{"id":"W4390512214","doi":"10.1016/j.artmed.2023.102751","title":"Evaluating the clinical utility of artificial intelligence assistance and its explanation on the glioma grading task","year":2024,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital; Simon Fraser University","funders":"Alliance de recherche numérique du Canada; BC Cancer Foundation; Nvidia","keywords":"Grading (engineering); Computer science; Artificial intelligence; Task (project management); Machine learning; Glioma; Medicine","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"],"consensus_categories":[],"category_scores_codex":[0.01006465,0.000307272,0.0005707822,0.0003833864,0.0003263274,0.00006973546,0.0003563986,0.0002270283,0.0004859874],"category_scores_gemma":[0.009610524,0.000179806,0.0001377034,0.001758909,0.0009875869,0.0001841419,0.00006492864,0.001137496,0.0001190183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001132434,"about_ca_system_score_gemma":0.0003503444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005288654,"about_ca_topic_score_gemma":0.0004265984,"domain_scores_codex":[0.9946946,0.0006511044,0.002457728,0.0007608427,0.0009434402,0.0004922721],"domain_scores_gemma":[0.9914464,0.007011876,0.0003071243,0.0006146764,0.0004405682,0.0001793142],"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":[0.0005509112,0.000230015,0.001083238,0.0002091674,0.00004523682,0.00003693748,0.006697707,0.0001014111,0.005477376,0.1469406,0.0003228909,0.8383045],"study_design_scores_gemma":[0.00002164472,0.002548391,0.003321768,0.002985171,0.000202778,0.00007741947,0.02727748,0.6247697,0.08565217,0.2523541,0.0004508594,0.0003384901],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.93401,0.003059289,0.01228178,0.04594389,0.002573786,0.001349671,0.000007523333,0.00007960092,0.0006944768],"genre_scores_gemma":[0.9967037,0.0007076119,0.0002409087,0.0008518017,0.001306292,0.00010195,0.00001283499,0.00002969015,0.00004515761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.837966,"threshold_uncertainty_score":0.998732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5735416713807948,"score_gpt":0.5688673115818328,"score_spread":0.004674359798962024,"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."}}