{"id":"W3190523902","doi":"10.1093/jamia/ocab124","title":"Application of natural language processing techniques to identify off-label drug usage from various online health communities","year":2021,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Pharmaceutical studies and practices","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bristol-Myers Squibb Canada","keywords":"Drug; Spelling; Recall; Computer science; Multi-label classification; Off-label use; Parsing; Variety (cybernetics); Medicine; Natural language processing; Artificial intelligence; Psychology; Pharmacology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00147351,0.00008482557,0.0004598904,0.00005726989,0.0001173636,0.00003162317,0.0002258667,0.00003759771,0.00001534799],"category_scores_gemma":[0.001518336,0.00005578003,0.0000916313,0.0004099621,0.00007551324,0.000188609,0.0001464401,0.0007114502,0.000001728677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003485529,"about_ca_system_score_gemma":0.0003779807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000660222,"about_ca_topic_score_gemma":0.0002046063,"domain_scores_codex":[0.9976398,0.0002114725,0.0008695802,0.00003460338,0.001089503,0.000155055],"domain_scores_gemma":[0.9960917,0.0005632014,0.00255665,0.0001443644,0.0004884198,0.0001557011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001091398,0.000405377,0.009898383,0.0001667685,0.0002861212,0.00000485285,0.01813899,0.000004934547,0.001196136,0.000007918964,0.004808066,0.9649733],"study_design_scores_gemma":[0.007441887,0.001781931,0.3881896,0.006337855,0.002080742,0.0006295936,0.3049483,0.1410209,0.02017357,0.0006283327,0.1258297,0.000937659],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9563823,0.002045526,0.003353431,0.03767876,0.0001503268,0.0001717629,0.00003188592,0.00001641825,0.0001695991],"genre_scores_gemma":[0.9703208,0.001453961,0.01189614,0.01603165,0.000211732,0.000002059896,0.00002706514,0.000007533346,0.00004902275],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9640356,"threshold_uncertainty_score":0.3090937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02667827383308776,"score_gpt":0.4245203176132349,"score_spread":0.3978420437801472,"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."}}