{"id":"W4394996333","doi":"10.2196/53091","title":"Use of Machine Learning for Early Detection of Maternal Cardiovascular Conditions: Retrospective Study Using Electronic Health Record Data","year":2024,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Cardiovascular Issues in Pregnancy","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Medicine; Pregnancy; Retrospective cohort study; Electronic health record; Health records; Health care; Medical emergency; Intensive care medicine; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00137323,0.0002219224,0.001162544,0.0003102582,0.0000962384,0.00004257093,0.0001691018,0.00009541911,0.00001020223],"category_scores_gemma":[0.0001940045,0.0002197711,0.001068686,0.0004798341,0.00006951096,0.0003251699,0.0001686897,0.0004625059,0.000002984986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005616105,"about_ca_system_score_gemma":0.0002566745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001674569,"about_ca_topic_score_gemma":0.00008255821,"domain_scores_codex":[0.9973876,0.0003308205,0.0005624191,0.000659947,0.0006902014,0.0003690462],"domain_scores_gemma":[0.9979885,0.00007224473,0.0001477501,0.001452526,0.0002597636,0.00007924671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001590479,0.0007598982,0.6684355,0.006905256,0.08950911,0.000683892,0.005323226,0.005351292,0.01563368,0.0002098639,0.0002962798,0.2053015],"study_design_scores_gemma":[0.0114817,0.01224425,0.806004,0.007043471,0.0198308,0.004277719,0.001429022,0.05121194,0.01451281,0.0004057071,0.07009079,0.001467765],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9461107,0.02620132,0.02366467,0.00001123254,0.0005460184,0.003044418,0.000246308,0.00014021,0.00003507276],"genre_scores_gemma":[0.9976582,0.0008537208,0.0007116373,0.00000470537,0.0003235167,0.0001343114,0.0001167203,0.00008698423,0.0001101827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2038338,"threshold_uncertainty_score":0.8962007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04866509182188834,"score_gpt":0.3423277797517992,"score_spread":0.2936626879299109,"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."}}