{"id":"W2077200403","doi":"10.1118/1.4826166","title":"Evaluating IMRT and VMAT dose accuracy: Practical examples of failure to detect systematic errors when applying a commonly used metric and action levels","year":2013,"lang":"en","type":"article","venue":"Medical Physics","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":233,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hôpital Maisonneuve-Rosemont","funders":"National Cancer Institute; Sun Nuclear Corporation","keywords":"Dosimetry; Metric (unit); Radiation treatment planning; Computer science; Medical physics; Normalization (sociology); Nuclear medicine; Linear particle accelerator; Quality assurance; Medicine; Beam (structure); Radiation therapy; Radiology; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005460737,0.0002008868,0.0005091237,0.00007463235,0.0001034352,0.00005729753,0.0001324636,0.00007306819,0.0001191808],"category_scores_gemma":[0.0005094798,0.0001611857,0.00005494109,0.000249724,0.0001043149,0.0003862515,0.0001074925,0.0002910787,0.000003568456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003751185,"about_ca_system_score_gemma":0.00006977315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002826366,"about_ca_topic_score_gemma":0.000005684723,"domain_scores_codex":[0.9983175,0.0001831007,0.0004098543,0.0002735529,0.0005762134,0.0002398142],"domain_scores_gemma":[0.9976751,0.001468414,0.0002788488,0.0002656211,0.00009512983,0.0002169114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004304548,0.0002490085,0.008010025,0.005389929,0.0004955059,0.0000033777,0.003790857,0.00004273785,0.07980859,0.003304838,0.0005171377,0.8983449],"study_design_scores_gemma":[0.01386319,0.003928557,0.02656321,0.0235708,0.002093782,0.0001459108,0.01063517,0.1694431,0.3355123,0.4066758,0.002002798,0.005565376],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3671288,0.00008444361,0.6310015,0.0003351661,0.00002881523,0.001320055,0.000006770055,0.00005873269,0.00003564073],"genre_scores_gemma":[0.9076059,0.000004307757,0.09188235,0.00006805546,0.0001349417,0.0002608665,0.000004096108,0.00002907031,0.00001040346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8927796,"threshold_uncertainty_score":0.6572962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09485530568331411,"score_gpt":0.3962924599790567,"score_spread":0.3014371542957425,"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."}}