{"id":"W2809074538","doi":"10.1007/978-3-030-35758-0_31","title":"Evaluating Image Training Systems for Medical Students","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Skin lesion; Categorization; Lesion; Computer science; Skin cancer; Medicine; Medical physics; Dermatology; Cancer; Artificial intelligence; Radiology; Surgery; Internal medicine","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":[0.001698663,0.0006834308,0.0004099264,0.0009332186,0.0001724078,0.0009696328,0.0007076815,0.0009936577,0.00837997],"category_scores_gemma":[0.00740844,0.0001939953,0.0003679144,0.0004309669,0.0001467899,0.0007120472,0.0005324675,0.0003607236,0.002190274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000437219,"about_ca_system_score_gemma":0.0002742716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001899489,"about_ca_topic_score_gemma":0.002679263,"domain_scores_codex":[0.9993383,0.0002146928,0.00004533256,0.0001235852,0.0002201833,0.00005777187],"domain_scores_gemma":[0.9958302,0.002876794,0.0001774858,0.0002064488,0.0007626892,0.000146363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00136688,0.0005634587,0.02247361,0.0002527749,0.000118548,0.0001028415,0.00009010793,0.0251421,0.02493524,0.0004347271,0.01535305,0.9091666],"study_design_scores_gemma":[0.0001835521,0.003763123,0.06332432,0.0001720633,0.0003975687,0.0007509911,0.0005105195,0.8044468,0.1130463,0.002110545,0.01123462,0.00005976167],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7869436,0.005609635,0.1731708,0.001526382,0.0009312875,0.0006965283,0.002468543,0.004439396,0.02421384],"genre_scores_gemma":[0.8868388,0.001264533,0.08861391,0.0003042493,0.0001682718,0.0001257752,0.003373939,0.0002220494,0.01908846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00837997,"threshold_uncertainty_score":0.02803379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04965815756900538,"score_gpt":0.3550171668521349,"score_spread":0.3053590092831295,"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."}}