Role of ChatGPT in Vestibular Schwannoma Management

NCT06163664 | Withdrawn

• 1 other identifier: UP-23-00541
• Study Type: interventional
• Target: N/A
• Locations: 0 countries
• Sites: N/A

Brief Summary

Previous studies have demonstrated that patients frequently undergo significant decision conflict regarding major medical decisions in otolaryngology. There lack validated tools available for decision support for patients. While limited evidence has demonstrated that clinical decision support tools can alleviate decision conflict for patients with diagnosis in otolaryngology, conversational language models were not employed in these studies and may provide additional benefit in this context. This study seeks to evaluate the efficacy of using ChatGPT, a conversational language model with basic clinical knowledge, in alleviating decision conflict for patients with new diagnosis in otolaryngology. For this pilot study, vestibular schwannoma, a benign tumor that develops on the vestibular nerve with known clinical equipoise, has been chosen for the initial study diagnosis. Efficacy will be evaluated by comparison of responses to the Decisional Conflict Scale (DCS) and Satisfaction with Decision (SWD) scores between a group given training in ChatGPT and a control group (no ChatGPT training).

Conditions

Vestibular Schwannoma

Outcome Measures

Primary Outcomes (3)

• Changes in scores of Decisional Conflict Scale after ChatGPT use

  The Decisional Conflict Scale (DCS) measures 5 dimensions of decision making (feeling: uncertain, uninformed, unclear about values, unsupported; ineffective decision making). 15-item validated questionnaire. Score range 5-75 (higher score corresponding to higher levels of conflict in decision making)

  baseline, 1 week follow up, 2 week follow up

• Changes in scores of Satisfaction with Decision after ChatGPT use

  The Satisfaction with Decision (SWD) scale measures satisfaction with health care decisions. 6-item validated questionnaire. Score range 5-30 (higher score corresponding to higher levels of satisfaction with decision)

  baseline, 1 week follow up, 2 week follow up

• Changes in scores for Knowledge on vestibular schwannoma management after ChatGPT use

  4-item questionnaire (Likert scale) assessing participants' confidence in understanding the diagnosis and treatment options for vestibular schwannoma. Score range 5-20 (higher score corresponding to higher levels of confidence in understanding diagnosis and management of vestibular schwannoma)

  baseline, 1 week follow up, 2 week follow up

Study Arms (2)

Intervention

EXPERIMENTAL

Intervention with 1 week use of ChatGPT

Behavioral: Use of chatGPT for 1 week

Delayed control

ACTIVE COMPARATOR

No ChatGPT use for 1 week and intervention after 1 week

Behavioral: Use of chatGPT for 1 week

Interventions

Use of chatGPT for 1 week BEHAVIORAL

Use of chatGPT for 1 week

Delayed control; Intervention

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• years or older
• Diagnosed with vestibular schwannoma
• Have access to internet-enabled device that is compatible with ChatGPT

You may not qualify if:

• \< 18 years old
• patient without diagnosis of vestibular schwannoma
• patient does not have access to internet-enabled device
• patient who declines study participation

Sponsors & Collaborators

• University of Southern California: lead

MeSH Terms

Conditions

Neuroma, Acoustic

Condition Hierarchy (Ancestors)

Neurilemmoma; Neuroendocrine Tumors; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms by Histologic Type; Neoplasms; Neuroma; Nerve Sheath Neoplasms; Neoplasms, Nerve Tissue; Cranial Nerve Neoplasms; Nervous System Neoplasms; Neoplasms by Site; Peripheral Nervous System Neoplasms; Vestibulocochlear Nerve Diseases; Retrocochlear Diseases; Ear Diseases; Otorhinolaryngologic Diseases; Otorhinolaryngologic Neoplasms; Cranial Nerve Diseases; Nervous System Diseases

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: October 24, 2023
• First Posted: December 11, 2023
• Study Start (Estimated): January 1, 2027
• Primary Completion (Estimated): June 30, 2027
• Study Completion (Estimated): November 30, 2027
• Last Updated: January 13, 2026

Record last verified: 2026-01