{"id":"W4324020367","doi":"10.1007/s10729-022-09627-y","title":"Predicting drug shortages using pharmacy data and machine learning","year":2023,"lang":"en","type":"article","venue":"Health Care Management Science","topic":"Pharmaceutical Economics and Policy","field":"Economics, Econometrics and Finance","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Economic shortage; Pharmacy; Health informatics; Medicine; Drug; Business; Public health; Family medicine; Pharmacology; Nursing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002292125,0.0001199306,0.0002165712,0.0004585845,0.0007259886,0.0001920909,0.0006499522,0.00001179727,0.00004835664],"category_scores_gemma":[0.00008085339,0.0001442434,0.00002068858,0.0007978306,0.0001579876,0.0005199581,0.00122705,0.0001718282,0.0001261884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001668309,"about_ca_system_score_gemma":0.00004591427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007827184,"about_ca_topic_score_gemma":0.00004959796,"domain_scores_codex":[0.9981659,0.00001696905,0.0004363274,0.0007173092,0.00006950444,0.0005939988],"domain_scores_gemma":[0.9990895,0.0000453006,0.0002002019,0.0004121678,0.00001242463,0.0002403878],"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":[0.00001696039,0.00004385845,0.7919962,0.001156187,0.00006705413,0.00002719088,0.00616418,0.003913915,0.0000218328,0.1016654,0.00525037,0.08967689],"study_design_scores_gemma":[0.0003582947,0.00001275844,0.01064799,0.00002442696,0.000005049153,0.00000217556,0.000730815,0.6957733,0.000009473418,0.0007787334,0.2914624,0.0001945546],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9245591,0.0125589,0.001259318,0.01447737,0.001651141,0.00104878,0.0007947469,0.0004379231,0.0432128],"genre_scores_gemma":[0.991423,0.004809535,0.0008033138,0.002498214,0.0000960472,0.00000741846,0.00005314587,0.00001802767,0.0002913664],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7813482,"threshold_uncertainty_score":0.5882074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1761174851863908,"score_gpt":0.3976542399635269,"score_spread":0.2215367547771361,"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."}}