{"id":"W4410288395","doi":"10.2196/71873","title":"Advancing the Use of Longitudinal Electronic Health Records: Tutorial for Uncovering Real-World Evidence in Chronic Disease Outcomes","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"U.S. Food and Drug Administration; National Institute of Neurological Disorders and Stroke; U.S. Department of Health and Human Services","keywords":"Pipeline (software); Computer science; Scalability; Data science; Disease; Missing data; Health records; Sampling bias; Medicine; Clinical trial; MEDLINE; Machine learning; Data mining; Artificial intelligence; Sample size determination; Health care; Database","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01427737,0.0001506909,0.0006202441,0.0006686999,0.00005975375,0.000068253,0.001085016,0.00009227846,0.00007532288],"category_scores_gemma":[0.04390911,0.00009628944,0.0001914657,0.0006985422,0.0002612453,0.0004436399,0.0003797971,0.001832325,7.664192e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003155272,"about_ca_system_score_gemma":0.005389728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00132474,"about_ca_topic_score_gemma":0.01105778,"domain_scores_codex":[0.9949954,0.0006638991,0.001323629,0.0002230184,0.002041269,0.0007527894],"domain_scores_gemma":[0.9837747,0.01440337,0.0004893984,0.0003882913,0.0006710022,0.0002732631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.006963655,0.001290698,0.1590969,0.00612822,0.0007523671,0.0003490827,0.00137041,0.0007007967,0.0006609235,0.5132329,0.1860512,0.1234029],"study_design_scores_gemma":[0.003735498,0.005196658,0.02349992,0.04462655,0.0001193888,0.00003639198,0.0004145238,0.01660059,0.004102384,0.8426124,0.0585619,0.000493754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5893547,0.004865725,0.3523993,0.04906618,0.001601147,0.00249531,0.00001272995,0.0001062949,0.00009858495],"genre_scores_gemma":[0.987302,0.005189356,0.005765632,0.0001646301,0.0004817912,0.00007283699,7.564417e-7,0.00003254523,0.0009904684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3979473,"threshold_uncertainty_score":0.9641445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3515612282020164,"score_gpt":0.5739641170098899,"score_spread":0.2224028888078736,"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."}}