{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002884647,0.000106305,0.0001738513,0.0006255088,0.0001651291,0.00001877339,0.0001682266,0.00009151052,0.0000954772],"category_scores_gemma":[0.0001245062,0.00008880216,0.00008596236,0.001155237,0.0003383676,0.0001353514,0.00001221322,0.00008332256,0.0000962136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006183552,"about_ca_system_score_gemma":0.0002268586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002228853,"about_ca_topic_score_gemma":3.118615e-7,"domain_scores_codex":[0.9986303,0.000008110653,0.0002252356,0.000427601,0.00044676,0.0002619357],"domain_scores_gemma":[0.9992341,0.00008096777,0.00007614293,0.0003156752,0.0002167353,0.00007632058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009657753,0.0005422817,0.3794745,0.0002014792,0.00003417169,0.0000138717,0.00007683833,0.0004290382,0.2739462,0.047122,0.00007412777,0.2971197],"study_design_scores_gemma":[0.006377572,0.002411816,0.7200685,0.000387743,0.0001694177,0.0000395556,0.00004843494,0.1825072,0.0352416,0.04743231,0.004939821,0.0003759711],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9657127,0.0001600559,0.02253638,0.009651179,0.0001168014,0.0008792134,0.00001432253,0.0001358507,0.0007935424],"genre_scores_gemma":[0.9795204,0.000006085082,0.02007158,0.0002088577,0.00001281495,0.00002074153,0.00003946947,0.00001063564,0.0001094493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.340594,"threshold_uncertainty_score":0.3621247,"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."}}