured: Immediately after intervention (within the same survey session)
Triage Accuracy (4-class exact match)
Triage accuracy was defined as the proportion of participants who selected the correct triage level (emergent care, within one day, within one week, or self-care) that matched the reference standard. There were 12 vignettes per triage category.
Measured: Immediately after intervention (within the same survey session)
Secondary outcomes (2)
Top-1 Diagnostic Accuracy
The proportion of participants who selected the correct diagnosis as their top (first) diagnosis after using the assigned tool. This measures the precision of laypeople's final diagnostic judgment.
Measured: Immediately after intervention (within the same survey session)
Triage Accuracy (2-class binary match)
Measured: Immediately after intervention (within the same survey session)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted26 Nov 2025
- Study start27 Apr 2025
- Primary completion1 Jul 2025
- Study completion1 Jul 2025
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Vignette Based InterventionStudies of the same condition, open and under way.
- More trials run by Huazhong University of Science and TechnologyThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind
- Who is masked
- Participant
- Enrolment
- 6,360 participants (actual)
Sponsor and investigators
- Lead sponsor
- Huazhong University of Science and Technology
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Zhang Min, Huazhong University of Science and Technology
- Investigators
- Chenxi Liu, Principal investigator, Huazhong University of Science and Technology
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07250516
- Sponsor's protocol ID
- JCYJ20240813115806009
- Status last verified
- Oct 2025
- First submitted
- 17 Nov 2025
- Last updated
- 10 Sep 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: According to the ethical agreements, individual participant data cannot be deposited in a public data repository and can be made available for research purposes upon request. Researchers can request the de-identified data by submitting a data use agreement (DUA) to the Medical Ethics Committee of Tongji Medical College, Huazhong University of Science and Technology. The DUA must state that the data will be used for research purposes only and that no attempt will be made to re-identify participants. Upon approval of the request, the data will be made available. The contact information is as follows: tongjilunli@vip.163.com (email); +86-27-83691785 (fax); Office 12, 16th Floor, Teaching Building 2, School of Basic Medicine, Tongji Medical College, No. 13 Hangkong Road, Wuhan, Hubei Province, China (address).
Study at a glance
From the registry record, last updated by the sponsor on 10 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- The Diagnostic and Triage Capacity of Laypeople-large Language Model Collaboration: a National Pretest-posttest Randomized Controlled Experiment in China
- ClinicalTrials.gov ID
- NCT07250516
- Acronym / sponsor ID
- JCYJ20240813115806009
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 6,360 participants (actual)
- Lead sponsor
- Huazhong University of Science and TechnologyUniversity, hospital or other
- Study start
- 27 Apr 2025 (actual)
- Primary completion
- 1 Jul 2025 (actual)
- Study completion
- 1 Jul 2025 (actual)
- First posted
- 26 Nov 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The goal of this randomized controlled trial is to evaluate the role of large language models in enhancing laypeople's ability to self-diagnose and triage common diseases. The main questions it aims to answer are:
- Does using an LLM help participants make more accurate self-diagnoses and care decisions for common illnesses, compared to their first guess without any help?
- How much better is it when people work together with an LLM, compared to using a regular search engine, using the LLM alone, or how doctors would decide? Researchers will compare participants who were randomly assigned to either the LLM group (using DeepSeek) or the search engine group to see if the LLM-assisted approach leads to better clinical judgments.
Participants will:
- Read one of 48 short, realistic health vignettes;
- Make an initial guess about what might be wrong by listing up to three possible causes, ranked from most to least likely, and choose a care level: seek immediate care, see a doctor within one day, see a doctor within one week, or manage at home without medical care.
- Use their assigned tool (either DeepSeek or a standard search engine) to look up information and update their guess and care decision;
- Submit their final diagnosis and care choice after using the tool. In addition, the study team evaluated the performance of four other AI models (GPT-4o, GPT-o1, DeepSeek-v3, and DeepSeek-r1) and 33 experienced general physicians on the same vignettes.
Study design
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind (participant)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| layperson-LLM integrated group | Experimental | Behavioral: AI-assisted health information seekingAfter initially answering a clinical diagnosis and triage question without the aid of tools, the participants were asked to use a large language model (Deepseek v3 or r1) to retrieve health information and then answer the same question again |
| layperson-search engine group | Active comparator | Behavioral: Conventional internet search for health informationAfter initially answering a clinical diagnosis and triage question without the use of tools, the participants were required to use a search engine to retrieve health information and then answer the same question again |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (3 listed)
- Age 18 years or older
- Current resident of mainland China
- History of high-quality participation in online surveys on Credamo platform (historical survey acceptance rate ≥ 80% and personal credit score ≥ 70)
Key exclusion criteria (5 listed)
- Incomplete survey responses
- Failure on embedded quality-check items
- Implausibly short completion time (<180 seconds for search engine group; <360 seconds for LLM group)
- Provision of non-diagnostic or irrelevant responses (e.g., "unknown", "don't know")
- Consistent pattern of identical responses across all items
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| AI-assisted health information seekingParticipants in this group used a large language model (DeepSeek) to search for medical information related to a clinical vignette after providing initial diagnostic and triage decisions. They were instructed to interact freely with the model to gather insights and then update their diagnoses and triage recommendations. The intervention simulates real-world use of AI tools for personal health decision-making | Behavioural | layperson-LLM integrated group |
| Conventional internet search for health informationParticipants in this group used mainstream internet search engines (e.g., Baidu, Google, Bing) to look up information about the clinical vignette after making initial diagnostic and triage decisions. They were allowed to search freely but were not permitted to use any named AI chatbot or large language model platform. This group represents typical self-directed online health information seeking behavior. | Behavioural | layperson-search engine group |
Primary outcome
Top-3 Diagnostic Accuracy
Time frame: Immediately after intervention (within the same survey session)
The primary diagnostic outcome was defined as the proportion of participants who included the correct diagnosis in their top three differential diagnoses after using the assigned tool (LLM or search engine). Accuracy was assessed for each of the 48 clinical vignettes and aggregated across all participants in each group.
Triage Accuracy (4-class exact match)
Time frame: Immediately after intervention (within the same survey session)
Triage accuracy was defined as the proportion of participants who selected the correct triage level (emergent care, within one day, within one week, or self-care) that matched the reference standard. There were 12 vignettes per triage category.
2 secondary outcomes
Top-1 Diagnostic Accuracy
Time frame: Immediately after intervention (within the same survey session)
Triage Accuracy (2-class binary match)
Time frame: Immediately after intervention (within the same survey session)
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 10 Sep 2026.
- Individual participant dataSharing planned: Yes. According to the ethical agreements, individual participant data cannot be deposited in a public data repository and can be made available for research purposes upon request. Researchers can request the de-identified data by submitting a data use agreement (DUA) to the Medical Ethics Committee of Tongji Medical College, Huazhong University of Science and Technology. The DUA must state that the data will be used for research purposes only and that no attempt will be made to re-identify participants. Upon approval of the request, the data will be made available. The contact information is as follows: tongjilunli@vip.163.com (email); +86-27-83691785 (fax); Office 12, 16th Floor, Teaching Building 2, School of Basic Medicine, Tongji Medical College, No. 13 Hangkong Road, Wuhan, Hubei Province, China (address).
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Chenxi Liu principal investigator
Huazhong University of Science and Technology
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing AI-assisted health information seeking and Conventional internet search for health information in people with Vignette Based Intervention and LLM-based AI Dialogue Bot, run by Huazhong University of Science and Technology at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 3 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 10 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Top-3 Diagnostic Accuracy (time frame: Immediately after intervention (within the same survey session)). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 10 Sep 2026.