{"id":"W3032017599","doi":"10.1007/s00264-020-04609-7","title":"Deep learning COVID-19 detection bias: accuracy through artificial intelligence","year":2020,"lang":"en","type":"article","venue":"International Orthopaedics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":192,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Medicine; Artificial intelligence; Coronavirus Infections; Deep learning; Orthopedic surgery; Machine learning; Virology; Surgery; Computer science; Internal medicine; Infectious disease (medical specialty)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003304338,0.0002169878,0.0002560378,0.0001517812,0.0001733024,0.00009788409,0.0002579174,0.0001402206,0.0009311431],"category_scores_gemma":[0.02028278,0.0002223159,0.0002256835,0.0004935208,0.0001178973,0.0002933762,0.0001473732,0.0006307688,0.000432553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004462605,"about_ca_system_score_gemma":0.0003571563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000183331,"about_ca_topic_score_gemma":0.00008094868,"domain_scores_codex":[0.9977449,0.00009234752,0.0005723265,0.000512566,0.0008179963,0.0002598651],"domain_scores_gemma":[0.9979349,0.0009053466,0.0002630898,0.0001876538,0.0003075711,0.0004014428],"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":[0.00231628,0.000851388,0.06163776,0.0005196165,0.0006937071,0.001421845,0.01276135,0.07670301,0.01346916,0.0107715,0.006389983,0.8124644],"study_design_scores_gemma":[0.0006079637,0.0004445706,0.002698113,0.0001015692,0.0001389433,0.0001504121,0.000854691,0.1710996,0.007178393,0.00235078,0.8140022,0.0003728482],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07495484,0.0002473049,0.6643472,0.2565784,0.001742904,0.0004967771,0.00001337286,0.0007036132,0.0009156229],"genre_scores_gemma":[0.905555,0.0002835145,0.002102961,0.09025189,0.001588352,0.0000318107,0.00007459916,0.00004119363,0.00007068305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8306001,"threshold_uncertainty_score":0.9999821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1324240516387547,"score_gpt":0.3865001703369287,"score_spread":0.254076118698174,"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."}}