{"id":"W2610180163","doi":"10.1002/cyto.b.21528","title":"A QA Program for MRD Testing Demonstrates That Systematic Education Can Reduce Discordance Among Experienced Interpreters","year":2017,"lang":"en","type":"article","venue":"Cytometry Part B Clinical Cytometry","topic":"Acute Lymphoblastic Leukemia research","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"London Health Sciences Centre","funders":"Genentech; AbbVie; National Cancer Institute; National Institutes of Health; Pfizer; Amgen; Foundation for the National Institutes of Health","keywords":"Cog; Protocol (science); Medicine; Medical physics; False positive paradox; Computer science; Pathology; Artificial intelligence","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00270906,0.0005508584,0.001628555,0.0006773462,0.0007915274,0.000657201,0.001322582,0.0004641984,0.0000404398],"category_scores_gemma":[0.05118841,0.0004454208,0.0005544436,0.001179445,0.001735311,0.0005792608,0.0004646596,0.0008528269,0.00005607376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000779901,"about_ca_system_score_gemma":0.001976232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000889654,"about_ca_topic_score_gemma":0.00001362596,"domain_scores_codex":[0.9944489,0.0002879889,0.001778207,0.001302857,0.00103471,0.001147355],"domain_scores_gemma":[0.9898087,0.004788721,0.001331603,0.002312261,0.0006924768,0.001066265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006855623,0.001473581,0.9487724,0.01136062,0.0004299453,0.00008292064,0.0003008618,0.000001375622,0.00166441,0.00004742349,0.002347853,0.032833],"study_design_scores_gemma":[0.01219699,0.007564103,0.875177,0.05046367,0.001541203,0.0007911222,0.009286125,0.02219806,0.01737291,0.0003751655,0.0007067922,0.002326914],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862487,0.0002948952,0.003511503,0.0005865651,0.001913071,0.005159909,0.00004990818,0.0003455292,0.001889964],"genre_scores_gemma":[0.9765972,0.00003566405,0.0178961,0.0003713922,0.001065273,0.00274808,0.00006643356,0.0001139435,0.001105902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07359551,"threshold_uncertainty_score":0.9997997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1480657558197203,"score_gpt":0.4737529076507508,"score_spread":0.3256871518310305,"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."}}