{"id":"W3111411783","doi":"10.23889/ijpds.v5i5.1637","title":"Deep Learning and NLP For Knowledge Extraction from Laboratory Reports","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Identifier; Natural language processing; Named-entity recognition; Parsing; Information extraction; Information retrieval; F1 score; Deep learning; Identification (biology); ENCODE; Task (project management); Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.003588066,0.001312878,0.0007460364,0.004344754,0.0008661774,0.002011879,0.00186586,0.001576304,0.004804558],"category_scores_gemma":[0.01218863,0.0006802516,0.001568293,0.003613613,0.0007987662,0.002085768,0.001882859,0.00220158,0.002044917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002351771,"about_ca_system_score_gemma":0.003234009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02096538,"about_ca_topic_score_gemma":0.01978827,"domain_scores_codex":[0.997335,0.0008698988,0.0003673522,0.0007151867,0.0005186656,0.0001937509],"domain_scores_gemma":[0.9918412,0.006186613,0.0004990875,0.0005354006,0.0008470928,0.00009069472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001513388,0.0002250297,0.003950492,0.0008469044,0.0001858826,0.0004620719,0.0002757436,0.1669276,0.005617655,0.007930282,0.0185766,0.7948504],"study_design_scores_gemma":[0.0000222553,0.00004485087,0.001109254,0.0001202044,0.00004188557,0.0001029752,0.00009649328,0.957621,0.008076314,0.02173463,0.01100606,0.00002398707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02066174,0.001370739,0.9502268,0.001669136,0.0001117935,0.0003912425,0.00874243,0.01400501,0.00282113],"genre_scores_gemma":[0.1915979,0.001086967,0.7820077,0.0005513033,0.0001100163,0.0007602284,0.02002103,0.0002672557,0.003597635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02096538,"threshold_uncertainty_score":0.04168665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05694203770010275,"score_gpt":0.3996541144822478,"score_spread":0.342712076782145,"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."}}