{"id":"W4416679389","doi":"10.1186/s12889-025-25621-9","title":"Machine learning vs. traditional logistic regression: predictive performance and risk factor identification for child nutritional outcome in Pakistan","year":2025,"lang":"en","type":"article","venue":"BMC Public Health","topic":"Child Nutrition and Water Access","field":"Nursing","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Interpretability; Logistic regression; Underweight; Malnutrition; Public health; Biostatistics; Identification (biology); Wasting","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":[0.008894448,0.0007482857,0.0004735827,0.001281605,0.0004291481,0.001151627,0.0006853614,0.0004591387,0.0014788],"category_scores_gemma":[0.02600477,0.0002388191,0.001026226,0.001250546,0.0005525919,0.001218742,0.001033206,0.001841853,0.000408464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008838127,"about_ca_system_score_gemma":0.001605098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03062069,"about_ca_topic_score_gemma":0.01424132,"domain_scores_codex":[0.9978372,0.001257625,0.0001080202,0.0004038782,0.0002104284,0.0001828176],"domain_scores_gemma":[0.9869835,0.009990058,0.001197862,0.0006472634,0.0008585615,0.0003227681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000317995,0.00009015411,0.9291707,0.0000917771,0.0002086457,0.0001418533,0.0003108972,0.01892308,0.00009842715,0.001196527,0.001599078,0.04785083],"study_design_scores_gemma":[0.00007459083,0.0004275998,0.4698312,0.0002871459,0.0003183245,0.0003153296,0.001496857,0.515229,0.0007540716,0.008368819,0.002813738,0.00008322827],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740268,0.001490713,0.01722149,0.003027689,0.00009647034,0.0000567008,0.001634982,0.0001448087,0.00230036],"genre_scores_gemma":[0.9955716,0.000360832,0.003009997,0.0001016003,0.00004211577,0.00002268598,0.000691643,0.000008196249,0.0001912495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03062069,"threshold_uncertainty_score":0.06088495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07411555351052472,"score_gpt":0.3650312997247877,"score_spread":0.290915746214263,"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."}}