{"id":"W2100420476","doi":"10.1093/biostatistics/kxr010","title":"Classifying tissue samples from measurements on cells with within-class tissue sample heterogeneity","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute","keywords":"Latent class model; Computer science; Macro; Replicate; Class (philosophy); Heuristic; Object (grammar); Focus (optics); Sample (material); Cluster analysis; Statistics; Mixture model; Artificial intelligence; Pattern recognition (psychology); Mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002034209,0.000277906,0.0002379544,0.00009144655,0.0002602503,0.0001851243,0.0006756952,0.000104542,0.00006653022],"category_scores_gemma":[0.0000854205,0.0002478502,0.00002276726,0.0002613049,0.00012615,0.0002252345,0.000140841,0.0001834184,0.0001577124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002092685,"about_ca_system_score_gemma":0.0001316619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002063025,"about_ca_topic_score_gemma":0.00134946,"domain_scores_codex":[0.9979126,0.0001170324,0.0003217842,0.0006548241,0.0006293426,0.0003643632],"domain_scores_gemma":[0.9983515,0.0002546466,0.0002543472,0.0008150851,0.0001559056,0.0001685384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00104196,0.001560785,0.04082082,0.0003602616,0.001063859,0.0004471067,0.02170815,0.002001368,0.3129566,0.05703414,0.01839606,0.5426089],"study_design_scores_gemma":[0.0005980406,0.001042986,0.009889972,0.00008602309,0.00004410249,0.000008078038,0.00004868434,0.003524546,0.9707023,0.005034875,0.008464078,0.0005563052],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02234086,0.00004372763,0.9748521,0.00005192388,0.001260959,0.0002822722,0.0003451452,0.0002211256,0.0006019147],"genre_scores_gemma":[0.5214664,0.000006102833,0.4781399,0.000218862,0.00008708599,0.00001555783,0.00001655744,0.0000246409,0.00002487042],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6577457,"threshold_uncertainty_score":0.9999974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1329927357574424,"score_gpt":0.2858008119355312,"score_spread":0.1528080761780888,"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."}}