{"id":"W4387963398","doi":"10.1093/jamia/ocad205","title":"Systematic replication of smoking disease associations using survey responses and EHR data in the <i>All of Us</i> Research Program","year":2023,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Phenome; Bonferroni correction; Biobank; Replication (statistics); Meta-analysis; Medicine; MEDLINE; Disease; Bioinformatics; Phenotype; Internal medicine; Biology; Genetics; Statistics","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1904694,0.00248996,0.004651906,0.00452509,0.002218071,0.004900369,0.003857881,0.002793902,0.00253298],"category_scores_gemma":[0.3728645,0.002410163,0.01801067,0.007652223,0.003067862,0.002036315,0.00439187,0.002252331,0.0007007692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001597407,"about_ca_system_score_gemma":0.005884228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008822761,"about_ca_topic_score_gemma":0.01250526,"domain_scores_codex":[0.752613,0.1787109,0.03140293,0.02247853,0.01202522,0.002769426],"domain_scores_gemma":[0.6501516,0.1639581,0.03375747,0.1243395,0.02605884,0.00173449],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006283794,0.0004251921,0.5132008,0.02360917,0.3885576,0.0008913674,0.002338794,0.003117329,0.008040584,0.003836864,0.008260942,0.04143758],"study_design_scores_gemma":[0.006928229,0.005171461,0.5084708,0.0105219,0.4177311,0.001218956,0.001070597,0.00419049,0.007732548,0.009464282,0.0271068,0.0003929418],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4788124,0.1291438,0.2998403,0.008524648,0.006368789,0.01835562,0.0410203,0.002046444,0.01588771],"genre_scores_gemma":[0.9192508,0.004689851,0.05288165,0.002823306,0.000483794,0.00943957,0.009380976,0.0003921883,0.0006577785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8095306,"threshold_uncertainty_score":0.9982953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1401989339252414,"score_gpt":0.4433557366599765,"score_spread":0.3031568027347351,"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."}}