PEAR: an AI chatbot to explain anaesthesia risks and consent.

Evaluating the Effectiveness of Large Language Models in Anaesthesia and Procedural Consent: A Comparative Analysis With Traditional Patient Consent Methods

Not applicable Interventional Singapore General Hospital · NCT06949462

This trial will test whether PEAR, a multilingual AI chatbot, helps adults having elective surgery understand anaesthesia risks, feel more satisfied, and have less preoperative anxiety compared with the usual face-to-face consent conversation.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment120 (estimated)
Ages21 Years to 99 Years
SexAll
SponsorSingapore General Hospital Academic / other
Locations2 sites (Singapore, Singapore and 1 other locations)
Trial IDNCT06949462 on ClinicalTrials.gov

What this trial studies

Adults scheduled for elective surgery at SingHealth hospitals are randomly assigned to use PEAR before meeting their anaesthetist or to receive the standard verbal consent process. PEAR is a conversational, multilingual interface that presents institution-aligned anaesthesia risk information and allows interactive questions. After the consent process, patients complete a short quiz to measure understanding, a satisfaction survey, and an anxiety scale while clinicians record time spent and perceived workload. All participants still meet the anaesthetist in person, and data are anonymised and stored securely for comparison between groups.

Who should consider this trial

Good fit: Adults aged 21 and over undergoing elective surgery with ASA physical status I–III who can read and communicate in English, Mandarin, Malay, or Tamil and are able to provide informed consent and use the chatbot are eligible.

Not a fit: Patients with ASA IV or higher, significant cognitive or psychiatric impairment, emergency surgery, non‑literacy, or inability to use the supported languages are unlikely to benefit from PEAR in this study.

Why it matters

Potential benefit: If successful, PEAR could improve patient understanding, increase satisfaction, reduce preoperative anxiety, and make consent discussions more efficient.

How similar studies have performed: Previous studies of digital and multimedia consent tools have shown improved comprehension and satisfaction in some settings, but the use of large language model–driven, multilingual chatbots for anaesthesia consent is relatively new and less tested.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

\- 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)

Exclusion Criteria:

* 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)

Where this trial is running

Singapore, Singapore and 1 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Consent FormsAnesthesiaArtificial IntelligenceAnaesthesiaInformed ConsentLarge Language Model
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.