{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001677184,0.00006291627,0.00006366583,0.00009712033,0.0003101401,0.0001926181,0.001354102,0.00005829983,0.000009834139],"category_scores_gemma":[0.002918534,0.00004408266,0.000009907376,0.0001395609,0.0003017668,0.0001356789,0.0003264351,0.0001182506,4.782805e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000023306,"about_ca_system_score_gemma":0.0001987629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009706811,"about_ca_topic_score_gemma":0.0003863524,"domain_scores_codex":[0.9985334,0.00005806819,0.0002231207,0.0003746303,0.0006213377,0.0001893981],"domain_scores_gemma":[0.9991875,0.00006047242,0.0001421443,0.0002933955,0.0002444504,0.00007202516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008290719,0.0001688028,0.2256471,0.000008936957,0.00004615661,0.000004939332,0.0003306653,0.00001714568,0.004768494,0.0006727137,0.0006891573,0.7668168],"study_design_scores_gemma":[0.01122682,0.00831286,0.4706706,0.0004681924,0.0001036149,0.0007897257,0.003101335,0.3325494,0.0007549329,0.007654773,0.1635051,0.0008625757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9269395,0.0000573099,0.07187184,0.0004535555,0.0004660875,0.0001403708,0.00005771201,0.000004257498,0.000009390525],"genre_scores_gemma":[0.9872242,0.00003470491,0.01010345,0.0001627197,0.0005497125,0.000003737943,0.001907949,0.00000593105,0.000007596117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7659542,"threshold_uncertainty_score":0.3493968,"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."}}