{"id":"W2508981042","doi":"10.17294/2330-0698.1401","title":"Identifying Race/Ethnicity Data via Natural Language Processing Among Women in a Uterine Fibroid Cohort Study","year":2016,"lang":"en","type":"article","venue":"Journal of patient-centered research and reviews","topic":"Uterine Myomas and Treatments","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Care Foundation","funders":"","keywords":"Uterine fibroids; Medicine; Retrospective cohort study; Ethnic group; Cohort; Gynecology; Race (biology); Obstetrics; Incidence (geometry); Cohort study; Internal medicine","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":[0.006676631,0.0002894772,0.0003716725,0.002449846,0.0009534059,0.001576454,0.000855246,0.0005976965,0.002243035],"category_scores_gemma":[0.02016526,0.0003450461,0.0007581508,0.001788878,0.0003541999,0.0006642403,0.001509415,0.001061473,0.001000866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008310573,"about_ca_system_score_gemma":0.001546983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02486362,"about_ca_topic_score_gemma":0.03298976,"domain_scores_codex":[0.9963301,0.001223299,0.0006738275,0.0009769385,0.0005806702,0.0002151993],"domain_scores_gemma":[0.991269,0.003860741,0.001889508,0.001266755,0.001303562,0.0004104221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004793495,0.0004394882,0.9602905,0.0002512308,0.0001543902,0.0008983022,0.003438653,0.0002751324,0.001819431,0.0005246626,0.01175062,0.0196783],"study_design_scores_gemma":[0.0001978203,0.0002440691,0.9580665,0.0002992449,0.0001814796,0.0008010676,0.005318861,0.006136828,0.001362759,0.001167262,0.02613476,0.00008931583],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9121795,0.0002991979,0.007472145,0.00136432,0.0000641507,0.002153833,0.07360581,0.0002192896,0.002641707],"genre_scores_gemma":[0.853532,0.0003714177,0.03450572,0.001962837,0.0001228356,0.006617648,0.1004596,0.0001448116,0.00228318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02486362,"threshold_uncertainty_score":0.04943782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1110683950026089,"score_gpt":0.4367853823513775,"score_spread":0.3257169873487686,"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."}}