AI-Generated Maternal Voice Storytelling During Pediatric Adenotonsillectomy

Official title

AI-Generated Maternal Voice Storytelling Modulates the Perioperative Stress Response and Reduces Emergence Delirium in Children Undergoing Adenotonsillectomy: A Three-Arm Randomized Controlled Trial

Overview

This prospective, three-arm randomized controlled trial aims to evaluate the effects of AI-generated maternal voice storytelling on the perioperative stress response, emergence delirium, anesthetic requirements, and perioperative physiological parameters in children undergoing elective adenotonsillectomy. Participants will be randomly assigned to receive AI-generated maternal voice storytelling, relaxing instrumental music, or standard perioperative care. Standardized anesthesia protocols will be used in all groups, and perioperative outcomes will be compared among the three study arms.

Detailed description

Pediatric adenotonsillectomy is frequently associated with perioperative anxiety, autonomic stress responses, and emergence delirium despite standardized anesthetic management. Non-pharmacological auditory interventions, including music and maternal voice exposure, have been investigated as potential strategies to improve perioperative outcomes. However, the effects of personalized artificial intelligence (AI)-generated maternal voice storytelling have not been evaluated in pediatric surgical patients.

This prospective, single-center, three-arm randomized controlled trial will investigate the effects of AI-generated maternal voice storytelling on perioperative stress response, emergence delirium, anesthetic requirements, and perioperative physiological parameters in children undergoing elective adenotonsillectomy under general anesthesia. Participants will be randomly assigned to one of three groups: (1) AI-generated maternal voice storytelling, (2) relaxing instrumental music, or (3) standard care without auditory intervention.

The assigned auditory intervention will be initiated after premedication and continued throughout the perioperative period using headphones. Standardized anesthesia protocols will be applied to all participants. Emergence delirium will be assessed using the Pediatric Anesthesia Emergence Delirium (PAED) scale. Secondary outcomes will include induction compliance, perioperative hemodynamic variables, sevoflurane consumption, postoperative pain scores, and recovery characteristics. The study aims to determine whether personalized AI-generated maternal voice storytelling influences perioperative outcomes compared with relaxing music and standard perioperative care.

Interventions

• Other AI-Generated Maternal Voice Storytelling
  Personalized storytelling generated using artificial intelligence voice synthesis based on a pre-recorded maternal voice sample. The audio intervention will be delivered through headphones after preoperative sedation and continued throughout the perioperative period until recovery.
• Other Relaxing Instrumental Music
  Relaxing instrumental music delivered through headphones after preoperative sedation and continued throughout the perioperative period until recovery.
• Drug midazolam premedication
  All participants receive intravenous midazolam as standard premedication before anesthesia induction according to the institutional pediatric anesthesia protocol to reduce preoperative anxiety and facilitate smooth separation from parents.
• Procedure Standard General Anesthesia Care
  All participants receive standardized general anesthesia according to the institutional pediatric anesthesia protocol. Anesthesia is induced with intravenous propofol, fentanyl, and rocuronium, followed by endotracheal intubation. Anesthesia is maintained with sevoflurane in an oxygen/air mixture throughout the surgical procedure. Intraoperative monitoring and anesthetic management are standardized for all study groups.
• Device Headphones
  Over-ear headphones are used in all study groups during the perioperative period. In the AI-generated maternal voice storytelling and relaxing music groups, the headphones deliver the assigned auditory intervention. In the control group, headphones are worn without audio playback to minimize exposure to environmental noise and to maintain consistency across study groups.

Primary outcome measures

• Emergence Delirium [Time frame: From admission to the post-anesthesia care unit until 30 minutes after arrival.]

Secondary outcome measures (5)

• Induction Compliance [Time frame: During anesthetic induction.]
• Sevoflurane Consumption [Time frame: Throughout the intraoperative period.]
• Mean Arterial Pressure (MAP) [Time frame: Baseline , and at 5, 15, 30, and 45 minutes after anesthesia induction.]
• Heart Rate (HR) [Time frame: Baseline , and at 5, 15, 30, and 45 minutes after anesthesia induction.]
• Heart Rate Variability (HRV) [Time frame: Baseline, and at 5, 15, 30, and 45 minutes after anesthesia induction.]

Eligibility criteria

Inclusion criteria

• Children aged 3 to 12 years.
• Scheduled for elective adenotonsillectomy under general anesthesia.
• American Society of Anesthesiologists (ASA) physical status I or II.
• Written informed consent obtained from a parent or legal guardian.

Exclusion criteria

• Hearing impairment or inability to receive auditory stimulation.
• Developmental delay, neurological or psychiatric disorders.
• Use of sedative, antipsychotic, or anticonvulsant medications.
• Known allergy or contraindication to study medications.
• Refusal of participation by the parent/legal guardian.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Single blind

Primary purpose

Prevention

Study locations

Turkey (Türkiye) · 1 center

• Adıyaman University — Adıyaman

Identifiers

NCT: NCT07706725 · ADYU-ANS-NY-015

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗