{"id":"W4390571530","doi":"10.1007/s00246-023-03385-6","title":"Progression of an Artificial Intelligence Chatbot (ChatGPT) for Pediatric Cardiology Educational Knowledge Assessment","year":2024,"lang":"en","type":"article","venue":"Pediatric Cardiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; SickKids Foundation; Hospital for Sick Children; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Subspecialty; Medicine; Test (biology); Modalities; Chatbot; Stethoscope; Cardiology; Internal medicine; Medical education; Pediatrics; Medical physics; Artificial intelligence; Family medicine; Radiology; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003846735,0.001133766,0.0006506915,0.001362362,0.00088591,0.001713063,0.00216583,0.001722316,0.01578637],"category_scores_gemma":[0.01494023,0.0006647422,0.0005450628,0.0004503557,0.0004308406,0.0022315,0.002620595,0.002184485,0.007488136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009035622,"about_ca_system_score_gemma":0.002791013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004728237,"about_ca_topic_score_gemma":0.00495203,"domain_scores_codex":[0.9972067,0.001112359,0.000164331,0.0006280447,0.0006198529,0.0002686727],"domain_scores_gemma":[0.9876687,0.005326162,0.0003415712,0.001147698,0.002971333,0.002544468],"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":[0.003907594,0.0101763,0.02489246,0.001638902,0.0001695451,0.001897272,0.007148042,0.01003379,0.05951276,0.004744916,0.06616513,0.8097133],"study_design_scores_gemma":[0.001798174,0.01183851,0.08230077,0.001255879,0.0005056296,0.003539047,0.005538609,0.5287114,0.1360505,0.01179109,0.2157763,0.0008941126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4523934,0.0006365766,0.3484892,0.002147198,0.001099657,0.005709785,0.00487376,0.1476924,0.03695797],"genre_scores_gemma":[0.5396567,0.0001930849,0.4182249,0.0007434073,0.000135209,0.002141747,0.006710207,0.002281455,0.02991319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01578637,"threshold_uncertainty_score":0.05281073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1389619495919286,"score_gpt":0.4954971808345658,"score_spread":0.3565352312426371,"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."}}