{"id":"W4317815057","doi":"10.1038/s41746-023-00753-7","title":"Making machine learning matter to clinicians: model actionability in medical decision-making","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Metric (unit); Computer science; Point (geometry); Medical decision making; Machine learning; Calibration; Artificial intelligence; Management science; Medicine; Engineering; Mathematics; Medical emergency","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001850151,0.0005349376,0.00233945,0.001020935,0.0001225831,0.00005228848,0.0003623883,0.0007291446,0.001135938],"category_scores_gemma":[0.01851412,0.0004014138,0.0002863001,0.001487519,0.0001697538,0.0002035918,0.0002077086,0.002003594,0.002182254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007599433,"about_ca_system_score_gemma":0.001211288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001278912,"about_ca_topic_score_gemma":0.0002025979,"domain_scores_codex":[0.994324,0.0001251828,0.002600961,0.0009532134,0.001325818,0.0006708085],"domain_scores_gemma":[0.994469,0.003784316,0.0004039786,0.0006252105,0.0002236426,0.0004938928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007394094,0.0001078684,0.001449376,0.00615261,0.00004222307,0.0001148194,0.0004833536,0.00005936939,4.800325e-8,0.00002991042,0.002016744,0.9894697],"study_design_scores_gemma":[0.0001334943,0.000526906,0.0001978666,0.2289202,0.0003377778,0.0002866757,0.0007518954,0.005949772,1.418409e-7,0.003550593,0.758774,0.000570678],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009888948,0.9687907,0.005927772,0.009084447,0.002827227,0.00311553,0.00005044758,0.0003711322,0.008843876],"genre_scores_gemma":[0.02290723,0.9684916,0.0005157046,0.003423563,0.002457393,0.0003133977,0.0003274017,0.0002123513,0.001351361],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9888991,"threshold_uncertainty_score":0.9998438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4566406973885117,"score_gpt":0.5864048797666964,"score_spread":0.1297641823781848,"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."}}