{"id":"W2990610567","doi":"10.3233/shti190538","title":"Development of a Method for Extracting Structured Dose Information from Free-Text Electronic Prescriptions","year":2019,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Pharmacy and Medical Practices","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Parsing; Medical prescription; Computer science; Text messaging; Set (abstract data type); Natural language processing; Information retrieval; Artificial intelligence; Data mining; Programming language; Medicine; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.001890082,0.000168513,0.0004426585,0.0004059745,0.0002874035,0.000006253923,0.000251327,0.0003287234,0.00006246079],"category_scores_gemma":[0.001149464,0.0001507236,0.00003114605,0.0003408241,0.0002080977,0.000691568,0.0002088573,0.001006912,0.00001071934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001361365,"about_ca_system_score_gemma":0.0003300002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001263405,"about_ca_topic_score_gemma":0.00004850797,"domain_scores_codex":[0.9979099,0.0001127976,0.001264142,0.0001101265,0.0001173378,0.0004857086],"domain_scores_gemma":[0.9977736,0.001074448,0.0007720158,0.000187466,0.0001174208,0.00007504429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009377727,0.0002201155,0.005701808,0.004688006,0.0009044294,7.515285e-7,0.07370694,0.0002437515,0.002056828,0.05159015,0.003310682,0.8566388],"study_design_scores_gemma":[0.004955568,0.0002985968,0.001101597,0.0001933031,0.00007237477,0.00001488796,0.03372,0.01863277,0.006673709,0.02341596,0.9106537,0.0002676006],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9607862,0.009370193,0.01891891,0.005076933,0.001854926,0.002483419,0.0001393257,0.000167805,0.001202306],"genre_scores_gemma":[0.8370132,0.004325293,0.1547671,0.003504917,0.00003963515,0.0002519213,0.00005345015,0.0000097786,0.00003478784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.907343,"threshold_uncertainty_score":0.6146331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1543424342733283,"score_gpt":0.5228502546413673,"score_spread":0.368507820368039,"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."}}