Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness.
Yu He Ke, Liyuan Jin, Kabilan Elangovan...
https://pubmed.ncbi.nlm.nih.gov/40185842Actively Recruiting
Phase Not Applicable
Age: 21Years - 99Years
All Genders
Healthy Volunteers
ID06949462
Evaluating the Effectiveness of Large Language Models in Anaesthesia and Procedural Consent: A Comparative Analysis With Traditional Patient Consent Methods
Led by Singapore General Hospital · Updated on 2026-05-07
120
Participants Needed
2
Research Sites
N/A
Total Duration
On this page
AI-Summary
What this Trial Is About
Researchers are evaluating the PEAR (Patient Education of Anaesthesia Risks) chatbot, a multilingual, AI-driven tool designed to improve patient understanding of anaesthesia risks during the consent process. The trial compares this digital method to the traditional face-to-face verbal consent provided by anaesthetists. PEAR aims to enhance patient education, satisfaction, and reduce preoperative anxiety while supporting clinician workflow without altering standard care. Participants undergoing elective surgery will be randomly assigned to either the PEAR chatbot intervention or the standard verbal consent control group. Those in the intervention group interact with the chatbot prior to meeting their anaesthetist, receiving personalized, interactive education on anaesthesia risks and procedures. The control group receives usual face-to-face counselling by a licensed anaesthetist following institutional protocols. Both groups eventually meet their anaesthetist to ensure clinical oversight. During the study visit, participants complete quizzes and surveys to assess understanding, satisfaction, and anxiety levels. Clinicians record the time and workload involved in each consent method. Data is collected electronically and stored securely. The main outcome measured is patient self-reported understanding of anaesthesia risks immediately after the PEAR interaction. The trial runs until April 2026, including assessments of perceived usefulness, ease of use, cost effectiveness, and behavioral intentions regarding the chatbot.
CONDITIONS
Brief Title
Effectiveness of Large Language Model for Anaesthesia and Procedural Consent
Who Can Participate
Age: 21Years - 99Years
All Genders
Healthy Volunteers
Eligibility Criteria
You may qualify if you...
- Adults (≥21 years old) undergoing elective surgery requiring anaesthesia
- Classified as ASA Physical Status I to III
- Able to provide informed consent
- Able to communicate effectively in English, Chinese (Mandarin), Malay, or Tamil
- Willing and able to complete questionnaires and interact with the PEAR chatbot (intervention arm)
You will not qualify if you...
- ASA Physical Status IV or above
- Cognitive impairment or psychiatric conditions that may limit comprehension or communication
- Non-literate patients or those unable to understand English, Chinese, Malay, or Tamil
- Emergency surgery cases
- Prior participation in the study (to prevent bias)
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
1
2
3
Your Study Journey
Screening
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Treatment
Duration - Single clinic visit
Participants receive anaesthesia risk counselling either through the PEAR chatbot before their face-to-face consultation with an anaesthetist or via the standard face-to-face verbal consent process.
1 visit (in-person)
Follow-up
Duration - Same day as treatment
Participants complete questionnaires and assessments immediately after the consent process to evaluate understanding, satisfaction, and anxiety.
1 visit (in-person, immediately post-consent)
Trial Site Locations
Total: 2 locations
1
Singapore General Hospital
Singapore, Singapore, Singapore, 249094
Actively Recruiting
2
Singapore General Hospital
Singapore, Singapore, Singapore, 751126
Not Yet Recruiting
Loading map...
Research Team
Y
Yuhe Ke, MMED (ANES)
How is the study designed?
Study Type
INTERVENTIONAL
Masking
SINGLE
Allocation
RANDOMIZED
Model
PARALLEL
Primary Purpose
OTHER
Number of Arms
2
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here