{"id":"W3092461455","doi":"10.1016/j.nic.2020.08.004","title":"Machine Learning Algorithm Validation","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Victoria Hospital; Jewish General Hospital; McGill University; Royal Victoria Regional Health Centre; University of Saskatchewan; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec","keywords":"Software deployment; Workflow; Domain (mathematical analysis); Model validation; Medicine; Machine learning; Health care; Artificial intelligence; Computer science; Medical physics; Algorithm; Data science; Software engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001838987,0.0003149942,0.001657524,0.0002157416,0.0000909251,0.00001969858,0.0001916239,0.0001085802,0.00005920148],"category_scores_gemma":[0.001491512,0.0002914174,0.0004935593,0.0007720519,0.0001218322,0.00006875583,0.00007149279,0.00130939,0.0002575034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006104761,"about_ca_system_score_gemma":0.000786083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001656196,"about_ca_topic_score_gemma":0.000001691581,"domain_scores_codex":[0.9972213,0.0002387045,0.001418268,0.0005256374,0.0003283973,0.0002676868],"domain_scores_gemma":[0.9972696,0.0007547819,0.001123845,0.0003847729,0.0002395586,0.0002274177],"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":[0.000007503801,0.00006874249,0.001831287,0.004131053,0.00004338616,0.00002581691,0.00009683947,0.000005410348,3.407148e-8,6.873825e-7,0.0001787214,0.9936105],"study_design_scores_gemma":[0.00002192426,0.0003682603,0.00003783549,0.001782886,0.0006810277,0.00004145419,0.00001977626,0.002540182,0.000001138032,0.000009871126,0.9943166,0.0001790751],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002226661,0.9960171,0.001570137,0.0005911962,0.0007375126,0.0006417471,0.00005479692,0.0001180553,0.0002471801],"genre_scores_gemma":[0.0000544773,0.9941974,0.003319818,0.0005159258,0.0006083575,0.00002342726,0.001080398,0.00008251578,0.0001177203],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9941378,"threshold_uncertainty_score":0.9999538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2090802705330677,"score_gpt":0.4713114398952047,"score_spread":0.262231169362137,"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."}}