Easing the hour before surgery.
A randomized trial found that giving prostate-cancer patients AI-drafted, personalized answers before they met their surgeon lowered anxiety and reduced the surgeon’s workload.
Original sources ↓ · Revision history ↓
Demonstrated · source published 2026-09-26
The human problem
The conversation before surgery carries a lot of fear, and surgeons have limited time to answer every question well.
The prior constraint
Patients relied on a single, time-pressured face-to-face conversation to get their questions answered.
AI’s actual role
A locally deployed large language model drafted personalized answers to each patient’s questions before the in-person conversation.
The documented result
Among 268 randomized patients, the AI-assisted group reported lower anxiety (GAD-7 3.2 vs 5.7) and lower physician workload (NASA-TLX 39.9 vs 56.8), with shorter conversations (11.3 vs 19.9 minutes); all differences were statistically significant.
Why it may matter
For these patients, the tool eased a stressful moment and shortened the documented pre-operative conversation.
Limitations
A single-centre trial of 268 patients in one cancer type, randomized by room. Bright reviewed the abstract of the peer-reviewed early-access paper; the specific model is not named there, and independent replication is unknown.
Unresolved questions
Does the benefit hold in other procedures, centres and patient populations?
Source history & evidence assessment
- Maturity
- Demonstrated
- Claim confidence
- medium
- Event date
- Not recorded
- Source published
- 2026-09-26
- Captured
- 2026-09-27
- Last source review
- 2026-09-27
- Editorial method
- AI-assisted source review
- Place / relevance
- Shanghai, China · institution-location
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Original sources
Institutions: Fudan University Shanghai Cancer Center
Explore the underlying question
Related developments
Editorial connections between distinct settings and results; these links do not imply replication.
Revision & correction history
2026-09-27 · Added to Bright from the 27 Sep 2026 intake as a bounded, source-checked record.
No corrections recorded.