{"id":"W4394951469","doi":"10.2196/53421","title":"A Multidisciplinary Assessment of ChatGPT’s Knowledge of Amyloidosis: Observational Study","year":2024,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Observational study; Multidisciplinary approach; Amyloidosis; Medical physics; Medicine; Intensive care medicine; Internal medicine; Sociology","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":[0.000327428,0.00007677316,0.0002480239,0.0001424283,0.00002598704,0.000005339748,0.00004791368,0.00005091968,0.0001304629],"category_scores_gemma":[0.00003080776,0.00006537929,0.0001230265,0.0003162466,0.00004152253,0.00004851853,0.00003185758,0.0001085286,0.00003245823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000083221,"about_ca_system_score_gemma":0.0004622302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001486862,"about_ca_topic_score_gemma":0.00002464652,"domain_scores_codex":[0.9991111,0.00004948731,0.000372074,0.0001753239,0.0001901549,0.0001019238],"domain_scores_gemma":[0.9993753,0.0001084324,0.00005051612,0.0002201664,0.0001883568,0.00005715702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005679334,0.001706394,0.9206499,0.001277197,0.0003350448,0.00001392494,0.02153216,0.00003810868,0.004124667,0.001628649,0.003342478,0.04529471],"study_design_scores_gemma":[0.0000767253,0.0007391476,0.9802574,0.0004707943,0.000123818,0.000007996133,0.009868041,0.002752501,0.002320572,0.0001723282,0.003127275,0.00008339455],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851587,0.000910999,0.0001855651,0.0004315877,0.00056002,0.0008794814,0.000007363432,0.00004519593,0.01182111],"genre_scores_gemma":[0.997125,0.00002287728,0.0003782747,0.00001000594,0.000315977,0.000194017,0.00001277187,0.00001986198,0.001921176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05960754,"threshold_uncertainty_score":0.266609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3116387691981336,"score_gpt":0.5349873825719419,"score_spread":0.2233486133738083,"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."}}