{"id":"W4311829616","doi":"10.1371/journal.pdig.0000152","title":"Large-scale application of named entity recognition to biomedicine and epidemiology","year":2022,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Public Health Ontario; University of Toronto","funders":"Institute of Health Services and Policy Research; Canadian Institutes of Health Research; University of Toronto","keywords":"Named-entity recognition; Computer science; Biomedicine; Inference; Data science; Parsing; Artificial intelligence; Declaration; Python (programming language); Machine learning; Bioinformatics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009712396,0.00007667679,0.0002572565,0.0001562139,0.0001864658,0.0000114831,0.0002694746,0.0000239825,0.00001133145],"category_scores_gemma":[0.0003413816,0.00007863848,0.0000218522,0.0004601841,0.00002827591,0.0001615259,0.0003844278,0.0001960044,0.00001561734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001158526,"about_ca_system_score_gemma":0.00009622353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000262522,"about_ca_topic_score_gemma":0.00003899145,"domain_scores_codex":[0.998477,0.0002514969,0.0004066603,0.0003654002,0.0002065,0.0002929528],"domain_scores_gemma":[0.9988584,0.000319151,0.0002270911,0.0003166173,0.00006055469,0.0002182139],"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":[0.0000491288,0.0006268809,0.2530206,0.0009146314,0.00001683342,0.000002106423,0.005550978,0.00008504948,0.00007095413,0.009399732,0.001417678,0.7288454],"study_design_scores_gemma":[0.002332114,0.008763832,0.3323435,0.0002626235,0.00001405733,0.0001713494,0.00169903,0.502292,0.0001470578,0.08282439,0.06826526,0.000884848],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5835989,0.0004549348,0.3735828,0.04011989,0.0002280424,0.0009936719,0.0002504372,0.0002147427,0.0005567151],"genre_scores_gemma":[0.9881001,0.0000149934,0.008268559,0.003322866,0.0000402165,0.00009942388,0.0001179999,0.000007382169,0.00002847719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7279606,"threshold_uncertainty_score":0.3206784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04028945877442753,"score_gpt":0.3309893893826754,"score_spread":0.2906999306082479,"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."}}