{"id":"W4415020928","doi":"10.1186/s12916-025-04289-3","title":"Early detection of non-small cell lung cancer: an electronic health record data-driven approach","year":2025,"lang":"en","type":"article","venue":"BMC Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"National Cancer Institute; National Institutes of Health","keywords":"Electronic health record; Lung cancer; Health records; Baseline (sea); Personalized medicine; Lung; Precision 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":[0.001203637,0.0001627472,0.0003927324,0.0002472337,0.0001341928,0.0000170104,0.001551605,0.00007639133,0.000009677457],"category_scores_gemma":[0.000101683,0.0001408764,0.00002666873,0.000783171,0.0000467341,0.0002004077,0.0003020234,0.0004913912,0.000001684545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002282392,"about_ca_system_score_gemma":0.001206552,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01988456,"about_ca_topic_score_gemma":0.003963636,"domain_scores_codex":[0.9976943,0.0003578992,0.0004957714,0.0007028728,0.0002887736,0.0004603509],"domain_scores_gemma":[0.9976481,0.0001468197,0.000312216,0.0016279,0.0001116216,0.0001533289],"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":[0.0001481634,0.0003513312,0.3563683,0.007997314,0.00008862015,0.000004305005,0.007801967,0.005936984,0.002609323,0.005361443,0.00442359,0.6089087],"study_design_scores_gemma":[0.0007392251,0.0007708728,0.06742524,0.0002635298,0.00001985241,0.000002962125,0.00007583178,0.9288062,0.0001135877,0.0001014479,0.001560876,0.000120403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1204835,0.002506506,0.8730235,0.001827648,0.0006454189,0.0005742296,0.000004108925,0.0001413594,0.000793751],"genre_scores_gemma":[0.9612013,0.0003065222,0.03714852,0.0006247555,0.0002742589,0.00004662782,0.00003602024,0.00001506798,0.0003469829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9228692,"threshold_uncertainty_score":0.9866421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0309205552597578,"score_gpt":0.3379229165506682,"score_spread":0.3070023612909104,"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."}}