{"id":"W4376602191","doi":"10.1186/s41512-023-00147-z","title":"Methodological concerns about “concordance-statistic for benefit” as a measure of discrimination in predicting treatment benefit","year":2023,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Concordance; Statistic; Metric (unit); Discriminative model; Counterfactual thinking; Econometrics; Computer science; Statistics; Categorical variable; Cut-point; Machine learning; Mathematics; Psychology; Medicine; Economics; Social psychology; Operations management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.219742,0.001361551,0.003553571,0.004242918,0.002124203,0.006036872,0.005751951,0.005736045,0.002720133],"category_scores_gemma":[0.5305835,0.000949783,0.002268826,0.004751378,0.01416396,0.007828893,0.006251056,0.009881945,0.0007059372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003402699,"about_ca_system_score_gemma":0.003152885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003450328,"about_ca_topic_score_gemma":0.001729645,"domain_scores_codex":[0.7970917,0.1583763,0.009865095,0.01246412,0.02087134,0.001331541],"domain_scores_gemma":[0.4175336,0.5212805,0.0174409,0.03303819,0.009713962,0.0009928897],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004803348,0.0001724393,0.02808271,0.0008317253,0.00110681,0.0002935629,0.001147821,0.01939512,0.0005495456,0.84421,0.008970644,0.09475933],"study_design_scores_gemma":[0.00007847526,0.0002783307,0.006596364,0.0004245453,0.0001339707,0.0004838392,0.0002114472,0.04592703,0.0009364976,0.9386047,0.006221853,0.000102962],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03507002,0.009134754,0.9139897,0.0219345,0.001175281,0.0006996542,0.0009833724,0.0002455454,0.01676719],"genre_scores_gemma":[0.7070115,0.002424268,0.2738622,0.008950533,0.001861611,0.001906708,0.0006920882,0.0002731094,0.003017926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.780258,"threshold_uncertainty_score":0.9621971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7855151177990123,"score_gpt":0.5831396648779538,"score_spread":0.2023754529210585,"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."}}