{"id":"W6920952998","doi":"10.6084/m9.figshare.20308078.v1","title":"Additional file 1 of Protocol for a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence for grading of ophthalmology imaging modalities","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Queen's University; University of Toronto","funders":"","keywords":"Protocol (science); Diagnostic accuracy; Grading (engineering); Medical imaging; Modalities; Neuro-ophthalmology","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001888885,0.0000876891,0.001267804,0.0001432938,0.00005122998,0.000003184207,0.0001414443,0.00001169469,0.6777293],"category_scores_gemma":[0.02546445,0.00005681938,0.0009194332,0.0004143393,0.0000332747,0.00002998614,0.00007561629,0.00005205097,5.435152e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001168759,"about_ca_system_score_gemma":0.0000693963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008528822,"about_ca_topic_score_gemma":3.859996e-7,"domain_scores_codex":[0.9987231,0.0001184347,0.0007316283,0.0001361302,0.000207105,0.0000836013],"domain_scores_gemma":[0.9893295,0.009038865,0.001019671,0.000236142,0.000356695,0.00001915575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.00004390451,0.0001788686,0.00001258028,0.5427439,0.0213415,0.000003302529,0.0001656586,0.0001729498,0.00003355814,0.00006955755,0.4351827,0.00005149667],"study_design_scores_gemma":[0.0004186789,0.0007861101,0.0003285866,0.1569655,0.7709901,0.0003278342,0.002552898,0.05430345,0.005985436,0.00246856,0.004374144,0.0004986202],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"protocol","genre_scores_codex":[0.000005879147,0.0004682537,0.00001731038,0.0001512847,0.000001266931,0.02911893,0.9701998,0.000002505682,0.00003481823],"genre_scores_gemma":[0.0210187,7.416174e-7,0.0008040089,0.00008375834,0.00001024394,0.7952352,0.1825805,0.00001380682,0.0002529986],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.7876192,"threshold_uncertainty_score":0.9827445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1690093788756687,"score_gpt":0.3996694095197112,"score_spread":0.2306600306440426,"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."}}