{"id":"W4414663910","doi":"10.1186/s12889-025-23960-1","title":"Testing regular expression searches and machine learning models to determine housing instability and low income status from primary care electronic medical record data in Toronto, Ontario","year":2025,"lang":"en","type":"article","venue":"BMC Public Health","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; North York General Hospital; University Health Network; University of Toronto; University of Calgary; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Biostatistics; Low income; Primary care; Public health; Electronic medical record; Epidemiology; Medical record; Electronic health record","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":[0.003526494,0.0003985541,0.0004607262,0.00105785,0.0009307265,0.0008869983,0.0009768277,0.000505493,0.0007633814],"category_scores_gemma":[0.01935184,0.0002684982,0.0004418639,0.002294178,0.0007542105,0.0004259506,0.0007766811,0.0003575302,0.0002881583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01278989,"about_ca_system_score_gemma":0.008594764,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9206822,"about_ca_topic_score_gemma":0.925974,"domain_scores_codex":[0.997068,0.0008673103,0.0003719635,0.0005580509,0.0006898518,0.0004449321],"domain_scores_gemma":[0.9852469,0.006819576,0.002302258,0.0008593728,0.004105937,0.0006659177],"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":[0.0003479267,0.00009426333,0.9783085,0.0001138634,0.00008493329,0.0001866042,0.001099654,0.003516701,0.0007363417,0.0001273668,0.001424832,0.01395907],"study_design_scores_gemma":[0.00003364187,0.0001082532,0.9672589,0.00003326535,0.00004188692,0.00008694505,0.001325101,0.0296079,0.0006450735,0.00007108223,0.0007733942,0.00001460431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964952,0.0001129777,0.0005132105,0.0001305355,0.000003734845,0.00006663369,0.002084839,0.00002306606,0.0005698039],"genre_scores_gemma":[0.9952973,0.00006177795,0.000992401,0.00003369717,0.00000454829,0.00003824845,0.003228814,0.000004347739,0.0003390243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07931781,"threshold_uncertainty_score":0.1595698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2952841740144811,"score_gpt":0.4323001316108341,"score_spread":0.137015957596353,"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."}}