{"id":"W4292940196","doi":"10.21203/rs.3.rs-1871614/v1","title":"SARS-CoV-2 Genomic Contextual Data Harmonization: Recommendations from a Mixed Methods Analysis of COVID-19 Case Report Forms Across Canada","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Genome British Columbia; Genome Canada","keywords":"Harmonization; Pandemic; Identification (biology); Data sharing; Data science; Standardization; Data integration; Data collection; Public health; Coronavirus disease 2019 (COVID-19); Computer science; Data mining; Medicine; Infectious disease (medical specialty); Disease; Biology; Pathology; Sociology","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3898045,0.002060736,0.003898238,0.008015925,0.005282426,0.0141821,0.01160849,0.003501136,0.007672639],"category_scores_gemma":[0.6439328,0.002890654,0.008491909,0.01672855,0.003743346,0.005341001,0.01077858,0.005470559,0.001563378],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0373038,"about_ca_system_score_gemma":0.2416403,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8891878,"about_ca_topic_score_gemma":0.8931863,"domain_scores_codex":[0.5871235,0.3255443,0.03052832,0.01308922,0.03573349,0.007981109],"domain_scores_gemma":[0.3568724,0.2945492,0.02523236,0.06462241,0.2485562,0.01016748],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.003648025,0.0005425944,0.3383839,0.008370473,0.0100577,0.000221378,0.02100408,0.01271779,0.001535768,0.01997848,0.2998337,0.2837061],"study_design_scores_gemma":[0.002965997,0.0008857203,0.5228695,0.03375348,0.01076807,0.0003166961,0.02500604,0.03817642,0.005556361,0.02546412,0.3334101,0.000827468],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1173846,0.01570581,0.3633788,0.2117876,0.003931002,0.04771317,0.2040069,0.003232725,0.03285949],"genre_scores_gemma":[0.270458,0.00351875,0.5893911,0.02976961,0.0007262723,0.03014633,0.06978168,0.002032302,0.004176018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9626962,"threshold_uncertainty_score":0.7524798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2568860167304794,"score_gpt":0.5453981565113779,"score_spread":0.2885121397808985,"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."}}