{"id":"W4412607413","doi":"10.1200/cci-24-00317","title":"Extraction of Social Determinants of Health From Electronic Health Records Using Natural Language Processing","year":2025,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of British Columbia, Okanagan Campus; Kelowna General Hospital","funders":"","keywords":"Pipeline (software); Benchmark (surveying); Artificial intelligence; Computer science; Social determinants of health; Natural language processing; Machine learning; Social media; Medicine; Public health; World Wide Web; Nursing; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.00233106,0.0001365989,0.0008191482,0.0001507915,0.000814872,0.000006436323,0.0001876329,0.0002720407,0.000106594],"category_scores_gemma":[0.0003568967,0.0001308533,0.0001282689,0.0004071717,0.0001076321,0.0002946689,0.00009578124,0.001156223,0.000005490483],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006227693,"about_ca_system_score_gemma":0.006187282,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008792192,"about_ca_topic_score_gemma":0.007159193,"domain_scores_codex":[0.994856,0.0005255929,0.003643101,0.0001298602,0.0002828664,0.0005625886],"domain_scores_gemma":[0.9957598,0.0005523631,0.003135115,0.0002011558,0.0002624628,0.00008912075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005129447,0.0003396349,0.3016067,0.01235301,0.00009452325,3.408711e-7,0.08109049,0.00008656915,0.000009226183,0.001560323,0.006812966,0.5955333],"study_design_scores_gemma":[0.006189071,0.0008041984,0.7013214,0.008539153,0.0001987064,0.000001053466,0.08693454,0.1557204,0.00004794464,0.002217636,0.03742087,0.000605117],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890333,0.004274319,0.001284142,0.001617314,0.002096436,0.0008596958,0.0002401886,0.00005243429,0.0005421509],"genre_scores_gemma":[0.9925395,0.0007068535,0.002740115,0.003542742,0.0002493538,0.0000231988,0.00005617203,0.00001130199,0.0001307643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5949282,"threshold_uncertainty_score":0.9994467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2724807600125266,"score_gpt":0.6235776239800963,"score_spread":0.3510968639675697,"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."}}