{"id":"W4399480892","doi":"10.1200/jco.2024.42.16_suppl.7565","title":"Automated myeloma cell selection using machine learning and artificial intelligence.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; Jewish General Hospital; Ontario Genomics","funders":"","keywords":"Medicine; Artificial intelligence; Selection (genetic algorithm); Multiple myeloma; Machine learning; Computer science; Internal medicine","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":[0.001620872,0.00009904409,0.0004214615,0.0001924329,0.00005988513,0.0002762332,0.0002540147,0.0001170278,0.00001499873],"category_scores_gemma":[0.001085296,0.0000790673,0.0001848459,0.0003519938,0.0001121366,0.000758219,0.0001391356,0.0006164117,0.00002169662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005894787,"about_ca_system_score_gemma":0.0007371496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000106439,"about_ca_topic_score_gemma":0.000005609415,"domain_scores_codex":[0.9979242,0.000266058,0.001202837,0.0002084445,0.0002203768,0.0001780501],"domain_scores_gemma":[0.9979376,0.001139318,0.0004738468,0.0000660169,0.0001648421,0.0002183536],"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":[0.0001044488,0.0005991696,0.005136986,0.00004440855,0.0001089259,0.0007110562,0.0001211648,0.00136523,0.0011567,0.004915732,0.0004712191,0.985265],"study_design_scores_gemma":[0.0001455128,0.00189218,0.001176185,0.00006032725,0.00007406279,0.0005991903,0.00002343802,0.9726443,0.001064074,0.008846397,0.0133671,0.0001072414],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7928223,0.003381296,0.1933535,0.002989753,0.004235278,0.0001016977,0.000001928821,0.0005024648,0.002611844],"genre_scores_gemma":[0.9541598,0.00008911842,0.04507251,0.0001888659,0.0004099269,3.23979e-7,3.637433e-7,0.000009775135,0.00006932013],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9851577,"threshold_uncertainty_score":0.3224271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1102276026324348,"score_gpt":0.4516102019391705,"score_spread":0.3413825993067356,"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."}}