{"id":"W4411727957","doi":"10.1371/journal.pone.0310937","title":"Machine learning for the prediction of spontaneous preterm birth using early second and third trimester maternal blood gene expression: A cautionary tale","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Preterm Birth and Chorioamnionitis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Langara College; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Overfitting; Logistic regression; Random forest; Medicine; Generalizability theory; Cohort; Machine learning; Artificial intelligence; Receiver operating characteristic; Pregnancy; Obstetrics; Artificial neural network; Statistics; Computer science; Internal medicine; Biology; Genetics; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02494967,0.001384679,0.002107638,0.001514044,0.0007751686,0.003833472,0.002242689,0.002080957,0.001228544],"category_scores_gemma":[0.0607222,0.0004778017,0.00217976,0.001588426,0.001481997,0.002357301,0.001517597,0.01093624,0.001527998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007397591,"about_ca_system_score_gemma":0.001899714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007053492,"about_ca_topic_score_gemma":0.008610544,"domain_scores_codex":[0.9916987,0.005637018,0.0007117532,0.0009516625,0.0008482407,0.0001526114],"domain_scores_gemma":[0.9750737,0.01858795,0.000866856,0.002657238,0.00244713,0.0003670464],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002316199,0.0005409888,0.1410149,0.002442618,0.005545068,0.001585478,0.001274083,0.07984712,0.007149274,0.01379336,0.1534164,0.5910745],"study_design_scores_gemma":[0.0005648619,0.001808007,0.05975953,0.004909267,0.001493092,0.001762256,0.001474345,0.657438,0.007379028,0.1594692,0.1033139,0.0006284859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1142437,0.1534683,0.4545169,0.2487535,0.01355888,0.000551107,0.004843768,0.003625328,0.006438571],"genre_scores_gemma":[0.6117335,0.03830178,0.2773657,0.04804904,0.0120174,0.0008303819,0.004171401,0.0008144451,0.00671629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9750503,"threshold_uncertainty_score":0.1319481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02153096589754806,"score_gpt":0.2247163385807517,"score_spread":0.2031853726832036,"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."}}