{"id":"W4402990496","doi":"10.1136/emermed-2024-rcem.26","title":"2772 AI assisted reader evaluation in CT head interpretation (AI-REACT): results from a multi-case multi-reader study","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Head (geology); Interpretation (philosophy); Computer science; Artificial intelligence; Natural language processing; Programming language; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05927518,0.001117182,0.001145073,0.002242777,0.0004837584,0.001842572,0.001082688,0.001106245,0.002847771],"category_scores_gemma":[0.1429267,0.001047938,0.004330318,0.002127149,0.0009050248,0.001617647,0.002098605,0.0006210252,0.001211819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006835985,"about_ca_system_score_gemma":0.0006209388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001281886,"about_ca_topic_score_gemma":0.001357415,"domain_scores_codex":[0.935353,0.03929744,0.008943323,0.007119065,0.008447946,0.0008392716],"domain_scores_gemma":[0.7688487,0.1459273,0.03890407,0.02437103,0.02069889,0.001250059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01479564,0.0008982317,0.9293867,0.001834654,0.01868787,0.0003837566,0.002136684,0.0008764056,0.00149065,0.0001366002,0.00168189,0.02769094],"study_design_scores_gemma":[0.0009094357,0.005689631,0.9646069,0.000534811,0.01397981,0.001950873,0.00117587,0.004444999,0.001998072,0.0002162085,0.004302911,0.0001904728],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9833172,0.004581031,0.007528522,0.0001221274,0.0001059691,0.0008171151,0.001869603,0.0001217349,0.001536701],"genre_scores_gemma":[0.9951103,0.0003430582,0.002536015,0.0001649081,0.000105573,0.0003086895,0.001133234,0.00007112939,0.0002270036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05927518,"threshold_uncertainty_score":0.3134809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06760469934268502,"score_gpt":0.4221357942249032,"score_spread":0.3545310948822182,"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."}}