{"id":"W4414343060","doi":"10.1101/2025.09.10.25335531","title":"Comparing Missing Data Imputation Methods for Patient-Reported Outcomes in Esophageal Cancer Research","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Esophageal Cancer Research and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Wilfrid Laurier University; McGill University Health Centre","funders":"","keywords":"Missing data; Imputation (statistics); Esophageal cancer; Principal component analysis; Data quality; Bayesian probability","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1491608,0.0008197629,0.001532689,0.001281201,0.0007586942,0.002240698,0.002968025,0.00158076,0.003635108],"category_scores_gemma":[0.3117657,0.0005740747,0.003323402,0.00234011,0.001229036,0.002344192,0.002480112,0.004038275,0.0007909351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001318499,"about_ca_system_score_gemma":0.003575332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00391928,"about_ca_topic_score_gemma":0.003602987,"domain_scores_codex":[0.9171606,0.0725815,0.003067322,0.003331155,0.00324321,0.0006161821],"domain_scores_gemma":[0.6188413,0.3337297,0.01060642,0.02328857,0.01224114,0.001292945],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008982704,0.001096854,0.1787988,0.002779728,0.009167807,0.0002284943,0.002146883,0.2551171,0.001137358,0.04621463,0.02216157,0.4721682],"study_design_scores_gemma":[0.001393111,0.00167698,0.03645828,0.001830543,0.00140991,0.000330324,0.0007264489,0.8401182,0.004176693,0.09976216,0.01191948,0.0001977825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1484852,0.005490229,0.8315413,0.005761752,0.0006383173,0.0008136263,0.004131412,0.0009999976,0.00213812],"genre_scores_gemma":[0.5642228,0.001583593,0.4234169,0.001200406,0.0002570969,0.001938245,0.00566578,0.0004063736,0.001308736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8508392,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2784053719694035,"score_gpt":0.5504951168616604,"score_spread":0.2720897448922569,"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."}}