Please note that the copy function is not enabled for this field.
If you wish to
modify
existing outcomes, please copy and paste the current outcome text into the Update field.
LOGIN
CREATE ACCOUNT
LOGIN
CREATE ACCOUNT
MY TRIALS
REGISTER TRIAL
FAQs
HINTS AND TIPS
DEFINITIONS
Trial Review
Please note that the ANZCTR website will be unavailable from 1:00pm until 2:30pm (AEST) on Thursday 5th June for website maintenance.
Please be sure to log out of the system in order to avoid any loss of data. Thank you and apologies for any inconvenience caused.
The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this
information for consumers
Download to PDF
Trial registered on ANZCTR
Registration number
ACTRN12625000474459p
Ethics application status
Submitted, not yet approved
Date submitted
10/04/2025
Date registered
16/05/2025
Date last updated
16/05/2025
Date data sharing statement initially provided
16/05/2025
Type of registration
Prospectively registered
Titles & IDs
Public title
Symptom checker self-care advice: A mixed-methods evaluation of different presentation formats.
Query!
Scientific title
Integrated generative artificial intelligence into symptom checker self-care advice: A mixed-methods evaluation of different presentation formats.
Query!
Secondary ID [1]
314029
0
None
Query!
Universal Trial Number (UTN)
None
Query!
Trial acronym
Query!
Linked study record
Query!
Health condition
Health condition(s) or problem(s) studied:
fever
336769
0
Query!
vomiting
337146
0
Query!
Condition category
Condition code
Public Health
333258
333258
0
0
Query!
Health promotion/education
Query!
Intervention/exposure
Study type
Interventional
Query!
Description of intervention(s) / exposure
2 (acuity level) x5 (framing group) parallel group design of generative AI self-care advice from an online Symptom Checker after participants are told to imagine they are sick (vomiting and fever). Generative AI self-care advice from an online Symptom checker involves inputing the symptoms one is experiencing into the symptom checker to receive tailored care advice about how to best manage the symptoms at home. The generative AI component is used to collate the relevant self-care information for the symptoms and present the relevant information/care to the user in a way that produces plausible human-like output.
Acuity levels:
Arm 1 = Triage advice given to participants will be 'self-care at home'
Arm 2 = Triage advice given to participants will be 'see the GP within 24 hours'
Framing group:
Arm A = Generative AI enhanced version without enhancements shown in Arms B to D
Arm B = Step-by-step care advice - this advice emphasizes the most important next step, in a logical and numbered sequence.
Arm C = Multi-media content - this advice also provides videos and images to increase user engagement with the health advice (for example, a video about how to manage a fever, and a graphic for signs of dehydration). These specific multi-media content are readily available resources. (Image: Healthdirect 2024 https://www.facebook.com/photo.php?fbid=870444085101447&id=100064075893726&set=a.160444812768048&locale=ga_IE Video: MyDr 2024 https://mydr.com.au/first-aid-self-care/how-do-i-manage-a-fever-dr-norman-swan/)
Arm D = Detailed information about AI used in the model
The the duration of the intervention is 2-5 minutes (this reading a vignette the specific health symptoms and reading the symptom checker advice). Adherence to the intervention will be assessed by submission of the survey. The online survey will be designed that request participants to view the symptom checker advice for a minimum of 2 minutes before moving forward through the survey.
Query!
Intervention code [1]
330606
0
Behaviour
Query!
Comparator / control treatment
the current Symptom checker advice which provides general self-care advice without use of generative AI is the fifth framing group and will be the control in both acuity levels arm 1 and 2.
Query!
Control group
Active
Query!
Outcomes
Primary outcome [1]
340827
0
Intention to follow self-care advice
Query!
Assessment method [1]
340827
0
4 point scale (1 =I would follow none of the advice , 4 = I would follow all the advice ). "Would you follow the self-care advice provided?"
Query!
Timepoint [1]
340827
0
Time 1 = immediately after the intervention
Query!
Primary outcome [2]
340828
0
Intention to see GP in the next 24 hours
Query!
Assessment method [2]
340828
0
5-point scale (1 = Definitely would, 5 = Definitely would not). "If you were in this situation, would you make an appointment with your GP in 24 hours?"
Query!
Timepoint [2]
340828
0
Time 1 = immediately after intervention
Query!
Secondary outcome [1]
445174
0
general trust
Query!
Assessment method [1]
445174
0
From Mac et al., (2024) 10-point scale (1 = not at all trustworthy, 10 = very trustworthy). "How trustworthy do you find the advice?"
Query!
Timepoint [1]
445174
0
Time 1 = immediately post intervention
Query!
Secondary outcome [2]
445175
0
Recall of the advice
Query!
Assessment method [2]
445175
0
Two purpose built questions: 1: Self-care advice: "If you were in this situation, please select the things you should do to manage your symptoms (select all that apply)." Response options: - Drink oral rehydration solution - Drink small sips of water or suck on an ice cube - Place a fan in front of you to help cool yourself down [incorrect] - Consider taking paracetamol if you’re uncomfortable - Dress in light clothing - Use a damp sponge or facecloth to help cool yourself down - Drink hot soup [incorrect] - Have a cool bath [incorrect] 2. Monitoring advice: "If you’re experiencing these symptoms, should you seek further medical advice with the GP? (True/false) - Only for self-care condition - If you have been experiencing bloody diarrhoea [false] - If you start dry heaving (dry heaving is when your body tries to vomit, but nothing comes out) [false] - If you notice that your vomit is white and foamy [false] - If your fever exceeds 39°C [true] - If your urine turns a darker colour [true] 2. Monitoring advice: "If you’re experiencing these symptoms, should you seek further medical advice with the GP? (True/false) - Only for see a GP condition If your urine starts to turn a darker colour [false] If you start dry heaving (dry heaving is when your body tries to vomit, but nothing comes out) [false] If you notice that your vomit is white and foamy [false] If you start to see what resembles coffee grounds in your vomit [true] If you develop sudden and severe abdominal pain [true]
Query!
Timepoint [2]
445175
0
Time 1 Immediately post intervention
Query!
Secondary outcome [3]
445177
0
Perceptions of advice
Query!
Assessment method [3]
445177
0
5 point scale from Davis et al., 2013 from strongly disagree to strongly agree. "The self-care tips were . . ." - worth remembering - attention grabbing - powerful - informative - meaningful - convincing
Query!
Timepoint [3]
445177
0
Time 1 immediately post intervention
Query!
Secondary outcome [4]
445178
0
Acceptability
Query!
Assessment method [4]
445178
0
From Venkatesh et al., 2003: - "Next time I have symptoms and am unsure what to do, I would use the symptom checker" - "I would recommend this symptom checker to a friend if they were not sure what to do about symptoms they were experiencing"
Query!
Timepoint [4]
445178
0
Time 1 immediately post intervention.
Query!
Secondary outcome [5]
445179
0
Emotional impact of the advice
Query!
Assessment method [5]
445179
0
From Dolan et al., 2002: Receiving this advice would make me feel: - positive - comfortable - satisfied - calm - negative - nervous - worried - confused - unsure
Query!
Timepoint [5]
445179
0
Time 1 immediately post intervention
Query!
Secondary outcome [6]
445182
0
Expectations
Query!
Assessment method [6]
445182
0
The symptom checker advice met my expectations (5-point strongly disagree to strongly agree)
Query!
Timepoint [6]
445182
0
Time 1 - Immediately post intervention
Query!
Secondary outcome [7]
445935
0
Symptoms described
Query!
Assessment method [7]
445935
0
What were the main symptoms described in the story before you saw the symptom checker advice? Headache Fever Body rash Shortness of breath Vomiting Chest pain
Query!
Timepoint [7]
445935
0
Time 1- immediately post-intervention
Query!
Secondary outcome [8]
446051
0
Recall of advice
Query!
Assessment method [8]
446051
0
Recall of advice: What was the advice you were given? Self-care at home See GP in 2 hours See GP in 24 hours See GP in week Go to emergency
Query!
Timepoint [8]
446051
0
Time 2 - 2 weeks post intervention
Query!
Secondary outcome [9]
446052
0
Brief understanding
Query!
Assessment method [9]
446052
0
Brief understanding (purpose-built): A) Self-care advice: Please select the things the symptom checker suggested you should do to manage your symptoms (select all that apply) a. Drink oral rehydration solution b. Drink small sips of water or suck on an ice cube c. Place a fan in front of you to help cool yourself down [false] d. Consider taking paracetamol if you’re uncomfortable e. Dress in light clothing f. Use a damp sponge or facecloth to help cool yourself down g. Drink hot soup [false] g. Have a cool bath [false] B. Monitoring advice: What were the suggestions by the symptom checker regarding when you should seek further medical advice with the GP? (True/false) - only for self-care If you have been experiencing blood diarrheoa [false] If you start dry heaving (dry heaving is when your body tries to vomit, but nothing comes out) [false] If you notice that your vomit is white and foamy [false] If your fever exceeds 39°C If your urine turns a darker colour B. Monitoring advice: What were the suggestions by the symptom checker regarding when you should you seek further medical advice by going to the nearest emergency department? (True/false) - only for see a GP in 24 hours a. If your urine starts to turn a darker colour [false] b. If you start dry heaving (dry heaving is when your body tries to vomit, but nothing comes out) [false] c. If you notice that your vomit is white and foamy [false] d. If you start to see what resembles coffee grounds in your vomit e. If you develop sudden and severe abdominal pain
Query!
Timepoint [9]
446052
0
Time 2 - 2 weeks post intervention
Query!
Secondary outcome [10]
446495
0
Emotional trust
Query!
Assessment method [10]
446495
0
Emotional trust - from Komiak & Benbasat (2006) (which was adapted for use in a previous trial evaluating a symptom checker chat bot by Jin et al., 2023) Please rate the following items from 1 (strongly agree) to 7 (strongly disagree): I feel secure about relying on this symptom checker to know what to do next I feel comfortable about relying on this symptom checker to know what to do next I feel content about relying on this symptom checker to know what to do next
Query!
Timepoint [10]
446495
0
timepoint 1 - immediately post intervention
Query!
Secondary outcome [11]
447629
0
Cognitive trust
Query!
Assessment method [11]
447629
0
Cognitive trust - from Komiak & Benbasat (2006) (which was adapted for use in a previous trial evaluating a symptom checker chat bot by Jin et al., 2023) Please rate the following items from 1 (strongly agree) to 7 (strongly disagree): This symptom checker is a real expert in providing relevant health information This symptom checker has good knowledge This symptom checker is unbiased This symptom checker provides me with competent and useful information
Query!
Timepoint [11]
447629
0
timepoint 1 - immediately post intervention
Query!
Eligibility
Key inclusion criteria
Inclusion criteria for participation in the trial include:
a) Reside in Australia
b) English proficiency
Query!
Minimum age
18
Years
Query!
Query!
Maximum age
No limit
Query!
Query!
Sex
Both males and females
Query!
Can healthy volunteers participate?
Yes
Query!
Key exclusion criteria
No exclusion criteria
Query!
Study design
Purpose of the study
Educational / counselling / training
Query!
Allocation to intervention
Randomised controlled trial
Query!
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Participation will be online and hosted by Qualtrics. Participants will be automatically randomised to one of the 10 study groups using the randomiser function in Qualtrics. Qualtrics utilises a randomiser which is based on the Mersenne Twister, a pseudorandom number generator. Therefore researchers will be unaware which participant is allocated into which study arm.
Query!
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Qualtrics utilises a randomiser which is based on the Mersenne Twister, a pseudorandom number generator.
Query!
Masking / blinding
Blinded (masking used)
Query!
Who is / are masked / blinded?
The people receiving the treatment/s
The people assessing the outcomes
The people analysing the results/data
Query!
Query!
Query!
Query!
Intervention assignment
Parallel
Query!
Other design features
Query!
Phase
Not Applicable
Query!
Type of endpoint/s
Efficacy
Query!
Statistical methods / analysis
A total of approximately 2000 participants will be recruited. As we plan a 2 (acuity levels) x 5 (framing group) parallel group design with 90%, alpha = 0.05, and a small effect size, the sample size given by Gpower is n = 160 per group. This totals n=1600 in total. We will also recruit approximately an additional 20% to account for drop-out at follow-up (Time 2).
This data will be analysed with appropriate regression models to test for overall differences in primary and secondary outcomes. To assess for any differences between groups, planned contrasts will also be used, adjusting the significance threshold for multiple pairwise comparisons.
Query!
Recruitment
Recruitment status
Not yet recruiting
Query!
Date of first participant enrolment
Anticipated
10/06/2025
Query!
Actual
Query!
Date of last participant enrolment
Anticipated
1/07/2025
Query!
Actual
Query!
Date of last data collection
Anticipated
14/07/2025
Query!
Actual
Query!
Sample size
Target
2000
Query!
Accrual to date
Query!
Final
Query!
Recruitment in Australia
Recruitment state(s)
ACT,NSW,NT,QLD,SA,TAS,WA,VIC
Query!
Funding & Sponsors
Funding source category [1]
318534
0
Government body
Query!
Name [1]
318534
0
HealthDirect Australia
Query!
Address [1]
318534
0
Query!
Country [1]
318534
0
Australia
Query!
Primary sponsor type
University
Query!
Name
Kirsten McCaffery - Sydney Health Literacy Lab, The University of Sydney
Query!
Address
Query!
Country
Australia
Query!
Secondary sponsor category [1]
321402
0
None
Query!
Name [1]
321402
0
Query!
Address [1]
321402
0
Query!
Country [1]
321402
0
Query!
Ethics approval
Ethics application status
Submitted, not yet approved
Query!
Ethics committee name [1]
317137
0
The University of Sydney Human Research Ethics Committee
Query!
Ethics committee address [1]
317137
0
https://www.sydney.edu.au/research/research-integrity-and-ethics.html
Query!
Ethics committee country [1]
317137
0
Australia
Query!
Date submitted for ethics approval [1]
317137
0
14/02/2025
Query!
Approval date [1]
317137
0
Query!
Ethics approval number [1]
317137
0
2025/HE000143
Query!
Summary
Brief summary
Online symptom checkers are digital health tools allowing health consumers to input symptoms to receive triage or diagnosis advice. If appropriate, another important feature is to provide consumers with self-care advice for managing their symptoms at home. Integrating Generative Artificial Intelligence (AI) into symptom checkers may help address unmet needs of diverse users, including those with lower health literacy. A retrieval-augmented generation (RAG) framework may be particularly useful by addressing concerns around accuracy via greater control of the quality of information informing the AI output. However, it is unknown how to best communicate the use of RAG generative AI in symptom checkers, nor how to present the advice. This project aims to 1) evaluate the effects of different presentations of generative AI symptom checker self-care advice on intentions, trustworthiness and understanding of the advice, and 2) explore in-depth user responses and perspectives on AI generated triage and self-care advice in an online symptom checker.
Query!
Trial website
Query!
Trial related presentations / publications
Query!
Public notes
Query!
Contacts
Principal investigator
Name
140122
0
Prof Kirsten McCaffery
Query!
Address
140122
0
Sydney Health literacy lab, The University of Sydney, 127A Edward Ford Building, Sydney, NSW, 2006
Query!
Country
140122
0
Australia
Query!
Phone
140122
0
+61 2 9351 7220
Query!
Fax
140122
0
Query!
Email
140122
0
[email protected]
Query!
Contact person for public queries
Name
140123
0
Kirsten McCaffery
Query!
Address
140123
0
Sydney Health Literacy Lab, The University of Sydney, 127A Edward Ford Building, Sydney, NSW, 2006
Query!
Country
140123
0
Australia
Query!
Phone
140123
0
+61 2 9351 7220
Query!
Fax
140123
0
Query!
Email
140123
0
[email protected]
Query!
Contact person for scientific queries
Name
140124
0
Kirsten McCaffery
Query!
Address
140124
0
Sydney Health Literacy Lab, The University of Sydney, 127A Edward Ford Building, Sydney, NSW, 2006
Query!
Country
140124
0
Australia
Query!
Phone
140124
0
+61 2 9351 7220
Query!
Fax
140124
0
Query!
Email
140124
0
[email protected]
Query!
Data sharing statement
Will the study consider sharing individual participant data?
Yes
Will there be any conditions when requesting access to individual participant data?
Persons/groups eligible to request access:
•
Researchers
Conditions for requesting access:
•
Yes, conditions apply:
•
Requires a data sharing agreement between data requester and trial custodian or sponsor
What individual participant data might be shared?
•
All de-identified individual participant data
What types of analyses could be done with individual participant data?
•
Any type of analysis (i.e. no restrictions on data re-use)
When can requests for individual participant data be made (start and end dates)?
From:
After publication of main results
To:
Not yet decided
Where can requests to access individual participant data be made, or data be obtained directly?
•
Email of trial custodian, sponsor or committee:
Principle Investigator - Professor Kirsten McCaffery:
[email protected]
Are there extra considerations when requesting access to individual participant data?
No
What supporting documents are/will be available?
No Supporting Document Provided
Results publications and other study-related documents
Documents added manually
No documents have been uploaded by study researchers.
Documents added automatically
No additional documents have been identified.
Download to PDF