{"id":"W2809472587","doi":"10.1093/annweh/wxy052","title":"Development of a Coding and Crosswalk Tool for Occupations and Industries","year":2018,"lang":"en","type":"article","venue":"Annals of Work Exposures and Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Cancer Research Society","keywords":"Schema crosswalk; Coding (social sciences); Computer science; Population; Statistics; Medicine; Engineering; Mathematics; Transport engineering; Environmental health","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.02786721,0.001724142,0.001287427,0.01305303,0.001784677,0.001924609,0.002581373,0.0007310121,0.01885184],"category_scores_gemma":[0.09173719,0.001179789,0.001820856,0.009968608,0.001087187,0.002622415,0.004037058,0.001806957,0.006759537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004406035,"about_ca_system_score_gemma":0.01514022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03003846,"about_ca_topic_score_gemma":0.03935364,"domain_scores_codex":[0.9772345,0.008248706,0.005621678,0.002188238,0.006013224,0.0006935963],"domain_scores_gemma":[0.9044195,0.03643792,0.007865614,0.008101164,0.04125883,0.001916952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008242223,0.000567238,0.03614896,0.002931097,0.0001435466,0.000569684,0.01376504,0.004027926,0.008929661,0.008360711,0.1333991,0.7903328],"study_design_scores_gemma":[0.0008160782,0.001319879,0.1532461,0.005392487,0.0002761585,0.002130369,0.01794255,0.07588643,0.03978185,0.02049373,0.6814237,0.0012907],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07170764,0.0005230236,0.8085079,0.00136058,0.0009746603,0.04479395,0.03791236,0.018483,0.01573687],"genre_scores_gemma":[0.03658367,0.000267706,0.913061,0.00019833,0.00008281726,0.02595368,0.01662859,0.001399653,0.005824524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03003846,"threshold_uncertainty_score":0.1473777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.170146835240855,"score_gpt":0.4260737662538271,"score_spread":0.2559269310129721,"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."}}