{"id":"W4388101483","doi":"10.21203/rs.3.rs-3472000/v1","title":"Assessing the research landscape and clinical utility of large language models: A scoping review","year":2023,"lang":"en","type":"review","venue":"Research Square","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Toronto","funders":"","keywords":"CINAHL; Socioeconomic status; MEDLINE; Health care; Medicine; Harm; Political science; Psychology; Environmental health; Population; Social psychology","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":[0.1617002,0.002133927,0.008563584,0.03487777,0.0018784,0.009981709,0.005012624,0.00512825,0.005665761],"category_scores_gemma":[0.5062021,0.002726851,0.0107234,0.0233986,0.004611504,0.01161928,0.005997342,0.004201859,0.0008514629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01083772,"about_ca_system_score_gemma":0.03709386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01129884,"about_ca_topic_score_gemma":0.02363672,"domain_scores_codex":[0.8845629,0.06017304,0.03564553,0.005178944,0.01332557,0.001114001],"domain_scores_gemma":[0.3503734,0.5738368,0.03193383,0.008671032,0.03410626,0.001078614],"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":[0.0002638356,0.00005672775,0.002614345,0.7669559,0.009306568,0.0001925965,0.001290721,0.0008082814,0.000209832,0.003791539,0.004038531,0.2104711],"study_design_scores_gemma":[0.00005390543,0.0001031333,0.00116321,0.970669,0.01226355,0.0001437411,0.0006104852,0.0003593681,0.0001409923,0.002036861,0.01241475,0.0000409725],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001370496,0.9895687,0.002619331,0.003482522,0.0003765218,0.001138828,0.0004373399,0.00003312708,0.0009731847],"genre_scores_gemma":[0.04078802,0.9392703,0.01132945,0.002893534,0.0003971145,0.004333187,0.000725059,0.00005665607,0.0002066884],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.1617002,"threshold_uncertainty_score":0.8551627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8617398855202563,"score_gpt":0.7510169103430525,"score_spread":0.1107229751772038,"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."}}