{"id":"W4225004662","doi":"10.1038/s41598-022-10887-5","title":"Automatic assessment of adverse drug reaction reports with interactive visual exploration","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Peking University","keywords":"Computer science; Workflow; Visualization; Multinomial logistic regression; Task (project management); Causality (physics); Adverse drug reaction; Logistic regression; Data mining; Artificial intelligence; Machine learning; Medicine; Database; Drug","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":[0.001884896,0.000112826,0.0001718093,0.000338052,0.0004221554,0.000151742,0.000206457,0.00001376085,0.0001221381],"category_scores_gemma":[0.00006753251,0.000101845,0.00005773347,0.00125315,0.00007972507,0.001742407,0.0003190389,0.000122633,0.000002591413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001707531,"about_ca_system_score_gemma":0.0004340142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000281629,"about_ca_topic_score_gemma":0.00001313816,"domain_scores_codex":[0.9972077,0.0001359673,0.0006593742,0.0006794544,0.001154525,0.000162953],"domain_scores_gemma":[0.9974973,0.00003043652,0.001181974,0.000944449,0.0002718981,0.00007398816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001150215,0.01475401,0.1083387,0.0009444578,0.001131882,0.02945412,0.07133076,0.1422685,0.2016487,0.05624359,0.2649539,0.1088165],"study_design_scores_gemma":[0.0002798476,0.0002726989,0.004883972,0.00008664846,0.00005542925,0.001782621,0.003849282,0.9406935,0.01237086,0.006335569,0.02892663,0.0004629184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6028582,0.00001075648,0.3827345,0.0003711598,0.009974161,0.0006730545,0.000004459107,0.0003596925,0.003013954],"genre_scores_gemma":[0.9924337,5.825576e-7,0.005849717,0.00003701247,0.00001513618,0.00004655019,0.0001757553,0.000008567958,0.001433018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7984251,"threshold_uncertainty_score":0.4153117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01705600346696524,"score_gpt":0.3193992264424932,"score_spread":0.302343222975528,"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."}}