{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004412492,0.001188844,0.002782668,0.007370475,0.0004013639,0.002941232,0.002830524,0.001883323,0.00291239],"category_scores_gemma":[0.01127199,0.00064991,0.001906399,0.009071726,0.002484875,0.003831196,0.002067014,0.004287626,0.001147188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00210077,"about_ca_system_score_gemma":0.005322536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004605133,"about_ca_topic_score_gemma":0.005234431,"domain_scores_codex":[0.9985661,0.0003509286,0.000440543,0.0002274641,0.0003529998,0.00006198498],"domain_scores_gemma":[0.9921179,0.005626259,0.0005794502,0.0002190369,0.001290969,0.0001664276],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002721301,0.0001418368,0.001424549,0.05815343,0.0007563914,0.0001773081,0.0002310964,0.001838277,0.0006391756,0.02774537,0.05119555,0.8574248],"study_design_scores_gemma":[0.000125613,0.0003079503,0.00321537,0.04650731,0.001761868,0.001621144,0.0003238274,0.002473116,0.001275102,0.02875397,0.9134492,0.0001855288],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001658194,0.9957599,0.001448793,0.001507644,0.0004787461,0.00001341163,0.0001085617,0.000009537788,0.0005076704],"genre_scores_gemma":[0.002244323,0.9916282,0.002928274,0.001965304,0.0007659061,0.00004064901,0.0001852589,0.00001009698,0.0002320082],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9955875,"threshold_uncertainty_score":0.02333575,"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."}}