{"id":"W4403828500","doi":"10.1002/mp.17468","title":"Which failures do patient‐specific quality assurance systems need to catch?","year":2024,"lang":"en","type":"article","venue":"Medical Physics","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baker Hughes (Canada); University of Toronto","funders":"","keywords":"Quality assurance; Failure mode and effects analysis; Medicine; Medical physics; Audit; Quality (philosophy); Reliability engineering; Computer science; Accounting; Engineering; Business","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":{"n_in":0,"stratum":"aff_core","weight":5595.2375,"opus":{"tier":"OUT","genre":"empirical","about_ca":false,"confidence":"high","reason":"Failure-mode analysis for radiotherapy patient-specific quality assurance; 'quality assurance' here is clinical dosimetry, not research practice (polysemy)."},"gpt":{"tier":"OUT","genre":"empirical","about_ca":false,"confidence":"high","reason":"This study evaluates clinical radiotherapy quality assurance rather than research quality or practice."},"grok":{"tier":"OUT","genre":"empirical","about_ca":false,"confidence":"high","reason":"Clinical radiotherapy patient-specific QA failure modes; quality-assurance polysemy, not research integrity or methods research."}},"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0991701,0.0007925557,0.001171604,0.007229967,0.00174167,0.00508381,0.001852053,0.001073722,0.002434316],"category_scores_gemma":[0.2628423,0.0006580204,0.001838939,0.006258148,0.001967242,0.006097909,0.00292558,0.001617028,0.0006391147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005018932,"about_ca_system_score_gemma":0.009803858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008574728,"about_ca_topic_score_gemma":0.006331342,"domain_scores_codex":[0.9293649,0.02316952,0.01380702,0.006867079,0.02398626,0.002805203],"domain_scores_gemma":[0.4901554,0.2538201,0.1497698,0.03093731,0.06995211,0.005365324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004199694,0.0001134172,0.6678095,0.001816601,0.0003612699,0.0001686027,0.0040599,0.003453955,0.001321424,0.002441161,0.003912405,0.3141218],"study_design_scores_gemma":[0.00008411145,0.001418988,0.9148901,0.003935577,0.0006651368,0.001170206,0.01102873,0.01302823,0.006183304,0.01834756,0.02898855,0.0002595905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7972048,0.01093031,0.1526575,0.01966211,0.0003573702,0.001383767,0.003946769,0.001606829,0.01225057],"genre_scores_gemma":[0.9595787,0.001825231,0.03506806,0.00123012,0.0001371558,0.0003190744,0.001175907,0.0001897747,0.0004760169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0991701,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307914533301444,"score_gpt":0.3050106248907061,"score_spread":0.2919314795576916,"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."}}