Before kidney stone surgery with a flexible or semirigid ureteroscope, patients must read and sign a written consent form, but many patients find these forms long and hard to understand. This study tests whether listening to an audio recording of the same consent form, in addition to the usual written form and the surgeon's explanation, helps patients understand the operation better. It also asks whether it matters if the recording is read by a real urologist or produced by artificial intelligence (AI) from a clone of that same urologist's voice.
Adults scheduled for their first ureteroscopy or retrograde intrarenal surgery at three hospitals in Turkey will be randomly assigned to one of three groups: (A) standard written consent only, (B) standard consent plus an audio recording read by a urologist, or (C) standard consent plus the same text produced by an AI-cloned version of the same urologist's voice. All three groups receive exactly the same information, word for word; only the way it is delivered differs. Patients in group C are told that the voice was produced by AI.
The main outcome is a 10-question knowledge test on the content of the consent form, taken immediately after the consent process. Anxiety (State-Trait Anxiety Inventory) and satisfaction are also measured on the same day. No forms are completed on the day of surgery.
Age 18 years or older
Scheduled for elective ureteroscopy (URS) or retrograde intrarenal surgery (RIRS)
Able to read, understand and communicate verbally in Turkish
Provides written informed consent to participate in the study
Hearing or visual impairment preventing use of the study materials
Confusion, dementia, psychosis or any other condition affecting capacity to consent
Emergency surgery
Previous URS or RIRS
Parallel
Standard written informed consent
Other interventionThe institution's unified written informed consent form for ureteroscopy and retrograde intrarenal surgery, read and signed by the patient, together with the physician's usual verbal explanation. Delivered identically in all three arms.
Human-voice audio consent recording
BehavioralAn approximately 12-minute audio recording of the complete consent text, read word for word by one urologist (the same recording at all centers; not the patient's own surgeon). Presented after the standard written consent and physician explanation, on a tablet with headphones in the patient's room without companions; the patient may replay it and the number of replays is recorded. Loudness-normalized to -24 LUFS. Introduced to the patient as "a recording of the entire consent form read by a urologist".
AI-cloned-voice audio consent recording
BehavioralThe same consent text, generated once with Resemble.ai from a voice clone of the same urologist (reference sample: a separate recording of at least 5 minutes of a different text), frozen before enrollment with no live AI calls. Duration approximately 12 minutes; loudness-matched (-24 LUFS), codec and delivery identical to the human-voice recording, presented after the standard written consent and physician explanation, on a tablet with headphones; replay allowed and counted. Patients are informed that the voice was generated with AI from a urologist's voice.
Post-consent knowledge score
Score on a 10-item multiple-choice test derived from the consent text (range 0-10; higher scores indicate better knowledge of the procedure, its risks, alternatives and patient responsibilities). Each item is mapped to a specific paragraph of the consent form. Analyzed as a continuous variable.
Post-consent state anxiety (STAI-S)
State-Trait Anxiety Inventory, State form (Turkish version, Öner \& Le Compte), range 20-80; higher scores indicate greater anxiety. Measured immediately after the consent process and analyzed adjusted for the pre-consent STAI-S score (measured immediately before the consent process) and STAI-T.
Patient satisfaction and perceived clarity
Three study-specific 5-point items (perceived clarity of the information, adequacy of the information for decision-making, overall satisfaction with the consent process); each scored 1-5, higher scores indicate better outcomes. Reported item by item; total score (3-15) secondary. Not validated.
Perceived naturalness and usefulness of the audio recording (arms B and C)
Two study-specific 5-point items: naturalness of the voice (1 = not at all natural to 5 = completely natural) and usefulness of receiving the information as audio (1 = not at all to 5 = very much). Higher scores indicate greater perceived naturalness/usefulness. Asked in both audio arms.
Acceptability of the AI-generated voice (arm C)
Single study-specific 5-point item: "Did it bother you that the voice was generated by artificial intelligence?" (1 = not at all to 5 = very much; higher scores indicate lower acceptability). Administered on a separate sheet after the naturalness items have been collected.
Click on the lead sponsor to view all of their trials.
Aydin Adnan Menderes University
Lead sponsor
Aydin City Hospital
Collaborator
Kutahya Health Sciences University
Collaborator
