{"id":"W4317935575","doi":"10.1038/s41598-023-28633-w","title":"Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; St. Michael's Hospital","funders":"Ludwig-Maximilians-Universität München; Volkswagen Foundation","keywords":"Advice (programming); Task (project management); Computer science; Medical education; Information retrieval; Data science; Medical physics; Medicine; Programming language; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001386847,0.00019186,0.0003903788,0.0002458228,0.0006063299,0.0001894663,0.0001299121,0.000109345,0.0004696313],"category_scores_gemma":[0.0004383145,0.000178274,0.0001623687,0.001122493,0.0001230165,0.0003332426,0.00006630763,0.0002305492,0.001020447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001692694,"about_ca_system_score_gemma":0.0003600259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003962414,"about_ca_topic_score_gemma":0.0002035691,"domain_scores_codex":[0.9969682,0.00003062619,0.0008349044,0.0009450607,0.0006439328,0.0005772874],"domain_scores_gemma":[0.997699,0.0001098225,0.000290036,0.001190663,0.0004892143,0.0002212738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002706733,0.000162284,0.01501393,0.0001672421,0.00003542956,0.000667069,0.02298629,0.00009378826,0.02956436,0.00001153662,0.7652047,0.1660664],"study_design_scores_gemma":[0.00005278257,0.0001370386,0.002522082,0.002025113,0.0001108806,0.0001416369,0.01320941,0.003966368,0.108573,0.02031724,0.8484206,0.000523921],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9580525,0.001655619,0.0003871398,0.005497241,0.02879794,0.001052899,0.000005925289,0.0005129488,0.004037861],"genre_scores_gemma":[0.9660628,0.0002398584,0.0006799654,0.002209209,0.001450475,0.0001972448,0.0006903791,0.00005244978,0.02841766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1655424,"threshold_uncertainty_score":0.9997573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08699927926590688,"score_gpt":0.3817459205517338,"score_spread":0.2947466412858269,"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."}}