{"id":"W4220689324","doi":"10.2196/33212","title":"Improving the Prediction of Persistent High Health Care Utilizers: Retrospective Analysis Using Ensemble Methodology","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Health care; Medicine; Retrospective cohort study; Observational study; Decision tree; Referral; Ensemble learning; Population; Random forest; Computer science; Machine learning; Statistics; Family medicine; Environmental health; Surgery; Mathematics; 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":[0.002372782,0.0001295661,0.0004239444,0.0002960042,0.0006162322,0.00003482965,0.001001818,0.00008672943,0.0001000178],"category_scores_gemma":[0.0004051565,0.00009937437,0.0002750848,0.001535084,0.0001094774,0.0002046103,0.0008878434,0.0009077319,0.000001156241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006606858,"about_ca_system_score_gemma":0.0007054269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001135517,"about_ca_topic_score_gemma":0.00003454312,"domain_scores_codex":[0.9962513,0.0009364001,0.0008571722,0.0001857345,0.001411486,0.0003578847],"domain_scores_gemma":[0.9978803,0.0003568213,0.0007171885,0.0006753964,0.0001858745,0.0001844417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006037537,0.0001997798,0.037474,0.001813504,0.001241557,0.00001517054,0.6383582,0.09864241,0.00003800974,0.02884426,0.001283447,0.1920293],"study_design_scores_gemma":[0.0002399409,0.0004675575,0.003031916,0.0000157591,0.00007406915,0.00003869114,0.02782127,0.9677436,0.00001262604,0.00008232083,0.0003927306,0.00007956394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2046974,0.0003561488,0.7905375,0.002567037,0.0007673931,0.0006231307,0.00004750046,0.0001669129,0.0002369641],"genre_scores_gemma":[0.9185237,0.00000950671,0.07983578,0.001480142,0.00005541497,0.00004798264,0.00002982155,0.000007047843,0.00001056109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8691012,"threshold_uncertainty_score":0.4739622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05789482117927493,"score_gpt":0.355619715336937,"score_spread":0.2977248941576621,"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."}}