{"id":"W1980988016","doi":"10.1016/j.compbiomed.2014.07.005","title":"Identifying high-cost patients using data mining techniques and a small set of non-trivial attributes","year":2014,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Health Information; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CHAID; Computer science; Machine learning; Health care; Artificial neural network; Percentile; Artificial intelligence; Data mining; Predictive modelling; Decision tree; Population; Classifier (UML); Medical record; Statistics; Medicine; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009627708,0.0001241129,0.0003402661,0.0002190229,0.00008243652,0.00001102386,0.0005953459,0.0001093087,8.229537e-7],"category_scores_gemma":[0.0002609566,0.0001021867,0.00000777189,0.0001926852,0.0002280326,0.0001081562,0.00100922,0.0001903225,1.39496e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001523743,"about_ca_system_score_gemma":0.00002011638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003975868,"about_ca_topic_score_gemma":0.00003245196,"domain_scores_codex":[0.9987298,0.0002166578,0.0003249451,0.0004437166,0.00006980941,0.0002150914],"domain_scores_gemma":[0.998733,0.0005196629,0.000171646,0.0004494368,0.00005472224,0.00007154316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000139477,0.00001503364,0.673377,0.0001629944,0.00001115172,0.00000501096,0.00111885,0.000006176596,0.0003195715,0.001420108,0.0001407668,0.3234094],"study_design_scores_gemma":[0.003946532,0.001674824,0.4117692,0.002270101,0.0000331525,0.0001011145,0.00007558585,0.5718367,0.0004479186,0.003895965,0.003467449,0.0004814843],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5965714,0.0002209208,0.4017712,0.000740564,0.0004792158,0.0001603479,0.000006014609,0.00003445231,0.00001588406],"genre_scores_gemma":[0.8054414,0.0000644212,0.1939536,0.0002771129,0.0001880984,0.000002376395,0.00006720353,0.000004657627,0.000001093301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5718305,"threshold_uncertainty_score":0.4167053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09254185859295516,"score_gpt":0.3903684077473535,"score_spread":0.2978265491543984,"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."}}