{"id":"W4405803587","doi":"10.2196/66094","title":"Applications of Natural Language Processing and Large Language Models for Social Determinants of Health: Protocol for a Systematic Review","year":2024,"lang":"en","type":"review","venue":"JMIR Research Protocols","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Drug Abuse; National Institute of Mental Health; National Institutes of Health; American Foundation for Suicide Prevention","keywords":"Preprint; Computer science; Protocol (science); Natural language processing; Data science; Artificial intelligence; World Wide Web; Medicine; Alternative medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08680401,0.005630994,0.0169388,0.01536914,0.004521702,0.007432463,0.005140284,0.008036912,0.05981105],"category_scores_gemma":[0.1333579,0.005015091,0.01624561,0.01279528,0.005301714,0.008504991,0.005925795,0.007160727,0.009609838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01683097,"about_ca_system_score_gemma":0.06842638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007680292,"about_ca_topic_score_gemma":0.01394347,"domain_scores_codex":[0.9424424,0.02388371,0.02075523,0.004097959,0.006460937,0.002359748],"domain_scores_gemma":[0.9221298,0.03171378,0.01717051,0.007848659,0.01888897,0.002248307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.003814396,0.0002141285,0.0006873694,0.9210994,0.002661913,0.000567708,0.001776105,0.001094338,0.001376086,0.005028212,0.03120937,0.03047107],"study_design_scores_gemma":[0.02159789,0.002021264,0.005706193,0.6955429,0.01214062,0.0006581553,0.002920842,0.00168185,0.002608579,0.01694093,0.2374661,0.0007146768],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.0003226307,0.002223125,0.001963668,0.0005469043,0.0003393281,0.9895023,0.004585635,0.0001000017,0.0004164734],"genre_scores_gemma":[0.0003235478,0.0008571946,0.002575793,0.0001845217,0.00002075347,0.995446,0.0003771514,0.00000807257,0.0002069614],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.08680401,"threshold_uncertainty_score":0.459069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6785737994058609,"score_gpt":0.7427247079090273,"score_spread":0.0641509085031664,"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."}}