{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058569,0.0006519687,0.000840669,0.00340797,0.0002825896,0.001673151,0.001140716,0.000806638,0.0004463894],"category_scores_gemma":[0.01354826,0.000320341,0.0008774094,0.002292922,0.0001971282,0.001333231,0.0009005402,0.0009244049,0.0002765813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008382765,"about_ca_system_score_gemma":0.001255891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004223059,"about_ca_topic_score_gemma":0.004924421,"domain_scores_codex":[0.9972795,0.001403025,0.0002324722,0.0004475612,0.000538144,0.00009936906],"domain_scores_gemma":[0.9915164,0.004904454,0.00114432,0.0005649516,0.001641922,0.0002281067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003698063,0.001062954,0.4506977,0.0007450841,0.0006636993,0.0005599149,0.0003622951,0.05973399,0.004956847,0.002311666,0.005272317,0.4732637],"study_design_scores_gemma":[0.00006252636,0.0004586935,0.1069919,0.0003294765,0.0003936291,0.0006892592,0.0004784147,0.871035,0.006604516,0.007902415,0.004973519,0.00008060697],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3872592,0.003614353,0.5860407,0.007287949,0.0001610959,0.001637078,0.008381474,0.001805594,0.003812421],"genre_scores_gemma":[0.815084,0.001021847,0.1775765,0.0006761876,0.0001227072,0.0002807793,0.004750422,0.00003341956,0.0004541034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0058569,"threshold_uncertainty_score":0.03097463,"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."}}