{"id":"W4399653857","doi":"10.1016/s2214-109x(24)00148-7","title":"Diagnostic yield as an important metric for the evaluation of novel tuberculosis tests: rationale and guidance for future research","year":2024,"lang":"en","type":"article","venue":"The Lancet Global Health","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Centre for Advancing Health Outcomes; McGill University Health Centre","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Metric (unit); Yield (engineering); Tuberculosis; Computer science; Psychology; Data science; Medicine; Engineering; Operations management; Pathology; Physics","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":[],"category_scores_codex":[0.01649536,0.0001004637,0.0003470868,0.00007607308,0.0002802605,0.00002903451,0.0001872569,0.00007761093,0.00002187227],"category_scores_gemma":[0.01715982,0.00005197717,0.00007197033,0.0006789424,0.0001511345,0.00006554455,0.00004330117,0.0002423867,0.000003067373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003205726,"about_ca_system_score_gemma":0.001126329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001186116,"about_ca_topic_score_gemma":0.001217636,"domain_scores_codex":[0.9977629,0.0003450759,0.0003920884,0.0003025678,0.0006690776,0.0005282563],"domain_scores_gemma":[0.9894722,0.00922507,0.00007240118,0.0004215254,0.0006458875,0.000162896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002066521,0.0005438427,0.04224468,0.002997831,0.0006411514,0.00000331992,0.00107532,0.0002418275,0.0005438009,0.2533388,0.4575118,0.2387911],"study_design_scores_gemma":[0.003121499,0.004011402,0.7173299,0.0006386883,0.0003129145,0.0001466892,0.001444753,0.1642567,0.0000930815,0.04458194,0.06390602,0.0001564822],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2660087,0.1545985,0.001653648,0.5679883,0.0004875072,0.007476709,0.001306691,0.00005487412,0.000425036],"genre_scores_gemma":[0.977294,0.01191453,0.00155006,0.005440596,0.002461884,0.001158341,0.0001186387,0.00001582782,0.00004609689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7112854,"threshold_uncertainty_score":0.9911191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2494196016747202,"score_gpt":0.5349694165364793,"score_spread":0.2855498148617591,"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."}}