{"id":"W4400452265","doi":"10.1016/j.jtho.2024.05.332","title":"PP01.105 Early Detection of Non-Small Cell Lung Cancer using Electronic Health Record Data","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Medicine; Electronic health record; Lung cancer; Health records; Oncology; Health care","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":[0.003931178,0.0002289132,0.0003137941,0.003908878,0.000358572,0.001873894,0.0006444894,0.0007377618,0.07496881],"category_scores_gemma":[0.02364109,0.0002920704,0.000595095,0.003526735,0.0002142364,0.001494471,0.000778636,0.0006224568,0.02121231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007055686,"about_ca_system_score_gemma":0.001575348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00533064,"about_ca_topic_score_gemma":0.007109345,"domain_scores_codex":[0.9973641,0.001012589,0.0004356672,0.0002193394,0.0007887944,0.0001795424],"domain_scores_gemma":[0.9718755,0.01696226,0.003241208,0.001739453,0.004630886,0.001550692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008164054,0.000417202,0.3731649,0.001317077,0.0001871982,0.0003115461,0.0001287823,0.0002327795,0.001883914,0.001737018,0.2933853,0.3264178],"study_design_scores_gemma":[0.000286596,0.0005221145,0.8092328,0.001488372,0.0002359809,0.0008922948,0.0002907761,0.002837584,0.002543686,0.001396219,0.1802259,0.0000477444],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2413573,0.008452287,0.009408903,0.01907608,0.004744968,0.00205699,0.3941106,0.002785336,0.3180076],"genre_scores_gemma":[0.6865899,0.006042884,0.0238388,0.008098697,0.003634875,0.001163887,0.1981186,0.0005044934,0.07200789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07496881,"threshold_uncertainty_score":0.2507957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04065701268092965,"score_gpt":0.4495400011999616,"score_spread":0.408882988519032,"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."}}