{"id":"W4396883665","doi":"10.2139/ssrn.4812540","title":"Automated Plan Generation for Prostate Radiotherapy Patients Using Deep Learning and Scripted Optimization","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University; University of Ottawa; McMaster University","funders":"","keywords":"Plan (archaeology); Computer science; Artificial intelligence; Deep learning; Prostate; Radiation therapy; Medical physics; Medicine; Radiology; Internal medicine; Geography; Archaeology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005101869,0.0002545282,0.0002189391,0.0002059125,0.0004420529,0.0004877411,0.0003427347,0.0001486807,9.731564e-7],"category_scores_gemma":[0.00002887904,0.0002486592,0.00007381802,0.0002554564,0.00002461774,0.0002464146,0.0002496984,0.001867675,8.373349e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104388,"about_ca_system_score_gemma":0.0007260524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005878649,"about_ca_topic_score_gemma":0.00002266938,"domain_scores_codex":[0.9976921,0.000103511,0.0003801164,0.000547403,0.0002093618,0.001067498],"domain_scores_gemma":[0.9991066,0.00003475411,0.0003812654,0.0001964051,0.0002071285,0.00007385256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001561667,0.00002397331,0.0001201872,0.00002620805,0.0001062845,6.529891e-7,0.0002649609,0.9391222,0.0008070718,0.008762511,0.00003438713,0.05071593],"study_design_scores_gemma":[0.0004285575,0.000158941,0.00001213849,0.00004760703,0.00003277809,0.00006596233,0.00001795998,0.9559709,0.00005566061,0.04276215,0.0002127929,0.0002345237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03711997,0.005074166,0.9557974,0.0002935806,0.0005043954,0.0007866321,0.000004442933,0.0004132611,0.000006190935],"genre_scores_gemma":[0.5169436,0.01386017,0.4671781,0.0001415315,0.0009897951,0.0001834048,0.0002959499,0.0001475933,0.0002598937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4886193,"threshold_uncertainty_score":0.9999965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01563107888899079,"score_gpt":0.278902755525507,"score_spread":0.2632716766365162,"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."}}