{"id":"W1955533988","doi":"10.6000/1929-6029.2015.04.02.2","title":"On the Relationship between the Reliability and Accuracy of Bio-Behavioral Diagnoses: Simple Math to the Rescue","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medical diagnosis; Kappa; Mathematics; Statistics; Cohen's kappa; Equivalence (formal languages); Statistic; Youden's J statistic; Combinatorics; Psychology; Medicine; Discrete mathematics; Pathology; Receiver operating characteristic; Geometry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05023639,0.001680531,0.002517236,0.005459091,0.001162353,0.003649302,0.002648136,0.00340312,0.006234325],"category_scores_gemma":[0.346624,0.001153544,0.002294475,0.002860126,0.01217632,0.006998986,0.005156949,0.003833644,0.001656136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00295246,"about_ca_system_score_gemma":0.001286862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006811299,"about_ca_topic_score_gemma":0.002479502,"domain_scores_codex":[0.9737587,0.01648511,0.001351278,0.004404689,0.003669622,0.000330577],"domain_scores_gemma":[0.6739147,0.2989172,0.006809124,0.01211349,0.007680553,0.0005650052],"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":[0.0006797015,0.0002794793,0.09642831,0.001040378,0.002039261,0.0007740232,0.005428107,0.08307695,0.001908605,0.5116899,0.01643725,0.2802181],"study_design_scores_gemma":[0.0001393438,0.0005725859,0.0240593,0.0006378466,0.0002491681,0.001078467,0.0009277313,0.1557358,0.0008009255,0.807289,0.008322484,0.0001874638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1341599,0.006576454,0.7750584,0.02442049,0.001090696,0.0005271196,0.001173182,0.0006519246,0.05634172],"genre_scores_gemma":[0.7232857,0.002299161,0.263975,0.003237677,0.0008563174,0.0008568435,0.0004658555,0.0002192981,0.004804197],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9497636,"threshold_uncertainty_score":0.2656786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5558141781385264,"score_gpt":0.5812588006269411,"score_spread":0.02544462248841473,"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."}}