{"id":"W2994804941","doi":"10.1016/j.jbi.2019.103354","title":"Task definition, annotated dataset, and supervised natural language processing models for symptom extraction from unstructured clinical notes","year":2019,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Coreference; Computer science; Natural language processing; Artificial intelligence; Named-entity recognition; Recall; Normalization (sociology); Task (project management); Automatic summarization; Information extraction; Annotation; Relationship extraction; Precision and recall; F1 score; Language model; Machine learning; Information retrieval; Resolution (logic)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003301329,0.001742153,0.0009471321,0.002731182,0.001180159,0.002008478,0.002121819,0.002147415,0.002924205],"category_scores_gemma":[0.01356602,0.0004001189,0.001703828,0.001648763,0.000708093,0.001962462,0.00213453,0.002005868,0.002164474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001485804,"about_ca_system_score_gemma":0.004565425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0103012,"about_ca_topic_score_gemma":0.02097226,"domain_scores_codex":[0.9970374,0.0009123593,0.0005652491,0.0008148383,0.0004130024,0.0002571237],"domain_scores_gemma":[0.9896534,0.006076212,0.0006555925,0.001256019,0.001894748,0.0004640321],"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":[0.005138321,0.006114213,0.07726279,0.007903213,0.0006919591,0.005690359,0.002841172,0.04283653,0.09588261,0.008917147,0.2674797,0.4792419],"study_design_scores_gemma":[0.001540966,0.002919276,0.07315045,0.001553276,0.001046283,0.006484872,0.005811511,0.6664075,0.09636255,0.02493174,0.1192373,0.0005544084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4539118,0.003044044,0.2623986,0.004928858,0.0009944143,0.006657233,0.239453,0.02013449,0.008477667],"genre_scores_gemma":[0.3471557,0.0005193243,0.2410778,0.0009217741,0.0002372386,0.003553272,0.402903,0.0004577143,0.003174219],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0103012,"threshold_uncertainty_score":0.02048248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03168750268367153,"score_gpt":0.350800854451614,"score_spread":0.3191133517679424,"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."}}