{"id":"W4411354886","doi":"10.1177/11206721251350809","title":"Artificial intelligence versus ophthalmology experts: Comparative analysis of responses to blepharitis patient queries","year":2025,"lang":"en","type":"article","venue":"European Journal of Ophthalmology","topic":"Retinal and Optic Conditions","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Blepharitis; Correctness; Likert scale; Context (archaeology); Medicine; Test (biology); Computer science; Psychology; Dermatology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005149156,0.0001617603,0.0008097241,0.001108327,0.00007481397,0.00001289101,0.0002209385,0.00004153926,0.00127129],"category_scores_gemma":[0.0007834528,0.000136804,0.0003172414,0.001113064,0.0003053755,0.0000546232,0.0001106999,0.0002199297,0.00002193103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005663297,"about_ca_system_score_gemma":0.0001568663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001359892,"about_ca_topic_score_gemma":8.262302e-7,"domain_scores_codex":[0.9975789,0.0007399005,0.001055426,0.0002110542,0.0001977123,0.0002169685],"domain_scores_gemma":[0.9979518,0.0006778999,0.0003830291,0.0002564958,0.0005749102,0.0001558864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"case_report","study_design_gemma":"observational","study_design_scores_codex":[0.1963563,0.008763861,0.1801838,0.0004078023,0.0404267,0.3125544,0.04458597,0.00792653,0.09752794,0.04652598,0.009601191,0.05513954],"study_design_scores_gemma":[0.002147855,0.04655284,0.8040335,0.0008403415,0.007277179,0.06877168,0.02304826,0.000315904,0.0395784,0.001602566,0.00505729,0.0007742504],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578954,0.0004038031,0.001018859,0.001207549,0.0006434687,0.0001360649,0.00002423738,0.000005814727,0.03866478],"genre_scores_gemma":[0.9964174,0.00001271976,0.002819658,0.00008680558,0.00006507542,0.000003219347,0.000008563419,0.000008261059,0.0005783236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6238496,"threshold_uncertainty_score":0.9996417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1033451015112932,"score_gpt":0.3939042094004439,"score_spread":0.2905591078891507,"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."}}