{"id":"W7117673507","doi":"10.1186/s13293-025-00783-8","title":"When algorithms infer gender: revisiting computational phenotyping with electronic health records data","year":2025,"lang":"en","type":"article","venue":"Biology of Sex Differences","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Women's and Gender Studies et Recherches Féministes; York University; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Health records; Electronic health record; Visibility; Computational model; Narrative review; Narrative; Health data; Ethical issues","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007900612,0.0001559194,0.0003688126,0.0001565623,0.0002099911,0.00004035082,0.001447991,0.00007820383,0.00001786322],"category_scores_gemma":[0.00009813312,0.0001215417,0.00002160262,0.0002766234,0.0001285033,0.0001585566,0.0005330951,0.0003245491,0.000002752315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004654004,"about_ca_system_score_gemma":0.0008128739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008518726,"about_ca_topic_score_gemma":0.00009292078,"domain_scores_codex":[0.9979872,0.0004124836,0.0004024726,0.0006154273,0.0001456016,0.000436878],"domain_scores_gemma":[0.9984425,0.0004790711,0.0002878368,0.000629733,0.000104051,0.00005684312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009185678,0.00002465657,0.3621189,0.0001956727,0.00007419884,6.864912e-7,0.0007610345,0.0001297923,0.000005505613,0.09219122,0.0001537695,0.5443354],"study_design_scores_gemma":[0.000652448,0.0006264883,0.2936818,0.0004197656,0.00001466927,0.00001788554,0.000250498,0.5983843,0.00001610345,0.09933355,0.006202931,0.0003995225],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05573907,0.002902616,0.9319764,0.008161678,0.000219628,0.0002349103,0.00001944659,0.0001473522,0.0005989348],"genre_scores_gemma":[0.8986456,0.00009182653,0.1002343,0.0007915939,0.0000778237,0.00000750709,0.00009600836,0.000005069541,0.00005019527],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8429066,"threshold_uncertainty_score":0.4956326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05595663651318956,"score_gpt":0.3468136480850986,"score_spread":0.2908570115719091,"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."}}