Human Doctors or AI: Evaluating Patient Satisfaction in Urinary Stone Disease Consultations
1 other identifier
interventional
100
1 country
1
Brief Summary
The goal of this observational study is to understand how satisfied patients are after getting medical advice about urinary stone disease from either a real doctor or an artificial intelligence (AI) chatbot. We want to learn whether people feel more satisfied with the information and support they get from human doctors or from AI tools like ChatGPT, Gemini, Perplexity, or Copilot. The main questions it aims to answer are:
- Are patients more satisfied after consulting a real doctor or an AI chatbot?
- Does the time spent in the consultation affect satisfaction? Researchers will compare doctor consultations with consultations from different AI chatbots to see if there are differences in patient satisfaction. Participants will:
- Ask all their medical questions about urinary stones to one of the sources (a doctor or a specific AI chatbot)
- Fill out a short questionnaire (CSQ-8) to rate how satisfied they felt with the answers they received
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P50-P75 for not_applicable
Started Jan 2025
Shorter than P25 for not_applicable
1 active site
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
Study Start
First participant enrolled
January 1, 2025
CompletedPrimary Completion
Last participant's last visit for primary outcome
May 20, 2025
CompletedStudy Completion
Last participant's last visit for all outcomes
May 30, 2025
CompletedFirst Submitted
Initial submission to the registry
July 25, 2025
CompletedFirst Posted
Study publicly available on registry
August 8, 2025
CompletedAugust 8, 2025
August 1, 2025
5 months
July 25, 2025
August 1, 2025
Conditions
Keywords
Outcome Measures
Primary Outcomes (1)
Patient Satisfaction Score
Patient satisfaction will be measured using the validated Client Satisfaction Questionnaire (CSQ-8), which consists of 8 items scored on a 4-point Likert scale. The total score ranges from 8 to 32, with higher scores indicating greater satisfaction.
Within 1 hour after the consultation
Secondary Outcomes (1)
Consultation Duration
During consultation
Study Arms (5)
Doctors Group
EXPERIMENTALParticipants consult a real urologist.
ChatGPT Group
EXPERIMENTALParticipants ask all questions to ChatGPT.
Gemini Group
EXPERIMENTALParticipants ask all questions to Gemini.
Perplexity Group
EXPERIMENTALParticipants ask all questions to Perplexity.
Copilot Group
EXPERIMENTALParticipants ask all questions to Microsoft Copilot.
Interventions
Participants will be randomly assigned to receive medical consultation about urinary stone disease from one of five sources: a real urologist (in-person) or one of four AI chatbots (ChatGPT, Gemini, Perplexity, or Microsoft Copilot). Each participant will be instructed to ask all their questions related to urinary stone disease and continue the consultation until they feel adequately informed. The consultation format (human vs. AI) will depend on group assignment. After the session, participants will complete a validated satisfaction questionnaire (CSQ-8) to assess their experience.
Eligibility Criteria
You may qualify if:
- Newly diagnosed with urinary stone disease,
- Aged 18 years or older,
- Provided written informed consent to participate in the study.
You may not qualify if:
- History of previous urinary stone disease, stone-related procedures,
- Presence of other acute medical conditions unrelated to urinary stone disease,
- Cognitive or communication impairments,
- Pregnancy.
Contact the study team to confirm eligibility.
Sponsors & Collaborators
Study Sites (1)
İzzet Baysal Eğitim ve Araştırma Hastanesi
Bolu, 14030, Turkey (Türkiye)
Related Publications (3)
Whiles BB, Bird VG, Canales BK, DiBianco JM, Terry RS. Caution! AI Bot Has Entered the Patient Chat: ChatGPT Has Limitations in Providing Accurate Urologic Healthcare Advice. Urology. 2023 Oct;180:278-284. doi: 10.1016/j.urology.2023.07.010. Epub 2023 Jul 17.
PMID: 37467806RESULTHanci V, Ergun B, Gul S, Uzun O, Erdemir I, Hanci FB. Assessment of readability, reliability, and quality of ChatGPT(R), BARD(R), Gemini(R), Copilot(R), Perplexity(R) responses on palliative care. Medicine (Baltimore). 2024 Aug 16;103(33):e39305. doi: 10.1097/MD.0000000000039305.
PMID: 39151545RESULTSimon BD, Gelikman DG, Turkbey B. Evaluating the efficacy of artificial intelligence chatbots in urological health: insights for urologists on patient interactions with large language models. Transl Androl Urol. 2024 May 31;13(5):879-883. doi: 10.21037/tau-23-635. Epub 2024 May 7. No abstract available.
PMID: 38855603RESULT
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Design
- Study Type
- interventional
- Phase
- not applicable
- Allocation
- RANDOMIZED
- Masking
- NONE
- Purpose
- HEALTH SERVICES RESEARCH
- Intervention Model
- PARALLEL
- Sponsor Type
- OTHER
- Responsible Party
- PRINCIPAL INVESTIGATOR
- PI Title
- Assistant Professor
Study Record Dates
First Submitted
July 25, 2025
First Posted
August 8, 2025
Study Start
January 1, 2025
Primary Completion
May 20, 2025
Study Completion
May 30, 2025
Last Updated
August 8, 2025
Record last verified: 2025-08
Data Sharing
- IPD Sharing
- Will not share
The data generated and analysed during the current study are not publicly available due to ethical and privacy concerns but are available from the corresponding author on reasonable request.