{"id":"W1875130055","doi":"10.4137/bii.s2222","title":"Avoiding Pitfalls in the Statistical Analysis of Heterogeneous Tumors","year":2009,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University Health Network","funders":"National Cancer Institute","keywords":"Context (archaeology); Computer science; Feature (linguistics); Focus (optics); Sample (material); Data science; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0006818241,0.0001105535,0.0002593249,0.0005783273,0.00009806744,0.0000743689,0.0008543599,0.00008083026,0.00001143532],"category_scores_gemma":[0.0001517781,0.00007164548,0.00007678864,0.00223931,0.000124581,0.0003049736,0.00007408918,0.0002786831,0.00001180868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007655789,"about_ca_system_score_gemma":0.00006409312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001863214,"about_ca_topic_score_gemma":0.00001435138,"domain_scores_codex":[0.9980946,0.0001347011,0.0007253651,0.000112634,0.0007126206,0.0002201193],"domain_scores_gemma":[0.9988458,0.0004171094,0.0001869334,0.0004166981,0.00004590627,0.00008753919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005518886,0.0011036,0.0003588081,0.0001785625,0.0007094785,0.0002928051,0.121902,0.007545438,0.0009737615,0.4946419,0.002592305,0.3696462],"study_design_scores_gemma":[0.0003757749,0.0004782935,0.009451386,0.00005393505,0.00009745252,0.00004974557,0.0005225617,0.9687493,0.001183155,0.01473496,0.004051861,0.0002515797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1416929,0.00005986808,0.8565897,0.0002586626,0.0001434248,0.000124806,0.000005163578,0.00004510215,0.001080364],"genre_scores_gemma":[0.9835453,0.00001997237,0.01553268,0.0008551732,0.00002739174,0.000004686636,0.00001024997,0.000001913695,0.000002622848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9612039,"threshold_uncertainty_score":0.2921618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01683642819409829,"score_gpt":0.2720042407984965,"score_spread":0.2551678126043982,"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."}}