{"id":"W2616885684","doi":"10.1016/j.jbi.2017.05.016","title":"RysannMD: A biomedical semantic annotator balancing speed and accuracy","year":2017,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01947826,0.00243956,0.002981036,0.008073088,0.003225157,0.005273901,0.004955448,0.003994393,0.01028642],"category_scores_gemma":[0.04290352,0.001962349,0.002967441,0.004745724,0.001600245,0.01002051,0.01190121,0.002947562,0.009928339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002198685,"about_ca_system_score_gemma":0.005575289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009721412,"about_ca_topic_score_gemma":0.02140534,"domain_scores_codex":[0.9841541,0.0054273,0.001824756,0.003397265,0.004552616,0.000643843],"domain_scores_gemma":[0.971806,0.010242,0.0007163969,0.008883803,0.007486402,0.0008653994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00306669,0.0005225586,0.00770314,0.003199613,0.001128898,0.0006914394,0.001256603,0.01195872,0.03655978,0.01154899,0.1810997,0.7412639],"study_design_scores_gemma":[0.0007952513,0.0005082967,0.005963214,0.0008726725,0.0009743018,0.002434516,0.001762385,0.5374481,0.103911,0.04326585,0.3014982,0.0005661987],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02957716,0.002864253,0.7771882,0.002063992,0.001639383,0.0009861543,0.01557506,0.1603861,0.009719679],"genre_scores_gemma":[0.06631463,0.0007346321,0.8816465,0.001042593,0.000179585,0.000482533,0.02941391,0.009981706,0.01020388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01947826,"threshold_uncertainty_score":0.1030121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01770952006212118,"score_gpt":0.3075889200199805,"score_spread":0.2898793999578593,"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."}}