{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004572367,0.00005396253,0.00005718129,0.00003730866,0.0001969225,0.0001222464,0.0003084708,0.00004834423,0.00000692],"category_scores_gemma":[0.002931899,0.00004863757,0.00002026386,0.00005879502,0.00008709534,0.00004848188,0.0001512586,0.00007187476,7.025639e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001446616,"about_ca_system_score_gemma":0.00007189826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000962652,"about_ca_topic_score_gemma":0.00001505704,"domain_scores_codex":[0.9992391,0.00001483109,0.0001901362,0.0002894059,0.0001718416,0.00009463413],"domain_scores_gemma":[0.9993221,0.00004708431,0.0001639254,0.00009259525,0.000280133,0.00009414079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003460696,0.0000688136,0.05723875,0.00001630986,0.00009917764,0.00001294183,0.0003478669,0.00028586,0.5016909,0.0002622091,0.008623272,0.4310078],"study_design_scores_gemma":[0.0006870447,0.0002945171,0.03017663,0.00002728638,0.00002442812,0.00009492485,0.0003361513,0.0568925,0.00918052,0.0007609674,0.9013183,0.0002067953],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6340051,0.001414323,0.3590494,0.002394623,0.002663779,0.000171108,0.0002159965,0.00002539567,0.00006025976],"genre_scores_gemma":[0.9754405,0.0001045299,0.02251496,0.0001811757,0.0009812129,0.000004567175,0.0007248207,0.00000575286,0.00004249812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.892695,"threshold_uncertainty_score":0.3509969,"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."}}