{"id":"W4412440867","doi":"10.1016/j.csbj.2025.07.010","title":"Comparative analysis of machine learning techniques in metabolomic-based preterm birth prediction","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Preterm Birth and Chorioamnionitis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Children's Hospital Foundation; Children's Hospital Foundation","keywords":"Artificial intelligence; Linear discriminant analysis; Machine learning; Receiver operating characteristic; Resampling; Logistic regression; Computer science; Artificial neural network; Metabolomics; Discriminative model; Mathematics; Biology; Bioinformatics","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":[0.009498724,0.001007296,0.0008146779,0.003139118,0.0002993645,0.001150245,0.0005607663,0.0007596311,0.0007683028],"category_scores_gemma":[0.01425275,0.0001664646,0.001332401,0.001406811,0.0003150832,0.0006716208,0.0008182945,0.0008817519,0.0003283197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007001731,"about_ca_system_score_gemma":0.0006989031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001987943,"about_ca_topic_score_gemma":0.00162358,"domain_scores_codex":[0.9972495,0.001764128,0.0001758502,0.0003349232,0.0003735139,0.0001020377],"domain_scores_gemma":[0.9859902,0.01186105,0.0006219774,0.0003842269,0.0009873305,0.0001552805],"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":[0.003031454,0.0007394923,0.2295243,0.0006845085,0.002327665,0.0002054585,0.0002441235,0.2269087,0.005850249,0.001496054,0.00183681,0.5271512],"study_design_scores_gemma":[0.00006067765,0.001314266,0.06113681,0.0001130328,0.0004406139,0.000181969,0.0001402764,0.9289851,0.004215303,0.00234773,0.001013873,0.00005037281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.809785,0.01156186,0.1713462,0.001282728,0.0001583922,0.0002358788,0.001159199,0.0009933389,0.003477372],"genre_scores_gemma":[0.9493027,0.001508401,0.04786974,0.0001021267,0.00007656516,0.0001213794,0.0006308508,0.00004878917,0.0003395309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009498724,"threshold_uncertainty_score":0.05023468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008851696021391742,"score_gpt":0.2759640531147327,"score_spread":0.267112357093341,"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."}}