{"id":"W4392239041","doi":"10.1002/cyto.b.22168","title":"<scp>MAGIC‐DR</scp>: An interpretable machine‐learning guided approach for acute myeloid leukemia measurable residual disease analysis","year":2024,"lang":"en","type":"article","venue":"Cytometry Part B Clinical Cytometry","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Terry Fox Research Institute; Vancouver General Hospital; University of British Columbia","funders":"Faculty of Medicine, University of British Columbia","keywords":"Myeloid leukemia; Residual; Minimal residual disease; Cytometry; Myeloid; Disease; MAGIC (telescope); Computational biology; Artificial intelligence; Infectious disease (medical specialty); Computer science; Leukemia; Medicine; Immunology; Flow cytometry; Biology; Internal medicine; Physics; Algorithm","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":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004623,0.0009523181,0.001714647,0.003318031,0.000491772,0.003992524,0.003716737,0.0003753811,0.00005513093],"category_scores_gemma":[0.00879581,0.0008904776,0.001960452,0.01333157,0.0004841282,0.004521031,0.001471357,0.00131819,0.0003712901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003929514,"about_ca_system_score_gemma":0.0009581528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004020888,"about_ca_topic_score_gemma":0.000002835045,"domain_scores_codex":[0.9904152,0.0007179329,0.002195128,0.003229568,0.001684375,0.001757782],"domain_scores_gemma":[0.9900689,0.00393566,0.0004738916,0.002684338,0.0005645233,0.002272745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005272871,0.00591517,0.6884801,0.001975297,0.02582158,0.001577817,0.0006113406,0.01908079,0.0007017839,0.01020995,0.1967309,0.04836802],"study_design_scores_gemma":[0.001696142,0.0007747638,0.02210068,0.0001852085,0.005814597,0.00005569682,0.0001184189,0.9027012,0.0007040767,0.002342917,0.06245387,0.001052464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1545524,0.007772717,0.8154149,0.0003952192,0.002210837,0.001289575,0.001079039,0.004065242,0.01322009],"genre_scores_gemma":[0.933203,0.0002306295,0.05064988,0.001067793,0.0009761328,0.0002266878,0.001281994,0.0002015835,0.01216228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8836204,"threshold_uncertainty_score":0.9995535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06366587601378457,"score_gpt":0.3726095513769933,"score_spread":0.3089436753632087,"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."}}