{"id":"W7117414157","doi":"10.64898/2025.12.23.25342921","title":"A novel open access multimodal dataset of nodule imaging and circulating proteome from a lung cancer screening cohort","year":2025,"lang":"","type":"article","venue":"medRxiv","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute","funders":"European Social Fund; Agencia Estatal de Investigación; European Regional Development Fund; HORIZON EUROPE Framework Programme; European Commission; Centro de Investigación Biomédica en Red de Cáncer; Ministerio de Ciencia e Innovación","keywords":"Lung cancer screening; Lung cancer; Biomarker; Proteomics; Radiomics; Cancer; Cohort; National Lung Screening Trial; Proteome","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":[0.00116317,0.0009178419,0.001135445,0.002318523,0.0004923818,0.001282357,0.00154391,0.001699281,0.002905674],"category_scores_gemma":[0.003652343,0.0002806634,0.0009128124,0.001892077,0.0004184298,0.0005452501,0.002027689,0.0007365524,0.002457517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006532425,"about_ca_system_score_gemma":0.0009229207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007090938,"about_ca_topic_score_gemma":0.01036049,"domain_scores_codex":[0.9987846,0.0001862579,0.0001240957,0.0005210677,0.0002337726,0.0001502992],"domain_scores_gemma":[0.9980579,0.0005425851,0.0003127737,0.000457458,0.00034913,0.0002802055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0052836,0.001365506,0.44994,0.004288021,0.001676517,0.004943219,0.0005912108,0.0127534,0.03719354,0.001954706,0.3600697,0.1199406],"study_design_scores_gemma":[0.000642887,0.0008687959,0.6932687,0.0007624896,0.0007290904,0.005735678,0.000694489,0.02604491,0.01176224,0.003876132,0.2553574,0.0002573396],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1561874,0.002372603,0.006173579,0.0007947731,0.0001344107,0.0002257543,0.8304327,0.001555253,0.002123463],"genre_scores_gemma":[0.07642228,0.0004223604,0.004534239,0.0002969778,0.00008182544,0.0003359303,0.9171247,0.00006319695,0.0007185181],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.007090938,"threshold_uncertainty_score":0.0140993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03716891817487041,"score_gpt":0.4006811923261161,"score_spread":0.3635122741512457,"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."}}