{"id":"W2905107612","doi":"10.1101/488924","title":"Identifying and Interpreting Subgroups in Health Care Utilization Data with Count Mixture Regression Models","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"Covariate; Negative binomial distribution; Statistics; Count data; Bayesian probability; Econometrics; Poisson regression; Skewness; Mixture model; Overdispersion; Regression analysis; Dispersion (optics); Health care; Binomial regression; Medicine; Logistic regression; Mathematics; Poisson distribution; Environmental health; Economics; Population","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001873864,0.0005809051,0.0006767795,0.0003812036,0.0002446742,0.0007286575,0.001990032,0.0004584296,0.000002389751],"category_scores_gemma":[0.00009474012,0.0005114734,0.0000430833,0.0006395503,0.0001144449,0.001095802,0.003092661,0.0008947194,0.000001929908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000337955,"about_ca_system_score_gemma":0.000845104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001568764,"about_ca_topic_score_gemma":0.00004431034,"domain_scores_codex":[0.9956324,0.0005092174,0.0006689172,0.002056421,0.0005198968,0.0006131421],"domain_scores_gemma":[0.9954819,0.00007010924,0.0006808249,0.00307106,0.0004262463,0.0002698293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002108898,0.00316372,0.09430775,0.08887825,0.002532176,0.003143113,0.0468416,0.004164047,0.2252646,0.4949464,0.01740101,0.01724847],"study_design_scores_gemma":[0.002051404,0.0003487222,0.01455003,0.02507177,0.0001120771,6.391697e-7,0.00007439354,0.9317011,0.01931578,0.0008425762,0.002504475,0.003427084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03273634,0.007914382,0.9572575,0.0003317393,0.0006717103,0.000702691,0.00009605308,0.000278922,0.00001067868],"genre_scores_gemma":[0.5900568,0.0005325157,0.4089234,0.0002666908,0.0001264542,0.00003320833,0.000001626013,0.00005847227,8.488495e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.927537,"threshold_uncertainty_score":0.9997337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04202427194684579,"score_gpt":0.2964048170238687,"score_spread":0.254380545077023,"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."}}