{"id":"W2915771614","doi":"10.1097/pai.0000000000000734","title":"Diagnostic Accuracy in Fit-for-Purpose PD-L1 Testing","year":2019,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Saskatchewan Health Authority; Vancouver General Hospital; University Health Network; University of Toronto; University of British Columbia","funders":"","keywords":"Gold standard (test); Quality assurance; Medicine; Diagnostic test; Medical physics; Tonsil; Diagnostic accuracy; External quality assessment; Computer science; Pathology; Internal medicine; Emergency medicine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002388506,0.000420653,0.0004387085,0.00007910951,0.00008077204,0.00003789349,0.0005904999,0.0004303876,0.00007678856],"category_scores_gemma":[0.001506145,0.0005153162,0.0001706765,0.0002254169,0.0001554942,0.000004646769,0.0003358712,0.0002921107,0.00008548573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384736,"about_ca_system_score_gemma":0.0002683612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007427327,"about_ca_topic_score_gemma":0.000001068109,"domain_scores_codex":[0.9976122,0.00002851913,0.0005498214,0.0009570313,0.0001486091,0.000703842],"domain_scores_gemma":[0.9979354,0.0004670421,0.0002393258,0.001104099,0.0001334456,0.0001206676],"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":[0.0002374239,0.0001193206,0.001314203,0.00007662422,0.00004794802,0.00004241823,0.00002693861,0.001055617,0.9937985,0.000295527,0.0009735068,0.002011965],"study_design_scores_gemma":[0.003217914,0.0003390669,0.002968543,0.00004760506,0.00005760067,0.0001508882,0.00008514174,0.00009015414,0.9840415,0.000649088,0.00748763,0.0008648536],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894404,0.002457786,0.001395294,0.00009937983,0.000349625,0.001080805,0.00006709802,0.00003043409,0.005079167],"genre_scores_gemma":[0.9937227,0.0001209621,0.003300052,0.001106523,0.0001632141,0.0006148263,0.00054839,0.00009982069,0.0003235505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009756994,"threshold_uncertainty_score":0.9997299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009939194139760184,"score_gpt":0.256723156792273,"score_spread":0.2467839626525128,"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."}}