{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04504124,0.0001944824,0.001582353,0.0004711701,0.0004757203,0.0001009369,0.0003414222,0.0004026831,0.0002003666],"category_scores_gemma":[0.01398296,0.0001176178,0.0003599992,0.002211951,0.0004758127,0.0001409116,0.0004258976,0.003123172,0.0001398441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009370031,"about_ca_system_score_gemma":0.004040938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004850813,"about_ca_topic_score_gemma":0.0002180987,"domain_scores_codex":[0.9899785,0.005348613,0.001569021,0.0006254981,0.001633467,0.0008448948],"domain_scores_gemma":[0.9851509,0.01173851,0.0002274427,0.001112935,0.001473755,0.000296455],"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":[0.000005779709,0.00008877826,0.0002323407,0.3825407,0.00003766892,0.00001815987,0.0003041839,1.271148e-8,2.267904e-8,0.00007302958,0.002549542,0.6141497],"study_design_scores_gemma":[0.00003363952,0.0002079547,0.00008833888,0.9423403,0.0001888482,0.00002127435,0.005823538,0.0004492204,8.544982e-7,0.0003197036,0.05041235,0.000114008],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002313392,0.9925157,0.00001584335,0.0009695924,0.0001272728,0.004887227,0.00002678643,0.00003769132,0.001188506],"genre_scores_gemma":[0.0009212032,0.9975956,0.00003718427,0.00004660032,0.0006149584,0.000342713,0.0001191725,0.00005310343,0.0002694619],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6140358,"threshold_uncertainty_score":0.9991767,"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."}}