{"id":"W3128741565","doi":"10.1016/j.jbi.2021.103694","title":"A neuro evolutionary algorithm for patient calibrated prediction of survival in Glioblastoma patients","year":2021,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"European Organisation for Research and Treatment of Cancer","keywords":"Temozolomide; Genetic algorithm; Artificial neural network; Schedule; Computer science; Autoencoder; Evolutionary algorithm; Glioblastoma; Medicine; Artificial intelligence; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006717939,0.0001603594,0.0006099429,0.0002988549,0.00003387675,0.00001229266,0.0001992784,0.0001973378,0.00006382664],"category_scores_gemma":[0.003685757,0.0001234347,0.0001899173,0.0005223178,0.0001722782,0.0002546991,0.0001059079,0.0003099018,0.000002496388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009666309,"about_ca_system_score_gemma":0.0002657127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.615605e-7,"about_ca_topic_score_gemma":9.767531e-7,"domain_scores_codex":[0.9963847,0.0001282544,0.002413874,0.0000765181,0.0007299395,0.0002667241],"domain_scores_gemma":[0.9963801,0.001338409,0.001133532,0.0001751272,0.0007795463,0.0001932881],"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":[0.003936027,0.05561454,0.04511428,0.01998283,0.003299785,0.001040811,0.04022928,0.0001362785,0.005833447,0.06742954,0.3395646,0.4178186],"study_design_scores_gemma":[0.03220845,0.02253624,0.01669497,0.004015699,0.0007778704,0.001759206,0.009524049,0.5650286,0.01968332,0.302963,0.02336756,0.001441041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8480312,0.00005063933,0.1491455,0.0003513673,0.001148858,0.0004765078,0.0004734093,0.00002788285,0.0002945888],"genre_scores_gemma":[0.5058701,0.000063876,0.4929152,0.0005172783,0.0003487403,0.00003227474,0.0001334974,0.00006391929,0.00005509889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5648923,"threshold_uncertainty_score":0.5033519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01838657716628617,"score_gpt":0.2629646292564601,"score_spread":0.244578052090174,"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."}}