{"id":"W4392283037","doi":"10.1038/s41467-024-46142-w","title":"Empirical data drift detection experiments on real-world medical imaging data","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; York University; Trillium Health Centre; University of Toronto; Vector Institute","funders":"","keywords":"Computer science; Concept drift; Proxy (statistics); Data mining; Tracking (education); Artificial intelligence; Data stream mining; Machine learning","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008919485,0.0001787554,0.0002237597,0.0003485473,0.0002779561,0.0001153405,0.003452562,0.0002426499,0.0001614396],"category_scores_gemma":[0.002266194,0.000160335,0.00005028625,0.0008627761,0.000195978,0.0003207454,0.003473116,0.002407816,0.000169792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000276228,"about_ca_system_score_gemma":0.0005354022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003066618,"about_ca_topic_score_gemma":0.002541187,"domain_scores_codex":[0.9977891,0.0002115306,0.0003404897,0.0007073619,0.000720715,0.0002308162],"domain_scores_gemma":[0.9862998,0.001724293,0.00005105031,0.01162016,0.00008612051,0.0002185582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004027645,0.0007341363,0.005797044,0.00007340322,0.0001545808,0.00007719635,0.0002949797,0.000001064244,0.0009519373,0.001162766,0.9198705,0.07084212],"study_design_scores_gemma":[0.0003167392,0.00002083958,0.008408053,0.0005749441,0.000144369,0.00003533094,0.00004638197,0.06785417,0.0003636093,0.00004260755,0.9220548,0.0001381355],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.003424196,0.03066434,0.0009928681,0.9495451,0.002175523,0.0008874122,0.0004712086,0.001533699,0.01030569],"genre_scores_gemma":[0.9598406,0.002302905,0.002985678,0.03011549,0.0004542612,0.00004334711,0.003933139,0.00005865233,0.000265946],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9564164,"threshold_uncertainty_score":0.9998937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1590621346926188,"score_gpt":0.5059469993638447,"score_spread":0.3468848646712259,"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."}}