{"id":"W4410206549","doi":"10.1289/ehp15034","title":"A Machine Learning–Based Clustering Analysis to Explore Bisphenol A and Phthalate Exposure from Medical Devices in Infants with Congenital Heart Defects","year":2025,"lang":"en","type":"article","venue":"Environmental Health Perspectives","topic":"Effects and risks of endocrine disrupting chemicals","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Centre for Disease Control","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Phthalate; Cluster analysis; Medicine; Bisphenol A; Computer science; Bioinformatics; Machine learning; Biology; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001276166,0.0006221858,0.000628678,0.004412201,0.0006699411,0.0007497919,0.0006926378,0.0006500506,0.0008486204],"category_scores_gemma":[0.002986301,0.0001452088,0.001342728,0.002217983,0.0002390212,0.0003759172,0.0005456305,0.000419362,0.0003037085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008821751,"about_ca_system_score_gemma":0.001015501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009012219,"about_ca_topic_score_gemma":0.007985599,"domain_scores_codex":[0.9991585,0.0001814568,0.0001100154,0.000253727,0.0001942602,0.0001019611],"domain_scores_gemma":[0.9983577,0.0004985249,0.0003898354,0.0001182529,0.0005451603,0.00009045733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009954604,0.001052452,0.6905683,0.0003787816,0.00101969,0.0007169705,0.000737465,0.0462223,0.02644652,0.0009171469,0.003114336,0.2278306],"study_design_scores_gemma":[0.00004253999,0.0006536087,0.5791661,0.00007943629,0.0004019285,0.001080186,0.001075272,0.4021367,0.01077412,0.001368352,0.003111254,0.0001105082],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9226873,0.0005787808,0.07238034,0.0002203403,0.00004097204,0.000387642,0.00173492,0.0004487438,0.001520986],"genre_scores_gemma":[0.9436341,0.0001868322,0.05334527,0.00003956255,0.00001696256,0.0002138107,0.001994926,0.00002792608,0.0005405674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009012219,"threshold_uncertainty_score":0.01791954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009614272189054699,"score_gpt":0.3250912505980159,"score_spread":0.3154769784089612,"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."}}