{"id":"W2995236054","doi":"10.1167/tvst.8.6.40","title":"Remote Tool-Based Adjudication for Grading Diabetic Retinopathy","year":2019,"lang":"en","type":"article","venue":"Translational Vision Science & Technology","topic":"Retinal Diseases and Treatments","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adjudication; Rubric; Cohen's kappa; Grading (engineering); Kappa; Medicine; Inter-rater reliability; Computer science; Artificial intelligence; Ophthalmology; Medical physics; Machine learning; Statistics; Psychology; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1086669,0.001433398,0.001342966,0.006728854,0.001488336,0.002689498,0.003966375,0.001864368,0.006759707],"category_scores_gemma":[0.1668076,0.0006845777,0.001921231,0.00243108,0.001701674,0.002674868,0.004620068,0.002900018,0.002973337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00192047,"about_ca_system_score_gemma":0.003918825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00181125,"about_ca_topic_score_gemma":0.004315096,"domain_scores_codex":[0.8394148,0.1113663,0.01392671,0.008976922,0.02494457,0.001370747],"domain_scores_gemma":[0.783904,0.09000655,0.03081,0.03812346,0.05383936,0.003316632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002169609,0.001155294,0.05018786,0.003118325,0.000446064,0.0002592509,0.003851476,0.003928802,0.02068972,0.003369991,0.011999,0.8988246],"study_design_scores_gemma":[0.005310997,0.0242814,0.5228519,0.01022966,0.002396748,0.01106769,0.006620973,0.1481961,0.09025127,0.02128722,0.1546354,0.002870716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1069335,0.002647921,0.8500603,0.001054614,0.0007994369,0.01510444,0.0009450528,0.005178035,0.01727674],"genre_scores_gemma":[0.2309219,0.0005613972,0.7562553,0.0006479209,0.0004430851,0.007399483,0.0008349746,0.0006040405,0.002331801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1086669,"threshold_uncertainty_score":0.5746926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01478552654088522,"score_gpt":0.3340873531479912,"score_spread":0.3193018266071059,"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."}}