{"id":"W4388608496","doi":"10.1093/bioinformatics/btad684","title":"PiDeeL: metabolic pathway-informed deep learning model for survival analysis and pathological classification of gliomas","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Bilim Akademisi; Centre National de la Recherche Scientifique","keywords":"Computer science; Recall; Artificial intelligence; Deep learning; Machine learning; Pathological; Index (typography); Concordance; Mechanism (biology); Pathology; Bioinformatics; Medicine; Biology; Psychology; Cognitive psychology","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":[0.0003447884,0.0001334396,0.0004599213,0.0004676187,0.00008389546,0.00002118706,0.0000498738,0.0001013279,0.000006211352],"category_scores_gemma":[0.0003751903,0.00009688101,0.0001992787,0.000901105,0.00005517738,0.0001088558,0.00004011019,0.00006404948,0.00001337436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272308,"about_ca_system_score_gemma":0.00004724577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005392923,"about_ca_topic_score_gemma":0.00001825983,"domain_scores_codex":[0.9989196,0.00001524562,0.0004987787,0.0001111209,0.0002375215,0.0002177063],"domain_scores_gemma":[0.9991161,0.0002192302,0.0002216464,0.0001964536,0.0001389804,0.0001075686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005290868,0.0008144836,0.6079556,0.001808886,0.004101674,0.00003705256,0.01339422,0.01642377,0.007810008,0.03204059,0.0004387463,0.3146459],"study_design_scores_gemma":[0.001018977,0.0001343923,0.2069955,0.00001251885,0.0007859871,0.000004407113,0.0008685167,0.7887554,0.0009354422,0.0001338541,0.0002737988,0.00008114096],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9632984,0.000147659,0.03494935,0.0001933449,0.00003939685,0.0004961119,0.00004477534,0.0001229526,0.0007080249],"genre_scores_gemma":[0.9808732,0.0003705684,0.01815948,0.00003432123,0.0000174151,0.00008729293,0.0003818649,0.0000101917,0.00006565967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7723317,"threshold_uncertainty_score":0.3950693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06304541078609775,"score_gpt":0.3137776443325855,"score_spread":0.2507322335464877,"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."}}