{"id":"W2086743973","doi":"10.1016/j.cmpb.2011.09.011","title":"Improving the medical scale predictability by the pairwise comparisons method: Evidence from a clinical data study","year":2011,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Laurentian University; University of Sudbury","funders":"","keywords":"Predictability; Pairwise comparison; Reliability (semiconductor); Scale (ratio); Computer science; Clinical Practice; Medical diagnosis; Psychology; Machine learning; Clinical psychology; Artificial intelligence; Data mining; Medicine; Statistics; Family medicine; Mathematics","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":["metaresearch"],"category_scores_codex":[0.1793863,0.0002894159,0.0008363718,0.00008299777,0.0003191493,0.0002491655,0.004832724,0.0001756389,0.0002173903],"category_scores_gemma":[0.009513216,0.0001200212,0.0001116892,0.001061813,0.001649009,0.0002811716,0.003049823,0.0009183004,0.000006736295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002656917,"about_ca_system_score_gemma":0.000122257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003380126,"about_ca_topic_score_gemma":0.0006363806,"domain_scores_codex":[0.9760513,0.01630038,0.002489472,0.001778335,0.002895773,0.0004847735],"domain_scores_gemma":[0.973866,0.02135486,0.0004825497,0.003689768,0.0002439377,0.000362854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006075152,0.0007554344,0.3858015,0.000005924553,0.00003327212,0.000004015284,0.002225504,1.999063e-7,0.00001315093,0.000002502944,0.003681539,0.6074162],"study_design_scores_gemma":[0.00204434,0.002515148,0.7219742,0.0003085799,0.000213825,0.00001543556,0.007361924,0.2323458,0.00003032667,0.004890793,0.02795997,0.0003396717],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1990132,0.00284358,0.7900453,0.004965369,0.001388695,0.001661804,0.00001653323,0.00004435506,0.00002120294],"genre_scores_gemma":[0.24369,0.0001705524,0.7543101,0.001048369,0.0006278991,0.0001063624,0.0000172475,0.00001223221,0.00001733413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6070765,"threshold_uncertainty_score":0.9988301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7015660725220738,"score_gpt":0.562736366494007,"score_spread":0.1388297060280668,"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."}}