{"id":"W2996406085","doi":"10.2196/16042","title":"Clinical Annotation Research Kit (CLARK): Computable Phenotyping Using Machine Learning","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences","keywords":"Machine learning; Artificial intelligence; Computer science; Naive Bayes classifier; Random forest; Support vector machine; Annotation; Decision tree; Classifier (UML); Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007237319,0.002185035,0.0009919835,0.00410626,0.0005895085,0.003138305,0.003204175,0.001980473,0.08670174],"category_scores_gemma":[0.04900406,0.001628339,0.001221672,0.002844274,0.0008329799,0.004166969,0.005125122,0.002060146,0.04545108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001136419,"about_ca_system_score_gemma":0.002975045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002494696,"about_ca_topic_score_gemma":0.003402713,"domain_scores_codex":[0.9953826,0.001427318,0.0008201441,0.0009942917,0.001195422,0.0001802472],"domain_scores_gemma":[0.9651573,0.02432819,0.001991792,0.003381414,0.00435942,0.0007817512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006953849,0.000103052,0.003520281,0.002589238,0.0001075302,0.0008787623,0.0009573688,0.001553109,0.004239918,0.01501366,0.7655603,0.2047814],"study_design_scores_gemma":[0.0007279264,0.0002412449,0.005848011,0.001347977,0.0001171351,0.002187309,0.0003929414,0.02388412,0.01836248,0.04790633,0.8986735,0.0003110179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.006186851,0.0009192278,0.3949597,0.004539446,0.0007547917,0.001900384,0.1168622,0.4445314,0.02934594],"genre_scores_gemma":[0.04643003,0.001266348,0.6821088,0.005544532,0.0003568432,0.005463832,0.1648245,0.05844589,0.03555918],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.08670174,"threshold_uncertainty_score":0.2900463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08154325136589928,"score_gpt":0.4319228986456122,"score_spread":0.3503796472797129,"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."}}