{"id":"W2134265312","doi":"10.1177/0163278709338561","title":"Medical Record Review Conduction Model for Improving Interrater Reliability of Abstracting Medical-Related Information","year":2009,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Inter-rater reliability; Reliability (semiconductor); Medical record; Medical information; Psychology; Medicine; Family medicine; Internal medicine; Developmental psychology","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":[0.3829258,0.002171156,0.002567743,0.007971213,0.002942379,0.00575095,0.005361676,0.002485123,0.00254889],"category_scores_gemma":[0.5388322,0.001860576,0.003532669,0.006129871,0.003738308,0.009083599,0.006219733,0.003221905,0.003060449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006480835,"about_ca_system_score_gemma":0.01942221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005794473,"about_ca_topic_score_gemma":0.008154671,"domain_scores_codex":[0.4661978,0.4419437,0.03157043,0.0155778,0.0427511,0.001959275],"domain_scores_gemma":[0.3149949,0.4417827,0.05847386,0.04881037,0.1328466,0.003091486],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002400611,0.001487466,0.1339931,0.005749167,0.001907797,0.0003943692,0.01979896,0.02827853,0.005643853,0.04084719,0.02297389,0.7365249],"study_design_scores_gemma":[0.002478471,0.01085366,0.1025524,0.007117652,0.0035063,0.002896751,0.007848274,0.6903766,0.02127996,0.07653934,0.07310417,0.001446352],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02757074,0.0009190796,0.9456509,0.002383454,0.0003382296,0.01364948,0.000436524,0.002707581,0.006344069],"genre_scores_gemma":[0.1322189,0.0004805689,0.8508326,0.0006609738,0.0001732751,0.01343722,0.0005142203,0.0002420151,0.00144019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6170743,"threshold_uncertainty_score":0.7609624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1741437033261165,"score_gpt":0.5366436959399579,"score_spread":0.3624999926138414,"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."}}