{"id":"W4310209114","doi":"10.3389/fneph.2022.1007002","title":"Machine learning in renal pathology","year":2022,"lang":"en","type":"article","venue":"Frontiers in Nephrology","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Toronto General Hospital; University of Toronto; University Health Network; Toronto Metropolitan University","funders":"Canadian Institutes of Health Research; Government of Canada; University of Toronto; Alport Syndrome Foundation; Nephcure Foundation","keywords":"Artificial intelligence; Renal pathology; Interpretability; Linear discriminant analysis; Glomerular basement membrane; Pathology; Digital pathology; Computer science; Deep learning; Classifier (UML); Nephropathy; Medicine; Machine learning; Pattern recognition (psychology); Kidney; Glomerulonephritis; Diabetes mellitus; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002482505,0.0005380621,0.0008863862,0.001184536,0.000275107,0.002073172,0.0008441452,0.001735035,0.004421992],"category_scores_gemma":[0.005643019,0.0002224231,0.0005028232,0.001505202,0.001450156,0.001513306,0.001060295,0.002599435,0.001568962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009628756,"about_ca_system_score_gemma":0.001068916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001903819,"about_ca_topic_score_gemma":0.001020355,"domain_scores_codex":[0.9987428,0.0005491058,0.00006877499,0.0002377178,0.0003403115,0.00006140354],"domain_scores_gemma":[0.9964134,0.002542696,0.0002277418,0.000206348,0.0005146925,0.00009522632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007164478,0.0001026347,0.006983033,0.001146266,0.0001974566,0.0002253256,0.0001435766,0.05951511,0.0006946325,0.1455991,0.06269064,0.7226306],"study_design_scores_gemma":[0.00004471535,0.0001400913,0.007546034,0.001061801,0.00006895913,0.0005601119,0.0001370753,0.3301701,0.001124764,0.5180864,0.1409776,0.00008247906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02587409,0.2728905,0.5694225,0.06977969,0.005938981,0.0002538314,0.001908593,0.001494676,0.05243717],"genre_scores_gemma":[0.6338509,0.1459779,0.1656846,0.007384763,0.01152521,0.0006159511,0.002861838,0.0002246372,0.0318741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004421992,"threshold_uncertainty_score":0.01479298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006872204105003736,"score_gpt":0.2101702649297685,"score_spread":0.2032980608247647,"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."}}