{"id":"W4389397788","doi":"10.2196/53058","title":"Risk Prediction of Emergency Department Visits in Patients With Lung Cancer Using Machine Learning: Retrospective Observational Study","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Emergency department; Observational study; Lung cancer; Medicine; Retrospective cohort study; Emergency medicine; Medical emergency; Machine learning; Computer science; Medical physics; Artificial intelligence; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004723821,0.000126057,0.0002876149,0.0001548855,0.00007585944,0.000005580986,0.00008315994,0.00008482837,0.0002354856],"category_scores_gemma":[0.0002563969,0.00009527738,0.000040057,0.0008621481,0.0000266601,0.0002387439,0.00006696112,0.0004051163,0.000003816498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002886007,"about_ca_system_score_gemma":0.0002033708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003465211,"about_ca_topic_score_gemma":0.0001906462,"domain_scores_codex":[0.9973542,0.00004197241,0.0007095402,0.0001077807,0.00156061,0.0002259077],"domain_scores_gemma":[0.9991115,0.00002652331,0.0003111911,0.0001295735,0.0002724389,0.000148717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002419709,0.000215094,0.994401,0.0000945139,0.00009669133,0.000006273761,0.003024777,0.0009654412,0.000001346191,0.000006298115,0.0003355088,0.0006110307],"study_design_scores_gemma":[0.002367161,0.0007546087,0.8499331,0.0002594906,0.00007485737,9.064728e-7,0.0009862625,0.1454872,0.00000626061,0.000006937202,0.00005768838,0.00006548192],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984299,0.00003625633,0.0001517957,0.00004534048,0.0001475177,0.0009441757,0.0000748149,0.00005451516,0.0001157106],"genre_scores_gemma":[0.9992136,0.0000800419,0.0002843318,0.00005815602,0.00006383835,0.00007574827,0.000183396,0.00001041916,0.00003052199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1445218,"threshold_uncertainty_score":0.3885299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07593051275939339,"score_gpt":0.3799649813524105,"score_spread":0.3040344685930171,"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."}}