Physician-Supervised ChatGPT-Assisted Versus Physician-Led Informed Consent for Reducing Preoperative Anxiety: A Randomized Controlled Trial.
Yavuz Mert Aydın, Tevfik Erdem Özarslan, Merve Sena Baytar et al.
✦ AI-curated · Sources linked
In 30 seconds
This prospective, open-label randomized controlled trial compared physician-supervised ChatGPT-assisted with conventional physician-led informed consent in adults scheduled for urologic procedures. Of 180 randomized patients, 161 were included in the analysis. Anxiety scores fell after consent in both groups, and adjusted postintervention anxiety did not differ significantly; the mean difference was 0.26 STAI-1 points (95% CI: -1.45 to 1.97), meeting the prespecified noninferiority criterion. Consent duration was 10 minutes in both groups, while postoperative quality-of-recovery scores favored physician-led consent.
Key findings
- Adjusted postintervention anxiety was similar between groups (mean difference, 0.26; 95% CI: -1.45 to 1.97), meeting the noninferiority criterion.
- STAI-1 anxiety scores decreased significantly after informed consent in both groups (p < 0.01).
- Median informed-consent duration was 10 minutes in both groups, with a significant between-group difference (p = 0.020).
- Postoperative QoR-15 scores favored the physician-led control group (p = 0.019).
Why it matters
Informed consent can be anxiety-provoking, and this trial suggests that a physician-supervised ChatGPT-assisted process can reduce preoperative anxiety comparably to physician-led consent in the studied urologic procedures. The findings support evaluating language models as adjuncts to clinician communication, while the difference in recovery scores underscores that anxiety outcomes alone do not capture all aspects of patient experience.
What to keep in mind
The trial was open-label and limited to adults undergoing specified urologic procedures; 19 randomized patients were excluded from the analysis.