{"id":"W4393908736","doi":"10.55124/jaim.v1i1.33","title":"Machine learning-based survival prediction in glioma using large scale registry data–the importance of chemotherapy and radiation therapy management as predictive features","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial intelligence and Machine Learning","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiation therapy; Scale (ratio); Glioma; Machine learning; Artificial intelligence; Medicine; Computer science; Oncology; Medical physics; Internal medicine; Cartography; Geography; Cancer research","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":[0.01307457,0.0003682555,0.0006639213,0.003130623,0.0002562071,0.001743839,0.0006991632,0.0005582987,0.001047101],"category_scores_gemma":[0.04817596,0.000188132,0.0007651016,0.003654375,0.0003498353,0.002071453,0.001035597,0.0008795267,0.0004429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005905542,"about_ca_system_score_gemma":0.00134721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005435567,"about_ca_topic_score_gemma":0.007741835,"domain_scores_codex":[0.9947189,0.00339238,0.0006003225,0.0005554059,0.0005293138,0.0002036149],"domain_scores_gemma":[0.9638019,0.02401526,0.006033081,0.003602749,0.001873242,0.0006737015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002707867,0.00009531241,0.9058835,0.0002410858,0.0004110862,0.0000998656,0.0001549637,0.01572113,0.000281243,0.001454309,0.003239848,0.07214691],"study_design_scores_gemma":[0.00008125391,0.0006173998,0.6848266,0.000948615,0.0008193334,0.0008304339,0.001233156,0.2771876,0.002085046,0.01197392,0.01927464,0.000122083],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9157249,0.005906497,0.046234,0.00758018,0.0001787902,0.0002812481,0.01981969,0.0004437352,0.003830853],"genre_scores_gemma":[0.9793779,0.00105182,0.01133055,0.0001828089,0.00008488217,0.0001006997,0.007663195,0.00002784202,0.0001802846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01307457,"threshold_uncertainty_score":0.06914574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0291896136111483,"score_gpt":0.3252552431161357,"score_spread":0.2960656295049874,"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."}}