{"id":"W4402194648","doi":"10.1111/1475-6773.14376","title":"Addressing immortal time bias in precision medicine: Practical guidance and methods development","year":2024,"lang":"en","type":"article","venue":"Health Services Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Terry Fox Research Institute; Genome British Columbia; Genome Canada","keywords":"Precision medicine; Pooling; Imputation (statistics); Missing data; Computer science; Data mining; Matching (statistics); Statistics; Sample size determination; Population; Personalized medicine; Selection bias; Econometrics; Machine learning; Medicine; Artificial intelligence; Mathematics; Bioinformatics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01506529,0.0001699676,0.0003836739,0.0005268616,0.0001938554,0.0001064115,0.0002187797,0.0001340137,0.0001887644],"category_scores_gemma":[0.001174155,0.0001309922,0.00001584597,0.0008997202,0.0001465505,0.0003813475,0.00035868,0.0009183553,0.00004568239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003557661,"about_ca_system_score_gemma":0.0005922209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003406717,"about_ca_topic_score_gemma":0.0003278283,"domain_scores_codex":[0.9958004,0.001391649,0.0007255766,0.0005133905,0.0008870899,0.000681948],"domain_scores_gemma":[0.9926118,0.006489182,0.0001169792,0.0003349694,0.000206341,0.0002407746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001753251,0.0002307552,0.0008800868,0.01656875,0.00004280137,0.0002749344,0.03625248,0.000002263773,0.005041029,0.04393914,0.004886022,0.8917064],"study_design_scores_gemma":[0.0008837827,0.00114558,0.0094438,0.03820982,0.00001526626,0.0002493469,0.006187302,0.09459383,0.0140673,0.7691149,0.06523123,0.0008578465],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4805264,0.0908068,0.3266072,0.04874162,0.000952834,0.01118033,0.00003098906,0.003848167,0.03730563],"genre_scores_gemma":[0.07389297,0.0007327411,0.9241136,0.0003165339,0.0001344244,0.0002061181,0.00001084007,0.00006202401,0.0005307829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8908486,"threshold_uncertainty_score":0.5341707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6727635142755471,"score_gpt":0.6964341676211453,"score_spread":0.02367065334559815,"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."}}