{"id":"W2033143990","doi":"10.1136/bjo.2006.112680","title":"Sensitivity and reliability of objective image analysis compared to subjective grading of bulbar hyperaemia","year":2007,"lang":"en","type":"article","venue":"British Journal of Ophthalmology","topic":"Ocular Surface and Contact Lens","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperaemia; Medicine; Grading (engineering); Gold standard (test); Ophthalmology; Radiology; Blood flow","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":[],"consensus_categories":[],"category_scores_codex":[0.001712379,0.0001160597,0.001039836,0.0003352278,0.00004024654,0.000006997364,0.00005937091,0.000110192,0.00004644895],"category_scores_gemma":[0.0006890477,0.0001263962,0.0002974497,0.0004800511,0.0001872048,0.000102166,0.00004559359,0.0003102252,7.435306e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008629941,"about_ca_system_score_gemma":0.00009491709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001312861,"about_ca_topic_score_gemma":0.00006760396,"domain_scores_codex":[0.9984466,0.0002173659,0.0006602629,0.0001990744,0.0002509294,0.0002257193],"domain_scores_gemma":[0.9979222,0.0004052788,0.0004122337,0.0001634029,0.0009086166,0.0001882942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001069615,0.000333176,0.9058338,0.00006805763,0.0007570874,0.01213759,0.0004360843,0.00005310463,0.07816704,0.000007819928,0.000007825631,0.001128826],"study_design_scores_gemma":[0.0009442104,0.0007365629,0.9195622,0.0001302462,0.0007249246,0.03129826,0.0007692008,0.00002718516,0.04564283,0.00007321341,0.000003805032,0.0000874125],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971191,0.0004229581,0.001167706,0.00006744549,0.00007978653,0.0001642904,0.00002622955,0.000003450241,0.0009490728],"genre_scores_gemma":[0.9955015,0.00002942859,0.00436248,0.00002421539,0.00004453461,4.257265e-7,0.000002591343,0.00001069313,0.00002412186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0325242,"threshold_uncertainty_score":0.5154287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01176677048024281,"score_gpt":0.2902295658282831,"score_spread":0.2784627953480402,"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."}}