{"id":"W4392104875","doi":"10.1097/sla.0000000000006250","title":"Distinguishing Clinical From Statistical Significances in Contemporary Comparative Effectiveness Research","year":2024,"lang":"en","type":"article","venue":"Annals of Surgery","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Cancer Institute","keywords":"Medicine; Clinical significance; Statistical significance; Observational study; Clinical trial; Sample size determination; Comparative effectiveness research; MEDLINE; Clinical study design; Internal medicine; Intensive care medicine; Alternative medicine; Pathology","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":[0.845305,0.002509543,0.007914533,0.03013181,0.003184652,0.01822002,0.008496745,0.008779519,0.00194025],"category_scores_gemma":[0.9470179,0.003057105,0.008621566,0.02672566,0.02951857,0.01971168,0.01147932,0.007176382,0.0003280018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01157295,"about_ca_system_score_gemma":0.01362056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001050707,"about_ca_topic_score_gemma":0.001342189,"domain_scores_codex":[0.04605808,0.6972525,0.1791228,0.01284925,0.06376204,0.0009552991],"domain_scores_gemma":[0.01014175,0.9022774,0.06051961,0.01448123,0.01217711,0.0004029273],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007402097,0.0004720736,0.161009,0.2370901,0.04580512,0.0009910429,0.0240198,0.003361847,0.001239432,0.1254033,0.0122629,0.3809433],"study_design_scores_gemma":[0.007540357,0.008749729,0.08961507,0.3558547,0.04143931,0.006617791,0.02068771,0.01757301,0.006919742,0.364406,0.07943342,0.001163212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.06727789,0.6877676,0.1593093,0.0496878,0.01049599,0.009932156,0.001510518,0.0003223057,0.01369659],"genre_scores_gemma":[0.7632149,0.03994439,0.1491025,0.02344948,0.006978285,0.01595609,0.0008694787,0.0001639624,0.0003210258],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.154695,"threshold_uncertainty_score":0.1907666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9704443140674623,"score_gpt":0.676357735808296,"score_spread":0.2940865782591664,"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."}}