{"id":"W2739875050","doi":"10.2196/medinform.7140","title":"Triaging Patient Complaints: Monte Carlo Cross-Validation of Six Machine Learning Classifiers","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Medical Malpractice and Liability Issues","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cross-validation; Monte Carlo method; Computer science; Artificial intelligence; Machine learning; Statistics; Mathematics","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002585412,0.0001729591,0.0004845754,0.00008752196,0.001278417,0.00005549369,0.0005292648,0.0004044265,0.002240316],"category_scores_gemma":[0.01518542,0.0001318349,0.00009709498,0.00007801048,0.0004721636,0.0007502744,0.0003690067,0.001800866,0.0002448602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003412,"about_ca_system_score_gemma":0.0003201065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003534176,"about_ca_topic_score_gemma":0.00004125298,"domain_scores_codex":[0.9959804,0.0004067617,0.001705156,0.0001231797,0.001309283,0.0004752415],"domain_scores_gemma":[0.9954787,0.001444522,0.001651994,0.0006321177,0.0003059647,0.0004867302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006655452,0.0006184616,0.6886362,0.006168619,0.0002133219,0.00003455569,0.1692121,0.0001906398,0.00003419979,0.00305947,0.0200064,0.1111605],"study_design_scores_gemma":[0.006482631,0.0006540141,0.03235007,0.002825927,0.00009121247,0.000009155653,0.0600953,0.1200866,0.0002371597,0.0002783137,0.7763363,0.0005533276],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746222,0.00003971104,0.0004338557,0.004240557,0.0008998235,0.0007568502,0.00001927912,0.00008676616,0.01890095],"genre_scores_gemma":[0.9972401,0.00008437943,0.0006717447,0.00114144,0.0002215088,0.00008332774,0.00003921921,0.00001487194,0.0005034225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7563299,"threshold_uncertainty_score":0.9986718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08262412564591218,"score_gpt":0.4701145027362492,"score_spread":0.387490377090337,"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."}}