2026-10-10T09:11:24Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33999616 2026-09-25T17:44:37Z category_7 category_734 category_64 category_106 portal_5 item_type_3 month_year_09_2026

<p>Inter-rater agreement metrics across evaluated rating domains.</p> Yuntao Wang (2871704) Mariluz De Ornelas (25111495) Matthew T. Studenski (25111498) Elizabeth Bossart (25111501) Siamak P. Nejad-Davarani (25111504) Yunze Yang (1423816) Medicine Biological Sciences not elsewhere classified Cancer Science Policy statistically significant differences standardized prompt based prompted four state objective causal extraction certified medical physicists advance patient safety accurate analyses aligned observed among models large language models suggested actions using generate root causes large language model div >< p subjective ratings (< quality improvement efforts aapm rca guidelines 5 pro exhibited models exhibited 5 pro subjective ratings generate relevant subjective assessments “ background solution ), reasoning capabilities radiation oncology potential utility p </ overall performance model outputs lessons learned ils cases ils ). grok 3 gemini 2 five board evaluated using assistive tools adjudicated ppv 61 %. 05 ). <p>Inter-rater agreement metrics across evaluated rating domains.</p> 2026-09-25T17:44:21Z Dataset Dataset 10.1371/journal.pdig.0001740.t005 https://figshare.com/articles/dataset/_p_Inter-rater_agreement_metrics_across_evaluated_rating_domains_p_/33999616 CC BY 4.0