{"id":"W4413334194","doi":"10.1101/2025.08.14.670178","title":"Genomic Characterization of Lung Cancer in Never-Smokers Using Deep Learning","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"National Institutes of Health; U.S. Department of Health and Human Services","keywords":"CDKN2A; KRAS; Receiver operating characteristic; Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Digital pathology; Computational biology; Pattern recognition (psychology); Biology; Cancer; Machine learning; Colorectal cancer; Genetics","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":[0.0003465934,0.000293553,0.0002139567,0.0007439276,0.0001008819,0.0004092808,0.0003230307,0.000289965,0.00070987],"category_scores_gemma":[0.0008198758,0.0001363584,0.0003001126,0.0002932313,0.0001166541,0.0002310121,0.0003185955,0.0003110544,0.0002476148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003350248,"about_ca_system_score_gemma":0.000238961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006529885,"about_ca_topic_score_gemma":0.01147099,"domain_scores_codex":[0.999896,0.000023388,0.000007339765,0.00004087964,0.0000174234,0.00001485181],"domain_scores_gemma":[0.9997444,0.0001051914,0.00004583221,0.00002774427,0.00005151,0.00002531619],"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":[0.0004520574,0.0001312288,0.8269855,0.00009422373,0.0001819705,0.000367279,0.00006198963,0.04033929,0.02951205,0.000329022,0.000964683,0.1005808],"study_design_scores_gemma":[0.00001784687,0.0001490941,0.3584872,0.00003930067,0.0001032003,0.0005141781,0.0001303201,0.6202306,0.01729672,0.001830442,0.00118009,0.00002112098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9762211,0.0007005416,0.0205537,0.000176916,0.0000111212,0.00002089112,0.001312092,0.0002407393,0.0007628066],"genre_scores_gemma":[0.9948546,0.0001031489,0.003509495,0.00003790227,0.000005740589,0.000008679926,0.001106941,0.000008316954,0.0003651358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006529885,"threshold_uncertainty_score":0.0129838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114366290867224,"score_gpt":0.2373101848453649,"score_spread":0.2258735557586425,"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."}}