{"id":"W4312065018","doi":"10.2196/41200","title":"Identifying Patterns of Clinical Interest in Clinicians’ Treatment Preferences: Hypothesis-free Data Science Approach to Prioritizing Prescribing Outliers for Clinical Review","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute for Health and Care Research; National Institute for Health and Care Research Applied Research Collaboration Oxford and Thames Valley; Research for Patient Benefit Programme; Department of Health and Social Care; Wellcome Trust","keywords":"Outlier; Medical prescription; Ranking (information retrieval); Antipsychotic; Medicine; Set (abstract data type); Pharmacoepidemiology; Data mining; Computer science; Information retrieval; Psychiatry; Artificial intelligence; Schizophrenia (object-oriented programming); Pharmacology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2218326,0.001685138,0.003429068,0.01676866,0.001707116,0.00693295,0.005479556,0.004327977,0.003166746],"category_scores_gemma":[0.4618135,0.001500251,0.007082485,0.01202257,0.0035351,0.00425509,0.003870249,0.004514076,0.0008354054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003766771,"about_ca_system_score_gemma":0.007174406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005919153,"about_ca_topic_score_gemma":0.008010766,"domain_scores_codex":[0.7644675,0.1789022,0.01771329,0.02015608,0.01701594,0.00174504],"domain_scores_gemma":[0.2959046,0.6256456,0.03425567,0.02978745,0.01256061,0.001846055],"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":[0.002912447,0.001615885,0.502541,0.008671278,0.011873,0.002423427,0.007555164,0.0971005,0.004589524,0.04493247,0.02099497,0.2947903],"study_design_scores_gemma":[0.001302275,0.001782937,0.1297168,0.001398309,0.002157231,0.00111334,0.0042047,0.6463587,0.004641434,0.1869146,0.01992952,0.0004800433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1355235,0.002272851,0.830063,0.00916882,0.0002918794,0.006348461,0.01170224,0.001902977,0.002726339],"genre_scores_gemma":[0.5140668,0.0003301585,0.4711682,0.001638799,0.0002710927,0.005001768,0.006888262,0.00009407094,0.000540843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2218326,"threshold_uncertainty_score":0.959619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7306613394438053,"score_gpt":0.6003858122933607,"score_spread":0.1302755271504445,"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."}}