{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02066479,0.001198262,0.0006261145,0.003705747,0.0009623409,0.001772038,0.001498551,0.001236159,0.0009269124],"category_scores_gemma":[0.08541869,0.0004308449,0.000615149,0.002677992,0.001778509,0.00136136,0.001759434,0.0007363727,0.000368154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534171,"about_ca_system_score_gemma":0.001025281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004893942,"about_ca_topic_score_gemma":0.005742044,"domain_scores_codex":[0.9736154,0.009741985,0.002704715,0.002527883,0.01091716,0.0004927379],"domain_scores_gemma":[0.9040936,0.05657921,0.01030262,0.01033256,0.0181782,0.0005137402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007826716,0.0002114045,0.4788186,0.001194959,0.000501447,0.001380998,0.006748561,0.06127053,0.03020238,0.00634029,0.003071041,0.4094772],"study_design_scores_gemma":[0.0001095386,0.002756897,0.433995,0.001057808,0.0005559062,0.01282594,0.005649451,0.1834378,0.3154577,0.01411479,0.02939583,0.0006432901],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6714658,0.001761721,0.3132761,0.0005887031,0.00009399114,0.0003077322,0.0004858082,0.001659927,0.01036019],"genre_scores_gemma":[0.898661,0.0001788223,0.1001872,0.00008310477,0.00001241828,0.00005963806,0.0001605356,0.0002496525,0.0004077049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02066479,"threshold_uncertainty_score":0.1092872,"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."}}