{"schemaVersion":"1.0","generatedFrom":"https://brightaifuture.com/discoveries/preop-llm","record":{"id":"preop-llm","headline":"Easing the hour before surgery.","canonicalUrl":"https://brightaifuture.com/discoveries/preop-llm","datePublished":"2026-09-27","dateModified":null,"sourcePublicationDate":"2026-09-26","author":null,"publisher":{"name":"Bright AI Future","url":"https://brightaifuture.com/"},"topics":[],"summary":"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.","evidenceState":"Demonstrated","keyFacts":[{"label":"AI’s role","value":"A locally deployed large language model drafted personalized answers to each patient’s questions before the in-person conversation."},{"label":"Documented result","value":"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."},{"label":"Important limitation","value":"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."}],"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."],"evidenceLinks":[{"title":"LLM-assisted preoperative communication reduces patient anxiety and physician workload in prostate cancer: a prospective randomized phase II trial · npj Digital Medicine","url":"https://www.nature.com/articles/s41746-026-03309-7","type":"paper"}],"evidencePackUrl":"https://brightaifuture.com/evidence-pack/preop-llm","embedUrl":"https://brightaifuture.com/embed/story/preop-llm","attribution":{"credit":"Bright AI Future","requirements":["Link to the canonical Bright record.","Keep material limitations with the claim they qualify.","Link to the original evidence when repeating a substantive claim.","Do not describe a source check or organization-reported result as independent verification."],"sourceRights":"Linked source material, quotations, trademarks and media remain subject to their owners’ terms. No reuse right is granted for third-party media."}},"claim":{"humanProblem":"The conversation before surgery carries a lot of fear, and surgeons have limited time to answer every question well.","priorConstraint":"Patients relied on a single, time-pressured face-to-face conversation to get their questions answered.","aiRole":"A locally deployed large language model drafted personalized answers to each patient’s questions before the in-person conversation.","documentedResult":"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.","whyItMayMatter":"For these patients, the tool eased a stressful moment and shortened the documented pre-operative conversation.","unresolvedQuestions":["Does the benefit hold in other procedures, centres and patient populations?"]},"evidenceAssessment":{"state":"Demonstrated","claimConfidence":"medium","reviewState":"source-checked","reviewMethod":"ai-assisted","reviewNote":"AI-assisted source check against the npj Digital Medicine article (abstract and reported results; trial NCT07082049). Full paper not reviewed by Bright; no independent clinical review is claimed.","lastSourceReview":"2026-09-27","independentVerification":"not-established-by-this-source-review"},"sources":[{"id":"source:preop-llm","title":"LLM-assisted preoperative communication reduces patient anxiety and physician workload in prostate cancer: a prospective randomized phase II trial · npj Digital Medicine","url":"https://www.nature.com/articles/s41746-026-03309-7","type":"paper"}],"revisions":[{"id":"revision:intake-20260927-preop-llm","recordedAt":"2026-09-27","summary":"Added to Bright from the 27 Sep 2026 intake as a bounded, source-checked record.","sourceIds":["source:preop-llm"]}],"corrections":[]}