{"id":"W4412991966","doi":"10.1148/radiol.243393","title":"External Testing of a Deep Learning Model for Lung Cancer Risk from Low-Dose Chest CT","year":2025,"lang":"en","type":"article","venue":"Radiology","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Medicine; Lung cancer; Lung cancer screening; Risk assessment; Lung; Radiology; Internal medicine","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":[0.00009451828,0.0001076302,0.0003602553,0.00005532372,0.00005929142,0.000003455602,0.00005545086,0.00005041285,0.0000341677],"category_scores_gemma":[0.0002381635,0.00008814681,0.00008812932,0.00007788936,0.00004468236,0.00001801358,0.00002352014,0.0001366809,7.972926e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002282291,"about_ca_system_score_gemma":0.0001434839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001278197,"about_ca_topic_score_gemma":0.0001584771,"domain_scores_codex":[0.9992708,0.00003485111,0.0002086423,0.000243759,0.00004990707,0.0001920689],"domain_scores_gemma":[0.9991273,0.0004946713,0.0001212012,0.0001457157,0.00006443037,0.00004670327],"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":[0.0001938766,0.0001022718,0.9183124,0.0001758042,0.0003840638,0.0000152569,0.0002465992,0.02178269,0.001735371,0.0001136393,0.0002827183,0.05665528],"study_design_scores_gemma":[0.003173925,0.0001675551,0.2358682,0.0004448467,0.0006650523,0.000009499924,0.00002316886,0.7571532,0.001809995,0.000451746,0.00015771,0.00007514287],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9616333,0.009566437,0.02750928,0.0003155738,0.0001890874,0.0003676169,0.00003829333,0.00003021419,0.000350213],"genre_scores_gemma":[0.9875343,0.0006412233,0.01093054,0.0001856586,0.0001568424,0.0002583882,0.00001826589,0.00001328842,0.0002615375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7353705,"threshold_uncertainty_score":0.3594523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01722028222474871,"score_gpt":0.3172603584521153,"score_spread":0.3000400762273666,"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."}}