Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
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:
Researchers will compare doctor consultations with consultations from different AI chatbots to see if there are differences in patient satisfaction.
Participants will:
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Doctors Group | Experimental | Participants consult a real urologist. |
|
| ChatGPT Group | Experimental | Participants ask all questions to ChatGPT. |
|
| Gemini Group | Experimental | Participants ask all questions to Gemini. |
|
| Perplexity Group | Experimental | Participants ask all questions to Perplexity. |
|
| Copilot Group | Experimental | Participants ask all questions to Microsoft Copilot. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Medical Consultation | Behavioral | 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. |
| Measure | Description | Time Frame |
|---|---|---|
| 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 |
| Measure | Description | Time Frame |
|---|---|---|
| Consultation Duration | Total duration (in minutes) of the consultation session (doctor or chatbot) will be recorded and compared across all groups. | During consultation |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| İzzet Baysal Eğitim ve Araştırma Hastanesi | Bolu | 14030 | Turkey (Türkiye) |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 37467806 | Result | 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. | |
| 39151545 | Result | Hanci 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. |
Not provided
Not provided
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.
Not provided
Not provided
Not provided
Not provided
Not provided
| Type | Includes Protocol | Includes SAP | Includes ICF | Document Label | Document Date | Document Uploaded Date | Document File Name |
|---|---|---|---|---|---|---|---|
| Prot | Yes | No | No | Study Protocol | Aug 1, 2025 | Aug 1, 2025 | Prot_000.pdf |
| SAP | No | Yes | No | Statistical Analysis Plan | Aug 1, 2025 | Aug 1, 2025 | SAP_001.pdf |
Not provided
| ID | Term |
|---|---|
| D017060 | Patient Satisfaction |
| ID | Term |
|---|---|
| D000074822 | Treatment Adherence and Compliance |
| D015438 | Health Behavior |
| D001519 | Behavior |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
|
| 38855603 | Result | Simon 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. |
| 41385971 | Derived | Yildiz HA. Human Doctors or AI? Evaluating Patient Satisfaction in Urinary Stone Disease Consultations. J Surg Res. 2026 Jan;317:181-188. doi: 10.1016/j.jss.2025.11.026. Epub 2025 Dec 11. |