{"id":"W2891337205","doi":"10.23889/ijpds.v3i4.761","title":"Using Biomedical Text as Data and Representation Learning for Identifying Patients with an Osteoarthritis Phenotype in the Electronic Medical Record","year":2018,"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":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Identification (biology); Supervised learning; Population; Support vector machine; Random forest; Representation (politics); Natural language processing; Medicine; Artificial neural network; Biology","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":[0.003593421,0.0007346793,0.0005031584,0.003150915,0.0004560276,0.001664973,0.001075892,0.00119272,0.002433714],"category_scores_gemma":[0.02078318,0.0002346677,0.0005861354,0.002360942,0.0005629071,0.002123738,0.00121157,0.001019084,0.001250068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008140291,"about_ca_system_score_gemma":0.000793689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003223587,"about_ca_topic_score_gemma":0.003018,"domain_scores_codex":[0.9968987,0.001727075,0.000317249,0.0005796373,0.00034823,0.0001291737],"domain_scores_gemma":[0.986075,0.01060478,0.001007326,0.0009924661,0.001124053,0.0001964387],"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":[0.0009279,0.00155855,0.1101125,0.0008719882,0.0002170039,0.0005497856,0.0007158203,0.06025038,0.01101549,0.00397703,0.01868148,0.791122],"study_design_scores_gemma":[0.0001511792,0.0006214684,0.04145075,0.0002585359,0.0001505332,0.0004384732,0.0007820182,0.9062381,0.02163248,0.01725496,0.01091879,0.0001027623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6869894,0.002304911,0.2773513,0.005695672,0.0003102378,0.000681464,0.01700716,0.004583323,0.005076618],"genre_scores_gemma":[0.7413803,0.0005475289,0.23673,0.0004364667,0.0002198464,0.0004108514,0.01859206,0.00006264977,0.001620263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003593421,"threshold_uncertainty_score":0.01900405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09758331678051675,"score_gpt":0.4400322389705772,"score_spread":0.3424489221900605,"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."}}