{"id":"W4412468874","doi":"10.3389/fphys.2025.1549306","title":"Prediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence","year":2025,"lang":"en","type":"article","venue":"Frontiers in Physiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Interpretability; Machine learning; Random forest; Gradient boosting; Decision tree; Artificial intelligence; Computer science; Naive Bayes classifier; Support vector machine; Boosting (machine learning)","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":[0.001687202,0.0008050246,0.0005014132,0.0009565655,0.0002301586,0.001143754,0.0007351611,0.0005002119,0.001056121],"category_scores_gemma":[0.005815709,0.0002936768,0.0009632999,0.0004425162,0.0002993751,0.000858112,0.0007000873,0.001172752,0.0003172873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007186486,"about_ca_system_score_gemma":0.001014948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004068663,"about_ca_topic_score_gemma":0.003978873,"domain_scores_codex":[0.9994732,0.0002012424,0.00002910802,0.0001463703,0.0001141176,0.00003599898],"domain_scores_gemma":[0.9979886,0.001346374,0.0002402861,0.0001109989,0.0002708773,0.00004280334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002091402,0.0003452554,0.05216595,0.0002013492,0.0003618577,0.0001843747,0.0002642819,0.7992075,0.004029069,0.006739671,0.001237326,0.1350542],"study_design_scores_gemma":[0.000004985233,0.00004127265,0.002466968,0.00001437625,0.00002631691,0.00001924821,0.00001340148,0.9943975,0.0004687541,0.002270645,0.0002694353,0.000007212188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1838521,0.0002566134,0.8120534,0.0006311082,0.00004816159,0.00009676204,0.0003621372,0.0008757347,0.001823896],"genre_scores_gemma":[0.8495427,0.0001586231,0.1482447,0.0001522429,0.00004274914,0.0001546973,0.0005827086,0.0000444119,0.001077182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004068663,"threshold_uncertainty_score":0.008922875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08546961578532303,"score_gpt":0.3738796469523352,"score_spread":0.2884100311670122,"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."}}