{"id":"W4416218296","doi":"10.2196/79307","title":"Methods for Addressing Missingness in Electronic Health Record Data for Clinical Prediction Models: Comparative Evaluation","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute","keywords":"Missing data; Imputation (statistics); Health records; Electronic health record; Predictive modelling; Data collection","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1795837,0.002524815,0.002533902,0.005527207,0.000946584,0.00273711,0.004100562,0.00283832,0.001834082],"category_scores_gemma":[0.3269346,0.001090069,0.004695878,0.004619181,0.001293283,0.005849068,0.003299042,0.003322973,0.0005276466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003112498,"about_ca_system_score_gemma":0.004332516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009080918,"about_ca_topic_score_gemma":0.00708499,"domain_scores_codex":[0.9084851,0.07292374,0.005038353,0.004109091,0.008889643,0.0005540954],"domain_scores_gemma":[0.384764,0.5756481,0.01134904,0.01136608,0.01545769,0.00141508],"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":[0.008998381,0.002487386,0.1045929,0.005864627,0.01172852,0.0001278761,0.001173594,0.1947841,0.0005243283,0.005830306,0.009478383,0.6544096],"study_design_scores_gemma":[0.001521283,0.003375515,0.02968843,0.002654155,0.002636123,0.0002805661,0.0005325475,0.9433571,0.001247358,0.01065065,0.003805214,0.000250992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3423387,0.06378683,0.5668902,0.007815753,0.001400387,0.002819656,0.005602994,0.004076993,0.005268483],"genre_scores_gemma":[0.6125889,0.01437039,0.3632909,0.0009561105,0.0006184492,0.001796648,0.005373623,0.0004089045,0.0005959423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8204163,"threshold_uncertainty_score":0.9497406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4341752573016447,"score_gpt":0.6180766846296293,"score_spread":0.1839014273279845,"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."}}