{"id":"W3023537583","doi":"10.1016/j.ejmp.2021.10.003","title":"On the use of machine learning methods for mPSD calibration in HDR brachytherapy","year":2021,"lang":"en","type":"preprint","venue":"Physica Medica","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Calibration; Brachytherapy; Linear regression; Random forest; Artificial neural network; Detector; Scintillator; Dosimetry; Mathematics; Statistics; Algorithm; Computer science; Optics; Physics; Artificial intelligence; Nuclear medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003722907,0.0002538412,0.0005036311,0.00006980897,0.00006461886,0.00004357661,0.0002653486,0.00009305658,0.0002007978],"category_scores_gemma":[0.0001009064,0.0001890558,0.0002372607,0.0001444807,0.00008834196,0.0001019881,0.0001103352,0.0008542345,1.71722e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003966427,"about_ca_system_score_gemma":0.0001180003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002526359,"about_ca_topic_score_gemma":0.000003489134,"domain_scores_codex":[0.9984257,0.0004555222,0.0003491923,0.0003842579,0.0001855129,0.0001998527],"domain_scores_gemma":[0.99742,0.001589224,0.000385698,0.0005020741,0.00006268876,0.00004035194],"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":[0.0002330591,0.0009965865,0.001712511,0.0002332302,0.0007907643,0.000001778323,0.004930152,0.02056647,0.04595606,0.07681691,0.002335029,0.8454275],"study_design_scores_gemma":[0.001314176,0.0003738682,0.0002555817,0.001082593,0.0001006391,4.134278e-7,0.0001853981,0.6538339,0.1485624,0.1043438,0.08907823,0.0008690615],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01317015,0.0002401195,0.9842134,0.001195607,0.0001353401,0.0007952896,0.00004798057,0.0000555966,0.000146498],"genre_scores_gemma":[0.5371413,0.000248195,0.45913,0.0005036421,0.0007078942,0.001206304,0.0006509168,0.0001362795,0.0002753553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8445584,"threshold_uncertainty_score":0.7709474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04704118007009968,"score_gpt":0.3745648581108261,"score_spread":0.3275236780407264,"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."}}