{"id":"W4411373846","doi":"10.2196/76128","title":"Comparative Analysis of Generative Artificial Intelligence Systems in Solving Clinical Pharmacy Problems: Mixed Methods Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pharmacy; Intraclass correlation; Medicine; Artificial intelligence; Computer science; Family medicine; Psychometrics; Clinical psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00506045,0.000196598,0.001273874,0.000959733,0.00008573138,0.00003675246,0.0002485602,0.000203028,0.0001375445],"category_scores_gemma":[0.001301756,0.000159745,0.0001969918,0.002968036,0.0002845604,0.0001825151,0.0001035143,0.0007641717,0.00001921654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001562135,"about_ca_system_score_gemma":0.001026434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000745918,"about_ca_topic_score_gemma":0.0005932672,"domain_scores_codex":[0.9941746,0.000779574,0.003839805,0.0002133899,0.000667612,0.000325046],"domain_scores_gemma":[0.9965557,0.001731505,0.0005302709,0.0003705569,0.0005420297,0.000269895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004284094,0.005567808,0.1581827,0.001211781,0.002869471,0.00001474362,0.1586405,0.003786785,0.00008312006,0.004663796,0.001203474,0.6633475],"study_design_scores_gemma":[0.0001355295,0.0004528259,0.009577456,0.0004963069,0.0007938731,0.000002483271,0.1835493,0.80142,0.002340478,0.0004740643,0.0005951843,0.0001624892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8894498,0.00026588,0.1052576,0.0007227178,0.001091162,0.00198426,0.000004775339,0.00004083808,0.001182957],"genre_scores_gemma":[0.9927328,0.0001136772,0.006199678,0.0004724971,0.0001358091,0.0002577494,0.000037733,0.00000534338,0.00004467642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7976332,"threshold_uncertainty_score":0.6514214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3585744896393742,"score_gpt":0.6052675788860328,"score_spread":0.2466930892466586,"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."}}