{"id":"W4416916393","doi":"10.21203/rs.3.rs-8237827/v1","title":"Machine Learning Prediction of Child Stunting and Wasting in Ethiopia Using DHS Data: XGBoost and Random Forest Models with SHAP Interpretability","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Child Nutrition and Water Access","field":"Nursing","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Wasting; Random forest; Interpretability; Malnutrition; Underweight; Overfitting; Sample (material); Logistic regression","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":[0.002654843,0.0006405049,0.0006647681,0.001236991,0.0002987563,0.0008712723,0.001054518,0.0007757277,0.001209818],"category_scores_gemma":[0.003227086,0.0003519829,0.0008973064,0.001037989,0.0002901177,0.0007201947,0.0003844504,0.0009650472,0.0003545131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001183733,"about_ca_system_score_gemma":0.0008616692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07002481,"about_ca_topic_score_gemma":0.04437489,"domain_scores_codex":[0.9995542,0.0002234118,0.00002256592,0.0000842295,0.00002171906,0.00009390039],"domain_scores_gemma":[0.9976298,0.001748587,0.0001825723,0.0000864802,0.0002063085,0.0001463033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006255623,0.0006100301,0.5852239,0.0001695699,0.0004632239,0.0002945084,0.0002331436,0.3710041,0.0005996148,0.001489562,0.003151254,0.03613537],"study_design_scores_gemma":[0.00002964247,0.00008474843,0.1394862,0.00006949861,0.00008427622,0.00005108988,0.0006593841,0.8572838,0.0005529056,0.001164561,0.0005042148,0.00002964389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909924,0.0003278279,0.0049091,0.0003384153,0.00002843619,0.00002464903,0.002923721,0.00004822779,0.0004071202],"genre_scores_gemma":[0.9942582,0.0001409044,0.002721388,0.00001702502,0.00001572661,0.00001707463,0.002438508,0.000006440736,0.0003846781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07002481,"threshold_uncertainty_score":0.1392345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1007032123112351,"score_gpt":0.3865983652189083,"score_spread":0.2858951529076732,"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."}}