{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002598743,0.0001391876,0.000263468,0.00008977314,0.0001616207,0.00004975245,0.0003521667,0.0005469698,0.0001808066],"category_scores_gemma":[0.0009643425,0.0001155756,0.00009113106,0.000238504,0.0003389661,0.00001160253,0.0003758948,0.0009514039,0.0001707272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002449166,"about_ca_system_score_gemma":0.0002408896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002588476,"about_ca_topic_score_gemma":0.000006515243,"domain_scores_codex":[0.9976209,0.0002542737,0.0006983817,0.0001908189,0.0007743937,0.0004612559],"domain_scores_gemma":[0.9989368,0.0001863255,0.000155899,0.0002826361,0.0001699494,0.0002683746],"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":[0.0004964833,0.0006545386,0.1385676,0.001035658,0.0003410089,0.00002849144,0.004268924,0.001306802,0.007946796,0.0006066391,0.01574307,0.829004],"study_design_scores_gemma":[0.001697143,0.0007190036,0.00140806,0.0002372969,0.00001189115,0.00004614512,0.002122584,0.5683177,0.0007679071,0.0001120464,0.4242329,0.0003274263],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9864598,0.0003384533,0.01000913,0.0001807287,0.0003615298,0.0002386129,0.000003292979,0.00005245908,0.002356],"genre_scores_gemma":[0.9798218,0.0002332458,0.01748362,0.0009384595,0.0005355877,0.0000125105,0.0002110199,0.00002557561,0.0007381719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8286766,"threshold_uncertainty_score":0.4713037,"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."}}