{"id":"W4384828140","doi":"10.21203/rs.3.rs-3135514/v1","title":"Predictive Biomarker Profiles in Cancer Using a Unique AI Model Based on Set Theory","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Numerical Methods and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Identification (biology); Biomarker; Outcome (game theory); Cancer; Set (abstract data type); Computer science; Artificial intelligence; Biomarker discovery; Machine learning; Computational biology; Medicine; Internal medicine; Mathematics; Biology; Proteomics","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":[0.005732266,0.0003013965,0.0004079151,0.001035725,0.0001737256,0.000289236,0.001524727,0.0003416548,0.00002203718],"category_scores_gemma":[0.0007055426,0.0002506728,0.0001482362,0.001634484,0.0001923029,0.0001585419,0.002373406,0.002174598,0.00001470119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006978139,"about_ca_system_score_gemma":0.001937948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001172116,"about_ca_topic_score_gemma":0.00002582075,"domain_scores_codex":[0.9931794,0.003054654,0.0003326501,0.00121903,0.001355688,0.000858595],"domain_scores_gemma":[0.9965883,0.00145522,0.00009117302,0.001168999,0.000472089,0.0002242006],"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":[0.0003156884,0.0004549351,0.00174619,0.001311076,0.00008521464,0.0003267331,0.001584801,0.8414563,0.000676281,0.02076759,0.001184058,0.1300911],"study_design_scores_gemma":[0.0001833979,0.0001052947,0.001482603,0.001574782,0.000002677511,3.922827e-7,0.00005449685,0.8629218,0.0004500721,0.1329455,0.00005096736,0.0002279871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002774522,0.0001424775,0.9921314,0.00237166,0.0002937663,0.001361347,0.0003565582,0.0002115688,0.0003566647],"genre_scores_gemma":[0.39509,0.0002955909,0.5988141,0.0006712998,0.0004017141,0.003401249,0.00008164896,0.000198566,0.00104585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3933174,"threshold_uncertainty_score":0.9999946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2520936272897684,"score_gpt":0.503769002380663,"score_spread":0.2516753750908946,"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."}}