{"id":"W4416702308","doi":"10.1016/j.ajcnut.2025.101126","title":"AI and machine learning in nutrition: the promise, the challenge, and recommendations","year":2025,"lang":"en","type":"article","venue":"American Journal of Clinical Nutrition","topic":"Nutrition, Genetics, and Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Heart, Lung, and Blood Institute; DOD Prostate Cancer Research Program; Office of the Assistant Secretary for Health; National Cancer Institute; National Institutes of Health; Bristol-Myers Squibb; U.S. Department of Veterans Affairs; AstraZeneca; U.S. Department of Agriculture; Advanced Research Projects Agency for Health","keywords":"Feature (linguistics); Active learning (machine learning); Training set; Support vector machine; Applications of artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0007274461,0.00008209088,0.0002009909,0.0000553463,0.0001287222,0.00003334611,0.000108032,0.00005286894,0.000006096145],"category_scores_gemma":[0.0004039384,0.00005476452,0.00008886582,0.0001301769,0.0003974834,0.000008238612,0.0000466185,0.0003143726,2.525115e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005580292,"about_ca_system_score_gemma":0.00005913855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008541173,"about_ca_topic_score_gemma":0.00003605507,"domain_scores_codex":[0.9987416,0.0003978225,0.0005263734,0.0001524856,0.0000802541,0.0001015048],"domain_scores_gemma":[0.9992164,0.0002013704,0.0002432562,0.0001246184,0.0001432344,0.00007113711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.006690704,0.006782201,0.1268931,0.0005293585,0.000484463,0.00002693854,0.0004023128,0.00003310365,0.005156574,0.002222704,0.05091969,0.7998589],"study_design_scores_gemma":[0.01987406,0.007070818,0.104705,0.001289165,0.0003189577,0.0001863697,0.004341766,0.0006374,0.001877662,0.02926291,0.8299478,0.0004880806],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8085452,0.02294582,0.0009974734,0.1666065,0.0002308626,0.0004068403,0.0000192563,0.00000555342,0.0002425019],"genre_scores_gemma":[0.928641,0.06818507,0.0005066755,0.002186354,0.0003914043,0.00002127979,0.00002037817,0.000005799431,0.00004204187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7993708,"threshold_uncertainty_score":0.2233232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076465878069513,"score_gpt":0.3555869223286267,"score_spread":0.3348222635479315,"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."}}