{"id":"W4392005596","doi":"10.1016/j.urology.2023.11.042","title":"Accuracy and Readability of Kidney Stone Patient Information Materials Generated by a Large Language Model Compared to Official Urologic Organizations","year":2024,"lang":"en","type":"letter","venue":"Urology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Medicine; Readability; Medical physics; Radiology; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001133544,0.0003216438,0.0007378692,0.0003320667,0.0003683282,0.00004892252,0.0002628758,0.001294107,0.001080169],"category_scores_gemma":[0.003969726,0.0002716685,0.00003734223,0.0004880573,0.00007030492,0.0007894443,0.000372181,0.00153667,0.0003754843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001818257,"about_ca_system_score_gemma":0.001267671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003812952,"about_ca_topic_score_gemma":0.00003179641,"domain_scores_codex":[0.9949217,0.001105274,0.002672939,0.0003695825,0.0002744443,0.0006560606],"domain_scores_gemma":[0.9968324,0.0004220736,0.001110206,0.0005888793,0.0007878455,0.0002585762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00015052,0.00004821381,0.0002592946,0.001728056,0.00002515103,0.000002066314,0.01450164,0.0001416035,0.0002984029,0.0001241127,0.9823883,0.0003326135],"study_design_scores_gemma":[0.0003574977,0.0001623354,0.00007926879,0.00005538324,0.00005895218,0.000002798701,0.0002872324,0.01663824,0.0002295909,0.0002331159,0.9816328,0.0002627443],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.4107811,0.0002247128,0.02836188,0.5230271,0.002242759,0.004841994,0.02922886,0.0004157614,0.0008757716],"genre_scores_gemma":[0.1044018,0.00002268823,0.0004907754,0.8772976,0.0003612646,0.0002473144,0.01681415,0.0000317969,0.000332583],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.3542705,"threshold_uncertainty_score":0.9999735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02282794518583499,"score_gpt":0.3693426068630186,"score_spread":0.3465146616771836,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}