{"id":"W2600272500","doi":"","title":"Developing a standardized tool for interpretation of radiology diagnostic accuracy trials","year":2016,"lang":"en","type":"dissertation","venue":"Middlesex University Research Repository (Middlesex University Of London)","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Diagnostic accuracy; Medical physics; Medicine; Gold standard (test); Radiological weapon; Radiology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01351656,0.0004534208,0.00181936,0.002416767,0.002225899,0.00009301206,0.00301248,0.001261954,0.0001714207],"category_scores_gemma":[0.02626481,0.0005191552,0.0009405555,0.001432206,0.002469915,0.0008440609,0.0004543122,0.0009924897,0.00002031874],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002880986,"about_ca_system_score_gemma":0.007292846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005527108,"about_ca_topic_score_gemma":0.003458563,"domain_scores_codex":[0.9866599,0.007504729,0.001013153,0.001093017,0.002501429,0.001227758],"domain_scores_gemma":[0.9635584,0.02779161,0.001532625,0.0008977416,0.00585768,0.0003619915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.1280404,0.002394672,0.009869264,0.01515197,0.008557083,0.003320252,0.1309119,0.0001307815,0.1136857,0.2277282,0.06482307,0.2953867],"study_design_scores_gemma":[0.02196085,0.00444589,0.00595254,0.0151244,0.001876531,0.00005078131,0.3762685,0.0003237904,0.08378776,0.02003775,0.4658923,0.004278912],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8095166,0.002728491,0.06473257,0.001881755,0.00224539,0.01517327,0.001656829,0.0005520073,0.1015131],"genre_scores_gemma":[0.8852394,0.0078302,0.006619509,0.000008032768,0.0003760983,0.00001389938,0.00050083,0.000104906,0.09930716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4010692,"threshold_uncertainty_score":0.999726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1423269352725825,"score_gpt":0.4268767891699926,"score_spread":0.2845498538974101,"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."}}