{"id":"W3196529262","doi":"10.1055/s-0041-1735184","title":"Systematic Review of Approaches to Preserve Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine","year":2021,"lang":"en","type":"review","venue":"Applied Clinical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Machine learning; Benchmark (surveying); Computer science; Artificial intelligence; Calibration; Feature (linguistics); Paradigm shift; Baseline (sea); Data mining; Statistics; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02058394,0.0003544915,0.005624537,0.0002381035,0.00003424429,0.00001065818,0.0008293411,0.0004663201,0.00004711987],"category_scores_gemma":[0.01371085,0.0002052886,0.0003788755,0.001271416,0.0003102594,0.000104475,0.0002408793,0.002074817,0.00004110564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005642954,"about_ca_system_score_gemma":0.0007800556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001551931,"about_ca_topic_score_gemma":0.00008486565,"domain_scores_codex":[0.9841682,0.00120341,0.01323674,0.0003009073,0.0007563417,0.0003344073],"domain_scores_gemma":[0.9868481,0.008365369,0.003080002,0.001400919,0.000124937,0.0001806439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002383822,0.0002955543,0.001558947,0.9040569,0.00007848521,0.00000267467,0.00128961,0.000006975064,1.087863e-9,0.00030173,0.0007856474,0.09159962],"study_design_scores_gemma":[0.0001317939,0.0006182647,0.0001239603,0.9183151,0.0012344,0.0000188547,0.001851591,0.0006244866,3.485177e-7,0.00003517506,0.07682901,0.0002170771],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002130257,0.9919066,0.00008389622,0.0005872389,0.0001986197,0.006234808,0.00007994686,0.000009805237,0.0006860545],"genre_scores_gemma":[0.002087662,0.9927343,0.0005914685,0.0009917039,0.000167474,0.0004646113,0.002927123,0.00002210393,0.00001362839],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.09138254,"threshold_uncertainty_score":0.9945971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6097023893970032,"score_gpt":0.5421238976580322,"score_spread":0.06757849173897101,"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."}}