{"id":"W4313585924","doi":"10.3389/fopht.2022.1057896","title":"Reverse translation of artificial intelligence in glaucoma: Connecting basic science with clinical applications","year":2023,"lang":"en","type":"article","venue":"Frontiers in Ophthalmology","topic":"Glaucoma and retinal disorders","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Center for Advancing Translational Sciences; National Eye Institute; Moorfields Eye Charity; National Institutes of Health; Singapore-MIT Alliance for Research and Technology Centre; Research to Prevent Blindness; National Research Foundation; BrightFocus Foundation; National Medical Research Council; National Research Foundation Singapore","keywords":"Generalizability theory; Translational research; Computer science; Translational science; Artificial intelligence; Data science; Basic research; Glaucoma; Identification (biology); Big data; Engineering ethics; Medicine; Psychology; Pathology; Engineering; Biology; Ophthalmology; Data mining","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":[0.0009280623,0.00008839376,0.0003189167,0.0005631174,0.00004898405,0.000003675355,0.0001441377,0.0001098792,0.00002712783],"category_scores_gemma":[0.0001922119,0.00007849027,0.00004574563,0.001899752,0.0006741244,0.00005853505,0.00002370996,0.0002568557,0.00001780683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000425208,"about_ca_system_score_gemma":0.0001635295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005798251,"about_ca_topic_score_gemma":0.00001153649,"domain_scores_codex":[0.9986789,0.0000779601,0.0004844136,0.0003253396,0.0001636056,0.0002697457],"domain_scores_gemma":[0.9994321,0.0001453544,0.00009743644,0.0002039979,0.00006101829,0.00006008193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004168906,0.0002000989,0.9634959,0.00006290583,0.00001199363,0.00018642,0.0003976357,0.00004517511,0.0004870727,0.0005335213,0.00005185905,0.03411056],"study_design_scores_gemma":[0.0007196506,0.0007326878,0.9661906,0.0001418197,0.00003816284,0.000463222,0.005394602,0.01945275,0.0005307738,0.005897535,0.0002669089,0.0001712685],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847924,0.0001143708,0.01188031,0.0005463445,0.000284845,0.0005046407,0.000001974443,0.00002296008,0.001852212],"genre_scores_gemma":[0.9851156,0.00003067994,0.0147112,0.0000241564,0.00002781032,0.00003740478,0.00001109597,0.00001028347,0.00003174303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03393929,"threshold_uncertainty_score":0.320074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04700723337720592,"score_gpt":0.3590602059301125,"score_spread":0.3120529725529065,"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."}}