{"id":"W4392691776","doi":"10.1186/s12911-024-02459-6","title":"Assessing the research landscape and clinical utility of large language models: a scoping review","year":2024,"lang":"en","type":"review","venue":"BMC Medical Informatics and Decision Making","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":167,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto; University of Calgary; University of New Brunswick","funders":"","keywords":"CINAHL; MEDLINE; Health care; Medicine; Socioeconomic status; Political science; Environmental health; Population","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":[0.01763517,0.0001883548,0.00136645,0.0002179159,0.0001814764,0.0001411413,0.0001921526,0.0004155312,0.0001334008],"category_scores_gemma":[0.007097843,0.00009650741,0.0002372634,0.0005184387,0.0002314001,0.0001652204,0.0004040261,0.001370531,0.00002194144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002120317,"about_ca_system_score_gemma":0.002202368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001014469,"about_ca_topic_score_gemma":0.00003820562,"domain_scores_codex":[0.9951904,0.0003896953,0.002696495,0.0002221824,0.00120109,0.0003001212],"domain_scores_gemma":[0.9880611,0.0105601,0.0004057875,0.0004723247,0.0002457912,0.0002548365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00000432901,0.0000215665,0.00003355946,0.194721,0.00001648893,0.000004538934,0.0003177943,3.543996e-8,2.90808e-10,0.00010671,0.001109848,0.8036641],"study_design_scores_gemma":[0.0000386937,0.00005281378,0.000004149568,0.8748825,0.0004742555,0.0001327601,0.003117344,0.104978,2.134851e-8,0.0009766652,0.01524681,0.00009597219],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003961424,0.9789982,0.01827583,0.00005200264,0.0002895147,0.001159765,0.000005503684,0.00001707742,0.0008059315],"genre_scores_gemma":[0.0005064775,0.9911513,0.007588251,0.000414845,0.0002658596,0.00003186136,0.00001779546,0.0000163987,0.000007247318],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8035682,"threshold_uncertainty_score":0.8497294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6937181054312056,"score_gpt":0.6891676052751003,"score_spread":0.004550500156105253,"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."}}