{"id":"W4393169231","doi":"10.1016/j.imu.2024.101481","title":"Predictive biomarker discovery in cancer using a unique AI model based on set theory","year":2024,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"MEDTEQ+","keywords":"Biomarker discovery; Computational biology; Set (abstract data type); Computer science; Biomarker; Cancer; Artificial intelligence; Machine learning; Biology; Proteomics; Genetics","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":[0.002014217,0.0002985371,0.0005761381,0.001205,0.00005041543,0.00004644375,0.0001737268,0.0001725303,0.00008192672],"category_scores_gemma":[0.0009197178,0.0002137117,0.00008086445,0.0009053248,0.0003280716,0.0003502047,0.00005530082,0.00137568,0.000005321476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000587148,"about_ca_system_score_gemma":0.0007289444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002733979,"about_ca_topic_score_gemma":0.00001780227,"domain_scores_codex":[0.9976533,0.0001178533,0.0009152747,0.000238201,0.0006353353,0.0004400071],"domain_scores_gemma":[0.998749,0.0005475678,0.0001072236,0.0003549035,0.00006468515,0.0001765744],"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":[0.002171942,0.0004320819,0.02278817,0.004141419,0.0002970005,0.0009397201,0.04277524,0.8555517,0.001906607,0.01266154,0.01050507,0.04582956],"study_design_scores_gemma":[0.002566101,0.0001976959,0.0009926584,0.008275392,0.000100176,0.00003472995,0.001318106,0.9826426,0.00006924592,0.002720326,0.0008837225,0.0001992623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5500003,0.0006611254,0.4275923,0.009896154,0.0008221868,0.001015922,0.00003943532,0.000189973,0.009782619],"genre_scores_gemma":[0.985267,0.000154646,0.003309365,0.01060483,0.0001693916,0.00005725806,0.00006951682,0.00005064777,0.0003173685],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4352667,"threshold_uncertainty_score":0.8714912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02898435212249525,"score_gpt":0.3698599668566209,"score_spread":0.3408756147341256,"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."}}