{"id":"W4396600570","doi":"10.1007/s11604-024-01608-1","title":"Data set terminology of deep learning in medicine: a historical review and recommendation","year":2024,"lang":"en","type":"review","venue":"Japanese Journal of Radiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Terminology; CLARITY; Generalizability theory; Computer science; Data science; Set (abstract data type); Artificial intelligence; Context (archaeology); Field (mathematics); Natural language processing; Psychology; Linguistics; Mathematics","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":[0.002095792,0.0001539357,0.002226521,0.0005031404,0.00001869359,0.000001676423,0.0001873751,0.0002371692,0.0001182917],"category_scores_gemma":[0.002697058,0.00009662769,0.00009384323,0.0003359728,0.0001001868,0.00007467924,0.00005674051,0.0009477898,0.000007513715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003296862,"about_ca_system_score_gemma":0.0002715148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001173168,"about_ca_topic_score_gemma":0.00002541221,"domain_scores_codex":[0.9972413,0.0005359246,0.001765236,0.0002183028,0.00008612461,0.00015318],"domain_scores_gemma":[0.9978997,0.0007437764,0.0008799983,0.0002309923,0.0001461369,0.00009936722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001895676,0.00002288291,0.0002409079,0.02549388,0.00006853283,0.00005731601,0.0007105371,1.070554e-7,0.000001902784,0.00000854615,0.004111146,0.9692653],"study_design_scores_gemma":[0.00005100595,0.000855824,0.00003783878,0.01870672,0.001988125,0.02553064,0.0003742141,0.0000344059,1.622863e-7,0.00008248322,0.9522626,0.00007597793],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004598549,0.9926624,0.00002128534,0.005920676,0.0006172478,0.0002613716,0.000001864356,0.000005136255,0.00005018091],"genre_scores_gemma":[0.0006902964,0.9982961,0.000150677,0.0002387821,0.0004534319,0.0000074605,0.0001015704,0.00001361957,0.00004810841],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9691893,"threshold_uncertainty_score":0.4117728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3895231184718287,"score_gpt":0.5197558236362534,"score_spread":0.1302327051644247,"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."}}