{"id":"W3045831398","doi":"10.1634/theoncologist.2020-0054","title":"Can Oncologists Predict the Efficacy of Treatments in Randomized Trials?","year":2020,"lang":"en","type":"article","venue":"The Oncologist","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Medicine; Confidence interval; Guideline; Subspecialty; Brier score; Sample size determination; Medical physics; Family medicine; Statistics; Surgery; Internal medicine; Mathematics","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":["metaresearch"],"category_scores_codex":[0.02946521,0.0001584037,0.00182204,0.00004169252,0.00008838785,0.0000158922,0.0006299085,0.0003099205,0.0002573904],"category_scores_gemma":[0.3210055,0.00006317904,0.0004949401,0.0004114428,0.002595699,0.0000156037,0.0002441614,0.001569869,0.00004797474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002436076,"about_ca_system_score_gemma":0.001092985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008859499,"about_ca_topic_score_gemma":0.0006955804,"domain_scores_codex":[0.9932042,0.004047191,0.001345245,0.0003077303,0.0007822044,0.0003134248],"domain_scores_gemma":[0.7511322,0.246684,0.000726866,0.0009456046,0.0002680871,0.0002433088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.8679041,0.004531074,0.02676366,0.0004809859,0.002510586,0.0005525488,0.009162645,0.0003893467,0.002299254,0.03084117,0.01568008,0.03888455],"study_design_scores_gemma":[0.8593111,0.008405362,0.08255006,0.0004795912,0.002035911,0.00002260637,0.001793724,0.001905184,0.002418753,0.03510158,0.005687539,0.0002885665],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.538013,0.0008386511,0.00006072186,0.4162537,0.0003202219,0.006345188,0.00003691859,0.00008118062,0.03805031],"genre_scores_gemma":[0.9931574,0.001277461,0.0002247052,0.00343368,0.0003283118,0.000207464,0.000009841925,0.00001553841,0.001345567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4551444,"threshold_uncertainty_score":0.9993698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6602040357516019,"score_gpt":0.6079458512679481,"score_spread":0.05225818448365382,"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."}}