{"id":"W4399327635","doi":"10.1016/j.radonc.2024.110345","title":"A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy","year":2024,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"European SocieTy for Radiotherapy and Oncology","keywords":"Guideline; Quality assurance; Medical physics; Computer science; Pace; Delphi; Process (computing); Delphi method; Quality (philosophy); Management science; Medicine; Process management; Artificial intelligence; Engineering; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.002549956,0.00008757297,0.0003692475,0.0001582624,0.00005041503,0.000020526,0.00001748761,0.0001647078,0.00001175787],"category_scores_gemma":[0.0003830888,0.00007495447,0.00003275137,0.0001160092,0.00009918463,0.0001160387,0.000005998843,0.0001292522,2.23979e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001133245,"about_ca_system_score_gemma":0.0004309788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001089924,"about_ca_topic_score_gemma":0.00006903143,"domain_scores_codex":[0.9976205,0.00007367614,0.001841367,0.0002662476,0.0000630507,0.0001351911],"domain_scores_gemma":[0.9990035,0.0004059194,0.0003576957,0.00007332415,0.00009110021,0.00006845343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003263229,0.00008565102,0.005326698,0.0001043147,0.00002748381,0.000003449989,0.004336707,0.00004293429,0.002134014,0.002041762,0.00006465344,0.985506],"study_design_scores_gemma":[0.0007857741,0.007178991,0.01711803,0.0006967962,0.000102732,0.0004386947,0.005263206,0.7183709,0.09531578,0.08526821,0.06888406,0.0005768221],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8813152,0.007088234,0.1070304,0.003670695,0.000296599,0.0005533184,0.000001130756,0.00001796489,0.00002654221],"genre_scores_gemma":[0.9551265,0.01163465,0.03227823,0.0005025839,0.0003576869,0.00005150458,0.00002039944,0.00001311029,0.00001540598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9849292,"threshold_uncertainty_score":0.3056554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4648756613231087,"score_gpt":0.5478378291840205,"score_spread":0.08296216786091176,"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."}}