{"id":"W4392947622","doi":"10.1136/bmjqs-2023-016695","title":"Crowdsourcing a diagnosis? Exploring the accuracy of the size and type of group diagnosis: an experimental study","year":2024,"lang":"en","type":"article","venue":"BMJ Quality & Safety","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Royal College of Physicians and Surgeons of Canada","keywords":"Medical diagnosis; Medicine; Differential diagnosis; Nominal group technique; Crowdsourcing; Group (periodic table); Diagnostic accuracy; Medical physics; Radiology; Artificial intelligence; Pathology; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03626793,0.0008178093,0.00119581,0.001145652,0.001465596,0.002683487,0.001652745,0.002291225,0.006503884],"category_scores_gemma":[0.2093454,0.0008379119,0.0009255696,0.0005549494,0.004572404,0.003114512,0.003420348,0.001789082,0.000822783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001535465,"about_ca_system_score_gemma":0.001616636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001243401,"about_ca_topic_score_gemma":0.0008578954,"domain_scores_codex":[0.9753233,0.01578092,0.001626723,0.003149212,0.003376316,0.0007436518],"domain_scores_gemma":[0.5698432,0.3779463,0.02436403,0.01801618,0.005453143,0.004377225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.1974841,0.18455,0.1845376,0.004128988,0.001556174,0.0009435636,0.1006702,0.01388338,0.04035729,0.008457655,0.00381033,0.2596208],"study_design_scores_gemma":[0.04667114,0.4400075,0.3046654,0.001160181,0.002009261,0.0008779679,0.0272793,0.1013795,0.03323266,0.02944972,0.01202669,0.001240673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994722,0.00005970639,0.001766694,0.0001588511,0.00007092582,0.001296586,0.00006226329,0.00002416261,0.001838815],"genre_scores_gemma":[0.988539,0.00007202721,0.006725293,0.0002404805,0.000129048,0.003197185,0.00008987093,0.00002267068,0.0009843262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03626793,"threshold_uncertainty_score":0.1918054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1647990118473574,"score_gpt":0.4631113570271014,"score_spread":0.2983123451797439,"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."}}