{"id":"W4405021649","doi":"10.3389/fmed.2024.1495582","title":"Why we need to be careful with LLMs in medicine","year":2024,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Context (archaeology); Health care; Workflow; Psychology; Data science; Computer science; Political science; Geography","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":[0.0008573091,0.0002516741,0.0007561162,0.001327177,0.00004355333,0.000009900195,0.0001524322,0.0001626122,0.0004398417],"category_scores_gemma":[0.0005500394,0.0001694375,0.00003160016,0.00206856,0.0002903788,0.0001097421,0.00002169977,0.0006013085,0.00002839981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005006063,"about_ca_system_score_gemma":0.0002838954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006533895,"about_ca_topic_score_gemma":0.002184542,"domain_scores_codex":[0.9976054,0.00007260776,0.0007148026,0.0005223778,0.0005785861,0.000506184],"domain_scores_gemma":[0.9988806,0.0001705414,0.00004670392,0.0003945557,0.0001341057,0.0003735427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005609373,0.00008058256,0.05484234,0.0006096888,0.00004952402,0.0006712745,0.04051387,0.00004660962,0.0004019539,0.000306756,0.8182673,0.0836491],"study_design_scores_gemma":[0.0008195994,0.003839004,0.005903128,0.01232288,0.0002061567,0.0001727491,0.1157052,0.003074805,0.001067647,0.003166673,0.8532901,0.0004320663],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1902831,0.01880137,0.01306161,0.7633278,0.007419922,0.001417229,0.00000395284,0.0001706636,0.005514338],"genre_scores_gemma":[0.9511971,0.002084915,0.005021789,0.03590957,0.002818401,0.0001915375,0.00009306857,0.00008413998,0.002599435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7609141,"threshold_uncertainty_score":0.9877338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1052464033688267,"score_gpt":0.4055075634106417,"score_spread":0.300261160041815,"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."}}