{"id":"W3137754773","doi":"10.1186/s12874-021-01242-9","title":"Waist circumference prediction for epidemiological research using gradient boosted trees","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Physical Activity and Health","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of New Brunswick; University of Toronto","funders":"Carolina Population Center, University of North Carolina at Chapel Hill; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Diabetes and Digestive and Kidney Diseases; Fogarty International Center; China-Japan Friendship Hospital; University of North Carolina at Chapel Hill; National Institutes of Health","keywords":"Waist; Circumference; Gradient boosting; Body mass index; Statistics; Linear regression; Mean squared error; Regression analysis; Predictive modelling; Regression; Decision tree; Medicine; Linear model; Mathematics; Demography; Artificial intelligence; Machine learning; Computer science; Random forest; Internal medicine","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06631733,0.0001916827,0.001248072,0.0004109494,0.0006784354,0.00002434442,0.0003567919,0.0007494841,0.0007926889],"category_scores_gemma":[0.3802235,0.000144569,0.0002684432,0.001266634,0.001932323,0.00008408347,0.000455334,0.003148345,0.00004830879],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000501474,"about_ca_system_score_gemma":0.005874541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000449677,"about_ca_topic_score_gemma":0.0006878828,"domain_scores_codex":[0.9635244,0.03031812,0.0007430713,0.001044896,0.002545076,0.001824418],"domain_scores_gemma":[0.8550749,0.1403873,0.000084188,0.0007143119,0.001972578,0.001766645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01421569,0.01135987,0.05584132,0.006405942,0.0005540492,0.001791149,0.001805687,0.00005743107,0.3053221,0.2535904,0.03665856,0.3123977],"study_design_scores_gemma":[0.01314131,0.01862903,0.2310639,0.003012682,0.0002297008,0.002407355,0.004426778,0.1567416,0.03477362,0.4370944,0.09763832,0.0008412773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6391985,0.001132145,0.3418073,0.01409046,0.0004554642,0.001308252,0.00004437727,0.00009831472,0.001865178],"genre_scores_gemma":[0.8275908,0.001544032,0.1649445,0.001108812,0.002845102,0.0005023595,0.0001777882,0.00005296772,0.001233616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3139062,"threshold_uncertainty_score":0.9997612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.934710567356231,"score_gpt":0.687416148352609,"score_spread":0.247294419003622,"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."}}