{"id":"W7149220147","doi":"","title":"External Test of a Deep Learning Algorithm for Pulmonary Nodule Malignancy Risk Stratification Using European Screening Data","year":2025,"lang":"en","type":"article","venue":"Utrecht University Repository (Utrecht University)","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Malignancy; Lung cancer screening; Lung cancer; Nodule (geology); Cohort; Retrospective cohort study; National Lung Screening Trial","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002774381,0.0002382921,0.0003774985,0.0005072029,0.0006208452,0.00002590692,0.0005022179,0.0001303695,0.00002140741],"category_scores_gemma":[0.00005866192,0.0002796984,0.000188272,0.0006843315,0.0001416157,0.0003812669,0.0003319443,0.0002824345,0.000002377892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006159819,"about_ca_system_score_gemma":0.0002347343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007422746,"about_ca_topic_score_gemma":0.0000350069,"domain_scores_codex":[0.9982774,0.000243007,0.0002545572,0.0007159001,0.000227367,0.0002817744],"domain_scores_gemma":[0.9981263,0.0003008762,0.0003844436,0.0007733383,0.0002688382,0.0001462229],"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":[0.0007555137,0.001909937,0.3601508,0.0004726803,0.00142991,0.002525484,0.0004470044,0.0004919858,0.01232936,0.0007067515,0.0004706445,0.61831],"study_design_scores_gemma":[0.02671948,0.00269604,0.2923564,0.008432087,0.02021834,0.0006200536,0.02134309,0.3979682,0.06296732,0.000158924,0.1640549,0.00246524],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2042136,0.001338539,0.6667791,0.0003095396,0.0007531031,0.002093292,0.0005726003,0.0004497571,0.1234905],"genre_scores_gemma":[0.8922935,0.0005618869,0.07744901,0.00002294818,0.0001641084,5.069227e-7,0.0003269802,0.00004004451,0.02914101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6880799,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0219573970203677,"score_gpt":0.2460785800531629,"score_spread":0.2241211830327952,"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."}}