{"id":"W4392614927","doi":"10.1038/s41375-024-02210-0","title":"Redefining high risk multiple myeloma with an APOBEC/Inflammation-based classifier","year":2024,"lang":"en","type":"letter","venue":"Leukemia","topic":"Multiple Myeloma Research and Treatments","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver General Hospital; Simon Fraser University; Terry Fox Research Institute; University of British Columbia","funders":"Canadian Institutes of Health Research; National Cancer Institute; BC Cancer Foundation; University of British Columbia; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC; Leukemia and Lymphoma Society of Canada; Simon Fraser University; Cancer Prevention and Research Institute of Texas","keywords":"APOBEC; Multiple myeloma; Classifier (UML); Inflammation; Medicine; Biology; Internal medicine; Genetics; Computer science; Genome; Gene; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002326819,0.0007163819,0.0008263228,0.0005305643,0.0002370864,0.0002081195,0.0002829246,0.001054617,0.0005197524],"category_scores_gemma":[0.0002704278,0.0005152922,0.0002480925,0.0004036964,0.0001913732,0.0001397571,0.00006771534,0.003583633,0.001270037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001701635,"about_ca_system_score_gemma":0.001950291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002498828,"about_ca_topic_score_gemma":0.0004609844,"domain_scores_codex":[0.9958999,0.0002104,0.0005169767,0.001128729,0.001291831,0.0009521267],"domain_scores_gemma":[0.997328,0.0005220681,0.0002569952,0.00129278,0.0002210019,0.0003791697],"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":[0.00199734,0.00009078314,0.02852802,0.001616027,0.001766098,0.02403565,0.0002276288,0.0002141248,0.00023407,0.00003776025,0.8957528,0.04549968],"study_design_scores_gemma":[0.01182191,0.002220165,0.0324514,0.002053348,0.001144123,0.0002088399,0.00005714557,0.03335653,0.002345114,0.0002225727,0.9129964,0.001122418],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5254866,0.0008947913,0.0008968663,0.4439023,0.001385106,0.004865153,0.001710332,0.002147686,0.01871115],"genre_scores_gemma":[0.6609839,0.0001678549,0.02790137,0.2202459,0.0178562,0.001556483,0.02954623,0.001125199,0.04061683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2236564,"threshold_uncertainty_score":0.9997299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02612859339725811,"score_gpt":0.2744422811506523,"score_spread":0.2483136877533942,"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."}}