{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02461889,0.0001979872,0.0009807898,0.000626731,0.0002500156,0.00007630281,0.0002156378,0.0001754479,0.0001036673],"category_scores_gemma":[0.1337187,0.0002064271,0.00009007525,0.0005815709,0.0002318232,0.0001910724,0.00008245053,0.0002065759,0.0001889844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003643316,"about_ca_system_score_gemma":0.000191658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002933246,"about_ca_topic_score_gemma":0.0006322453,"domain_scores_codex":[0.9954098,0.0005999224,0.00234338,0.0007039809,0.0002397782,0.0007031245],"domain_scores_gemma":[0.9248229,0.07383874,0.0006025193,0.0002934129,0.0002441795,0.0001982166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000870861,0.0001806298,0.6755842,0.00092022,0.00006927198,0.00001040748,0.00534664,0.0004345097,0.000005112083,0.3051331,0.0009131745,0.01131558],"study_design_scores_gemma":[0.002253449,0.001491401,0.6960245,0.0008035965,0.00002418215,0.000005536489,0.004535316,0.02184948,0.00003432658,0.2700699,0.00260126,0.0003071253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9758888,0.004892482,0.004813643,0.008025375,0.0002866603,0.003681921,0.001049118,0.00005843268,0.001303609],"genre_scores_gemma":[0.9917309,0.002084567,0.002862662,0.0001937244,0.0002200889,0.002260247,0.0001929442,0.00003389777,0.0004209696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1090998,"threshold_uncertainty_score":0.8735784,"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."}}