{"id":"W4404393826","doi":"10.3899/jrheum.2024-0975","title":"Large Language Models in Rheumatologic Diagnosis: A Multimodal Performance Analysis","year":2024,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Ideological and Political Education","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Medicine; Intensive care medicine; Natural language processing; Physical therapy","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":[0.01478272,0.00172856,0.001695345,0.002837223,0.001155198,0.002567986,0.001429246,0.002360885,0.003517428],"category_scores_gemma":[0.03504406,0.0006065559,0.002104586,0.001621921,0.0008236349,0.002410004,0.002080986,0.002740123,0.001245901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001631073,"about_ca_system_score_gemma":0.001930304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01834258,"about_ca_topic_score_gemma":0.01780829,"domain_scores_codex":[0.9938825,0.004579,0.0002792025,0.0006556428,0.0003122647,0.0002912404],"domain_scores_gemma":[0.9447749,0.05151607,0.0007601334,0.001477653,0.0009153713,0.0005559001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003834953,0.001303265,0.06419925,0.0004490508,0.00214302,0.0007006546,0.0007232675,0.642451,0.002309722,0.006102259,0.01676842,0.2590152],"study_design_scores_gemma":[0.00005073425,0.0001182438,0.00452938,0.00002605744,0.0001774727,0.00006001026,0.000109174,0.9885439,0.0003606831,0.005553196,0.0004457384,0.00002535751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7717307,0.006578897,0.1995751,0.00706059,0.0002451231,0.0002353043,0.007556536,0.003337045,0.003680859],"genre_scores_gemma":[0.9715407,0.0005212086,0.01998512,0.0002299416,0.0001930514,0.0001172125,0.005664938,0.0001665862,0.001581212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01834258,"threshold_uncertainty_score":0.07817948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02012968155019597,"score_gpt":0.3283211079038516,"score_spread":0.3081914263536556,"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."}}