{"id":"W2619187656","doi":"10.1002/jrsm.1243","title":"Evaluating the accuracy and economic value of a new test in the absence of a perfect reference test","year":2017,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre; University of Toronto","funders":"","keywords":"Test (biology); Medicine; Confidence interval; Diagnostic test; Diagnostic accuracy; Computer science; Statistics; Internal medicine; Mathematics; Pediatrics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01662544,0.00007244194,0.0001520514,0.00004037785,0.0002503805,0.0001072329,0.0007813271,0.00006600105,0.0000251632],"category_scores_gemma":[0.1268317,0.00004564477,0.00004006538,0.00005414705,0.000374222,0.00001001269,0.0002669285,0.0001573776,0.000001928648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001308658,"about_ca_system_score_gemma":0.0002607122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001252464,"about_ca_topic_score_gemma":0.0001608465,"domain_scores_codex":[0.9973073,0.001808257,0.0002755713,0.0002672011,0.0001643951,0.0001772663],"domain_scores_gemma":[0.9871649,0.01135512,0.0002164977,0.001097321,0.0001267513,0.00003945906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001963153,0.00003000917,0.01849449,0.00003276566,0.000006089046,1.514382e-7,0.000216503,0.000004300945,0.9005696,0.0001197192,0.00003487731,0.08047186],"study_design_scores_gemma":[0.000149562,0.0002485235,0.4613861,0.0000889465,0.000009401933,0.000006679766,0.0004655987,0.002755907,0.5336058,0.0008105335,0.0003911627,0.00008183535],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978194,0.0001494502,0.0001517504,0.0006515713,0.00002097533,0.0002555486,0.0000101792,0.000001649589,0.0009395406],"genre_scores_gemma":[0.9843975,0.0001555537,0.01521724,0.000009026195,0.00006124982,0.00002922284,0.000001249398,0.000006517157,0.0001224547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4428916,"threshold_uncertainty_score":0.8805233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.344092019384229,"score_gpt":0.5575045538813157,"score_spread":0.2134125344970867,"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."}}