{"id":"W4404368553","doi":"10.1016/j.jeph.2024.202791","title":"Extracting social determinants of health from inpatient electronic medical records using natural language processing","year":2024,"lang":"en","type":"article","venue":"Journal of Epidemiology and Population Health","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"South Health Campus; University of Calgary; Alberta Health Services","funders":"Canadian Institutes of Health Research","keywords":"Health records; Medical record; Natural language processing; Electronic health record; Natural (archaeology); Data science; Psychology; Computer science; Medicine; Geography; Political science; Health care","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006927446,0.00100992,0.0006930524,0.01032378,0.000602124,0.001932567,0.0008947073,0.0007202231,0.001214421],"category_scores_gemma":[0.0341532,0.0003465082,0.001522796,0.00398312,0.0004552628,0.00126538,0.001807958,0.0008641865,0.0006785085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009524495,"about_ca_system_score_gemma":0.002925632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007447667,"about_ca_topic_score_gemma":0.01029107,"domain_scores_codex":[0.9941443,0.002175702,0.001567144,0.00101457,0.0008979361,0.0002003532],"domain_scores_gemma":[0.9498851,0.03683725,0.006831463,0.002148363,0.003855336,0.0004424802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006166159,0.0009071684,0.5416142,0.003674582,0.0007140664,0.00222142,0.003737007,0.009064234,0.01073089,0.002691029,0.01594492,0.4080837],"study_design_scores_gemma":[0.0003893368,0.0009238532,0.6399162,0.001945581,0.0008977315,0.002972385,0.009723808,0.2466159,0.01484627,0.03647977,0.04493103,0.000358101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5956181,0.003416529,0.2598025,0.004802188,0.0003490943,0.005749344,0.1205943,0.003870464,0.005797477],"genre_scores_gemma":[0.5446544,0.0009513249,0.3713386,0.0007079632,0.0003673101,0.002495329,0.07866511,0.00007605922,0.000743825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01032378,"threshold_uncertainty_score":0.03663629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2551996765807935,"score_gpt":0.5727994810308287,"score_spread":0.3175998044500352,"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."}}