{"id":"W3208971449","doi":"10.1136/oem-2021-epi.84","title":"O-467 Evaluating the impact of sex and gender on the performance of machine learning for auto encoding of job titles","year":2021,"lang":"en","type":"article","venue":"Oral Presentations","topic":"Healthcare Systems and Public Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Bespoke; Coding (social sciences); Artificial intelligence; Machine learning; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009213601,0.00004526956,0.0001502669,0.00003219137,0.0001115102,0.000005410675,0.00003294449,0.00002432722,0.0001033359],"category_scores_gemma":[0.0005702045,0.00002365289,0.00005157482,0.0001273947,0.00003797632,0.00003262157,0.00001643262,0.0001098678,4.897244e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001538873,"about_ca_system_score_gemma":0.0004157278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002056541,"about_ca_topic_score_gemma":0.00005038405,"domain_scores_codex":[0.9992393,0.000189827,0.0002437567,0.000070626,0.0001594383,0.00009701878],"domain_scores_gemma":[0.9989728,0.0005383455,0.0001228847,0.0001274206,0.0002007222,0.00003780994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001347277,0.0001331844,0.8830929,0.00245045,0.0002810635,0.000001013657,0.02083928,0.003372988,0.04744888,0.005324649,0.001938694,0.03498217],"study_design_scores_gemma":[0.001071986,0.001505583,0.6595696,0.0002627376,0.00007183867,0.00002614337,0.005823602,0.3262161,0.004556758,0.0002007907,0.0006162724,0.00007857465],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945951,0.0001931903,0.0001427057,0.001774017,0.00002638837,0.0003487997,0.00002086484,0.000004292974,0.002894606],"genre_scores_gemma":[0.9989053,0.00003858775,0.0002898285,0.0000434281,0.00004082302,0.00001469757,0.00001450559,0.000006369461,0.0006464305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3228431,"threshold_uncertainty_score":0.3108889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2198778754194947,"score_gpt":0.4890386529592827,"score_spread":0.2691607775397881,"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."}}